Ondine

Ondine was a nymph whose lover swore that his every waking breath was a testimony to his love of her. Finding him unfaithful, she cursed him – should he fall asleep he would stop breathing.

Marilyn died of an overdose of barbiturate sleeping pills (Tragedy). A bystander, Lou Lasagna, noted she had been denied access to a sleeping pill that was safe in overdose, the first pill of any sort that had been proven to work and be safe in an RCT before it was marketed. She was denied by doctors who put more weight on uncontrolled clinical observations than RCT data. As she died, she uttered a curse. Life went on. At first Lou noticed nothing but over the years his horror grew (Empire 1,  Empire 2).

Fishers

In the Spring of  1926, Ronald Aylmer Fisher, a lifelong smoker and denier of the idea that smoking might cause lung cancer, undertook some studies on the effects of fertilizers on seed growth in some fields outside Cambridge. Many factors could confound the results of a fertilizer study from differences in soil drainage, to the angle of the incident sunlight, exposure to wind and a myriad of soil elements that could only be guessed at. Fisher hit on a way to control both known and unknown confounders – he randomized the fertilizer to alternate seed and soil patches. And so the randomized controlled trial (RCT) was borne.

Fisher tied significance testing to RCTs. If we got the same result every time, we had designed a good experiment. There was a Quod Erat Demonstrandum quality to this – shave a bit off one side of a coin and you can expect heads to come up nineteen times out of twenty. He was looking for something close to a Euclidean Theorem – if you understand something the results will almost always be the same. But this insight on what Fisher meant by statistical significance, like most things about RCTs, has been inverted or perverted.

In 1947, Bradford Hill applied Fisher’s randomization to testing whether claims made for the efficacy of streptomycin for tuberculosis held up. He didn’t discover that streptomycin worked – others had done that in laboratories and clinics. But against a background of desperation and false claims, he showed that this time the claims could not be dismissed.

The RCT tide came in quickly after that and by the mid-1960s Hill noted that drug company salesmen ironically were encouraging doctors to use our products based on RCT evidence. While believing RCTs had a place in medicine, Hill noted that if RCTs ever became the only way to evaluate drugs that the pendulum would not just have swung too far it would have come off its hook.

Pharmers

RCTs have since been fetishized – made into a Golden Calf. Few can see any problems with bringing the rating scales and other measuring tools linked to them into clinical care – to make it more scientific. But just as with Midas, the touch of Gold brings death not benefit.

The pendulum has not just come off its hook, Pharma has picked it up and is battering people and governments over the head with it. We have recently had the close to degrading spectacle of the UK government in a parliamentary committee touting for Pharma “clinical trial business” and being told by GSK and Roche that UK clinical practices are just not Pharma friendly enough.

In this battering of people and governments, Pharma’s most useful allies are the proponents of Evidence Based Medicine, who insist clinical trials are if not the only way forward then by far the most useful way. RCTs, they indicate, would be just perfect if trial design was taken out of Pharma’s hands, if we had a registry of all trials done, and if we were let have a Witty-style peek at the data from time to time. It’s this fetishing of trials by independent academics that gives Pharma its grip over US and European governments.

Mediculture or Medicine?

For 80 years we have unthinkingly celebrated Fisher’s apparent managing of confounders. Many trumpet the ability of RCTs to demonstrate cause and effect. Few accept that these trials are simply association studies with a particular method for controlling confounders. Few guess that there are more disturbing problems.

Let’s return to whatever image an agricultural field outside Cambridge conjures up in your mind. Using her FishCam, Crusoe watched Fisher weed his patches of Rye, exclude all stones, meticulously ensure each of the A patches was the same size as the B patches and got the same amount of seed. After days of preparation, he allocated the fertilizer randomly and headed home to his pipe. (For more on Crusoe see The Girl who was not Heard). She saw him check the patches weekly and then on the night of June 1, just as the first plants were sprouting, she saw a Sprite arrive and sprinkle Pixie Dust on Fisher’s handiwork.

Some weeks later when there was clearly much more Rye growing on the A than on the B patches, and the Rye on B was moldy, she saw Fisher race out to invest in Company A shares.

Using her Sprite tracking App, Crusoe locates where the imp dwells and while he is out one night creating mischief, she sneaks into his tree-house, finds the bag containing the Pixie Dust, steals some and brings it home to analyse. And for good measure she borrows a pretty pink envelope lying beside it.

The Dust contains a mixture of MM Rye and MM mold. She opens the envelope and finds a message: If you chant these words on scattering the supercharged Rye will all land on the A patches and the mold on B:

‘Norma-Jeanne thou art, Marilyn thou wilt be, and Queen of Camelot hereafter‘.

Crusoe concludes that this can never happen in agriculture and there is no need to warn Fisher he’s at risk of losing his money. But she sees that this can and must happen in medicine, and that it won’t be spotted because medicine is a much more desperate business than agriculture. Human beings and diseases are not an inert field that you sprinkle fertilizer on. In medicine you give poisons that have effects on both a person and a disease that no randomization can control for.

She concludes that RCTs will be of limited use for testing medical treatments but she recognizes that the idea of a simple solution has irresistible appeal to desperate people and the invention of this idea makes investment in pharmaceutical companies worthwhile – because it hands companies the perfect way to market Snake Oil.

Standing back and surveying the clinical domain over seven decades she sees the value of RCTs as a marketing tool for pharmaceutical companies steadily grow until it far outweighs the value of trials to doctors testing treatments in clinical conditions. As this happens she notices one group of clinicians – those with least contact with the pharmaceutical industry – develop a delusional belief in the invincibility of RCTs.

These believers try to update GSK Chesterton’s (and Gandhi’s) message that it is not Christianity that has failed, it is Christians, substituting RCTs for Christianity.  She sees the annual Christmas solemnities of a people celebrating their control of confounders, and giving thanks to EBM, completely oblivious to the confounding produced by the Clinical Sprite that cannot be overcome.

The Clinical Sprite

Imipramine, the first antidepressant, was discovered in 1957, the year Fisher left England for Adelaide. It was launched in 1958 – not an RCT in sight. A year later in 1959, three years before Fisher died of cancer, and a few miles away from his patches of ground, a meeting of psychiatrists was convened in Cambridge to discuss its effects.

At this meeting, some doctors, mainly Danes, noted on the basis of the Christmas Tree lightbulb test that wonderful though it was for many of their patients imipramine could trigger suicidal and homicidal ideation in some (See Time to Abandon Evidence Based Medicine at 38 minutes et seq).

When Christmas Trees had old style light bulbs, after a year laid up there was an annual drama as the lights failed to work. Unscrewing them sequentially would finally lead to one which when unscrewed lit them up. Screwing that bulb back in turned them off again. Jettisoning this bulb fixed the problem, even more conclusively than Fishers nineteen heads out of twenty.

So imipramine causes suicide. But it is also a far more potent antidepressant than Prozac, or any subsequent antidepressant. It got people with melancholia well where later drugs don’t. Melancholic patients are 80 times more likely to commit suicide than mildly depressed patients – according to studies drug companies cite.

Accordingly comparing imipramine and placebo in an RCT would likely show less suicides and suicidal acts on imipramine than placebo. The relative risk might be 0.5. Imipramine protects against suicide.

Had an RCT been done showing no risk on imipramine, we cannot know for sure what effect it might have had on the doctors in Cambridge, celebrating imipramine’s benefits but acutely aware of its hazards.

But some hints come from an RCT four years earlier, in 1955, which found reserpine worked well for depression and caused no suicidality. The immediately preceding articles in the Lancet were Christmas Tree light bulb reports of it causing suicide from Geelong and Dunedin. Where? The field didn’t need an RCT to know that reserpine could be useful. In the face of an RCT from the most distinguished Institute in the world showing no problems, doctors still had no difficulty believing reserpine could cause suicide on the basis of light bulb reports from goodness only knew where. If asked what they made of these new-fangled RCTs, most clinicians would almost certainly have said “interesting but hardly clinically relevant”.

It took a political impasse about drug regulation in 1962 and the need to find something simple enough for bureaucrats to work with to produce the primacy that RCTs have now. Something signed into law by Marilyn’s lover, nine weeks after her death and ten weeks after Fisher’s, that put the lights out on the Christmas tree.

The Sprite’s RCT

The findings of our imipramine thought experiment are represented in figure 1. These are the findings even though the drug causes suicide.

Figure 2 shows the findings for suicides and suicidal acts in SSRI trials.

In these trials we get a relative risk that the drugs will cause suicide and suicidal acts of 2.0. This happens because SSRIs are much weaker than imipramine and so were tested in people who were mildly depressed at little or no risk of suicide. When the findings got to be statistically significant, the regulators seemingly felt obliged to agree that the SSRIs caused suicide and came out with a warning to that effect.

The regulators were wrong. The data in this SSRI population show the drugs produce an excess of suicides over lives saved. They say nothing about causality except in so far as there could not be an excess of suicides if the drugs didn’t cause suicide. In the case of the SSRIs and suicide, the evidence comes from Teicher’s 1990 Christmas Tree light bulb paper on Prozac and suicide – and earlier cases.

The first point to make is this is not confounding by indication.

The second is that despite mantras to the contrary, RCTs do not and cannot show cause and effect.

The third is that they do not even give useful data on frequency. We in principle cannot have any idea from RCT figures how often antidepressants trigger suicidality.

But here’s the real deal. This finding is not an inconvenience that stems from some oddity to do with antidepressants or suicide or drug companies. It is intrinsic to RCTs within medicine. It can be expected every time a treatment and an illness produce at least superficially similar outcomes – whether a benefit or a harm.

It happens to cardiac rhythm problems in trials of anti-arrhythmics given for cardiac arrhythmias, and to breathing difficulties in trials of anti-asthmatics given for asthma. It happens with vaccines. It happens to the benefits of treatments just as much as their harms.

It holds as true for completely independent RCTs with hard outcome measures, no surrogate outcomes, complete data access, and intention-to-treat analyses, in long duration or short duration studies, as it does for industry studies.

It means that notions of Numbers Needed to Treat (NNTs) or to Harm (NNH) or even treatment effect sizes are for the most part little more than empty statistical artefacts, except in so far as they apply to dead bodies.

Patients can in fact distinguish between depression induced and drug induced suicidality or between antidepressant induced and spontaneous recovery from depression – if we ask them. Patients can tell you if a drug is ‘working’ even if its not ‘working’ – as when they say this SSRI is producing a useful emotional numbing even though it’s not making much difference overall. It is only if you listen to the patient that you can know whether to add another Therapeutic Principle into the mix or whether you should stop the drug they are on and try another.

Having your ears stopped to what the patient says, with the poison of “this is anecdotal data”, is a way to turn your patients into ghosts who must wander abroad seeking someone to come to their aid.

Cardiologists can also distinguish between drug and illness induced arrhythmias.

But if we believe a patient’s answers or a cardiologist’s clinical experience, RCTs immediately shape shift from gold standard evaluation to gold-plated but often misleading association studies.

So, who does not asking patients suit most?

The only trials that the Clinical Sprite cannot confound are Drug Trials. These trials of a drug done in healthy volunteers reveal unconfounded drugs effects.  But there is no register of these trials, and no access to their data even though there are no issues of clinical confidentiality involved.

The Clinical Pixie

The Clinical Sprite has a sister – the Clinical Pixie.

In the late 1980s, Eli Lilly undertook a trial of Prozac in a group of patients with recurrent brief depressive disorder (RBDD). In this trial placebo was sweepingly statistically superior to Prozac. The study was published four years later shorn of all key data.

In the early 1990s, SmithKline Beecham (GSK 2B) undertook study 106 of Paxil – Prozac’s sister SSRI in the same hospital centre, in the same RBDD patients, possibly with some of the same patients who had been in the Prozac trial. This second study terminated early.  The results were never published. The rate of suicidal acts on Paxil (Paroxetine) was three-fold higher than on placebo.

Nevertheless a few years later GSK 2B undertook study 057 in a similar group of patients. Several different sets of results from this trial circulate, none of which support using Paxil in this group of patients.

In April 2006, GlaxoSmithKline (GSK Not 2B) issued a press release with the following figures for suicidal acts in the Paroxetine trials in Major Depressive Disorder.

Suicidal Acts in MDD Trials

The MDD patients show a significant increase in the suicidal act risk on Paroxetine. But even though the results of studies 106 and 057 were so bad, GSK Not 2B gleefully added them in to the mix – and when they did so Hey Presto the risk from Paxil vanished. It can even be made protective against suicidal acts (See Table 2).

Suicidal Acts in MDD & RBDD Trials

We can dump lots more suicidal acts into the RBDD trials and still get the same magical outcome – see Table 3.

Suicidal Acts in MDD & RBDD Trials w Sprite

This paradoxical outcome is not a funny quirk of antidepressants and suicide. It is totally predictable and obvious. I could have advised GSK-2B or Not 2B to do studies 106 and 057 to get this outcome. Knowing what a drug can do, you can often design studies that use a problem the drug causes to hide that very same problem.

Now the pillars of the EBM establishment, so used to dealing with the scurvy knaves from Pharma, look at this and say it is just bad meta-analytic technique – you shouldn’t mix studies like this. And you shouldn’t. There is a horrific scandal here – FDA, MHRA, and the luminaries of EBM have let GSK Not 2B get away with this without a peep of protest.

But there is a deeper problem. We can see what is going on here. But exactly the same thing can happen by accident in clinical trials done in every illness we don’t fully understand – from pain to Parkinson’s Disease.

RBDD patients can meet criteria for MDD easily. Provided there is more than one of them entered into MDD trials randomization will ensure these Pixie patients will hide some benefit or harm.

Unlike fertilizers, drugs have a hundred or more effects. When we Design an Experiment employing randomization to manage the unknown unknowns for one of these effects, we risk generating an ignorance about ignorance regarding most of what the drug in fact does, and sometimes even for the effect we are focused on. This is true for statins, antibiotics and all drugs – not just antidepressants.

Pharmagnosia

Generating ignorance about ignorance is a serious clinical problem – for which pharmagnosia seems a good term. If a good medicine is a chemical that comes with good information, then RCTs through pharmagnosia are leading to a systematic degradation of our medical arsenal.

All RCTs do harm. Some do good as well. Pharmagnosia is worth risking when there are grounds to think a claimed benefit does not hold water and if wrong vulnerable patients are likely to be harmed. If the drug doesn’t work, we don’t CReate Ignorance in MEdicine (CRIME).

The only way to get the result Fisher would have insisted on for the main effect of a drug rather than a fertilizer, that is the same outcome every time, is to understand the clinical condition you are treating and the agent you are using so that you produce a Quod Erat Demonstrandum – this treatment works every time or no it doesn’t work.

But if we understand the clinical population this well, RCTs come close to being irrelevant to moving decent medicine forward. Their main value lies in dealing with the claims of hucksters and charlatans.

The Clinical Pixie looks like Tinker-belle but she is a not a benign fairy. There are far more MDD patients that RBDD patients in this world. If you spot what she has done in this case, you can see that the results show the drug harms more people than not.

But if you don’t spot what she has done, she will beguile you if you are a public health official or regulator into supporting a treatment in front of the press saying it has a favorable risk benefit ratio by which you mean produces more benefit than harms on a population basis. You will do this although in fact the treatment is cripplingly bad for far more patients than it benefits.

At a rough guess, 90% of these pronouncements by regulators are wrong and 99% or more are lacking in appropriate supportive evidence.

One of the most egregious examples of this came recently in a Cochrane review of Statins that focusing exclusively on their lipid lowering effects, neglecting their effects on muscle, endocrine and cognitive function, concluded that the evidence supports their use (Cochrane Library 2013, Issue 1). Only time will tell which of the current blockbuster drugs will in the longer run take the title for the drug group that has caused the most damage but the statins are worth betting on.

In Elsinore

Within the walls of the Elsinore, the citizens of EBM remain at ease. As far as they can see the only Sprites that might confound clinical trial results are those scurvy knaves who work in the pharmaceutical industry. The citizens still believe that the suicide risks of antidepressants were discovered in clinical trials done in children, not knowing that trials were actively and likely deliberately used to hide an obvious link for fifteen years.

Within the Citadel, Claudius has decreed that anyone who seems to question the primacy of trials should never be engaged in public, can be attacked in ad hominem fashion, or failing all else should be consigned to the Antidepressants & Suicide Chamber, on the door of which there is a notice Here be Sprites.

Lethe, the river of forgetfulness runs through EBM. What need is there for History. Things could not have been better in the past. Fisher’s texts are revered as they lie sealed in a glass cabinet. No-one can find out that he was looking for a Christmas Tree light bulb equivalent. They don’t even know he was dealing with agriculture not medicine.

In the Real World, outside the Castle, the one foot on the ground world, RCTs can be seen to function in medicine primarily as a rhetorical device giving the impression that if a drug has passed through them, a patient will get the same beneficial outcome time after time, even when in fact in 80% of the trials the drug has performed worse than placebo.

Cut to the battlements of Elsinore, where a man stands paralyzed with fear by the approach of what his fevered imagination sees as a ghost. The ghost of a beautiful woman. Frozen with fear, he murmurs:

Illustration: Put-Me-to-Sleep Pills, © 2013 created by Billiam James

You and your meds Give the real story. Get the real story.

© David_Healy for Dr. David Healy, 2013.

Faced with questions about the $3 Billion fine imposed on GSK – is it just the cost of doing business? Andrew Witty snapped back:

“Although corporate malfeasance cases end up looking very big, they often have their origin in just… one or two people who didn’t quite do the right thing. It’s not about the big piece. The 100,000 people who work for GSK are just like you, right? I’m sure everybody who reads the BMJ has friends who work for drug companies. They’re normal people… Many of them are doctors.

Panalba

The current action against the European Medicines’ Agency (EMA) in the European Court is the first time Pharma has taken the regulator to a Supreme Court since the Panalba case (see Tragedy).

The 1962 amendments to the Food and Drugs Act required a determination of efficacy for any drugs marketed. In the case of drugs that had been licensed prior to 1962, FDA put in place a Drug Evaluation Study Initiative (DESI) to determine if they were likely to be efficacious. DESI convened panels of academics to adjudicate on these drugs.

FDA and many academic physicians, including Louis Lasagna, did not approve of combination products, whether antibiotics, analgesics or psychotropics of which there are plenty on the market. DESI recommended removing a large number of these. Lasagna’s career changed forever when he came out against this recommendation (see Tragedy).

In 1969, DESI recommended removing Upjohn’s Panalba, a combination of tetracycline and novobiocin. By FDA’s calculations Panalba was likely responsible for 12-15 deaths per year that wouldn’t have otherwise happened if doctors had used tetracycline alone. At the time Panalba was making $18 million per year for Upjohn – 12% of their income; $1 million per death. There was evidence that Upjohn knew of the risks the drug posed and in house evidence that Panalba was no more effective than tetracycline alone.

The options for Upjohn were:

1. to pull the drug immediately from the market,
2. to stop production but let doctors use up the supplies available,
3. to continue to produce but stop marketing,
4. to continue to produce and to promote until it was actually banned,
5. to attempt to overturn FDA’s decision using the Government and Judicial System

The company chose option 5. It involved the Secretary of State for Health in the Nixon Administration and pursued a legal action all the way to the Supreme Court.

When the details of the case were presented some years later to business management students in the University of Pennsylvania, Scott Armstrong found that none of his class supported Upjohn and all bar two of the 71 found Upjohn’s behaviour irresponsible.

But when he got students to role play the Upjohn Board and faced them with the decision to pull the drug or not, he found to his astonishment that 79% of respondents opted to take the same course of action as Upjohn and none withdrew the drug. This result has been widely replicated in different national groups with socialist Swedes behaving the same as capitalist Americans, and the idealistic young in just the same way as their cynical elders.

Debriefing the subjects and attempting to adjust the board and the circumstance to see if behaviour could be modified, Armstrong and others were left with the conclusion that it is generally accepted that the primary duty of Board members is to stockholders rather than to society at large. Board behaviour can be modified by appointing stakeholders but even then few Boards opt to remove Panalba from the market.

Armstrong modified the role play experiments by introducing an Upjohn safety officer who told the Board that the company did have hidden evidence supporting the complaints – to no effect. In real life not even the death of the CEO’s wife from suicide, from the Company’s drug Prozac, has led to a decision to pull the drug or add warnings.

Putting people in a group where the unstated assumption is they will behave like a proper Board produces a situation which has commentators reaching for comparisons with the Milgram experiment where decent ordinary people in experimental settings can be induced to give life-threatening shocks to innocent strangers simply because they are asked to do so by the conductor of the experiment.

The only thing that appears to modify the likely behaviour of a Board is a threat of boycott – that is if maintaining the drug on the market led to a disenchantment that led the company share price to fall.

While accepting Andrew Witty’s suggestion that he and other employees of GSK are just like us, few of us can imagine being party to behaviours that warrant a $3 Billion fine. But from this study it seems we are more like him than he is like what we might like to think of ourselves.

GSK’s proposals for transparency need to be read against this background – is the company really offering to do the equivalent of remove their drugs from competition? Or are GSK just a little bit smarter than the competition?

When faced with the growing Fascism in healthcare, we can retreat to the wilder shores of conspiracy theory and claim the problems are down to the Germans, the Jews, or a Socialist cabal. Or we can attribute the problems to some evil people somewhere in pharmaceutical companies who break laws.

But if we accept that the Board of GSK and other companies are populated with people just like you and me, who are perhaps even less likely to break the law than you or I, the $3 Billion fine for GSK notwithstanding, then the problem must stem from and the remedy lie in the system.

Witty A: Report to the President on Changing the System

(Accounts of what led to the 2017 Amendments to the Food and Drugs Act vary wildly. Some say the President’s first grandson was born with Tetralogy of Fallot linked to his daughter’s antidepressant intake. Conspiracy theories invoked Marilyn’s Curse. They noted things like the coincidence of initials between the unknown American Woman whose baby had a Tetralogy of Fallot and Andrew Witty (See AW and AW2). Others thought it was triggered by the fact that the previous President had to step down early because of cognitive failure linked to treatment with a Statin. Whatever the reason, Andrew Witty was recruited from GSK to become special advisor to the White House on how to change the system. Here is a précis of his option appraisal).

1). Regulation & Science

The licensing of drugs is a bureaucratic procedure that has nothing to do with science. As things stand, this procedure has enough of the appearances of science so that most doctors and patients taking part in it are fooled into thinking they are participating in scientific exercises when they are not.

Regulation is incompatible with science. Science seeks uncertainty, whereas regulation seeks to abolish uncertainty.

That Pharma does regulation not science should have been crystal clear in the legal action taken by Pharma against the EMA (2013), when Pharma took the option to stress that their “data” was simply the result of a regulatory exercise and regulators ordinarily maintain the confidentiality of submissions on products they regulate. This was the winning option.

There were doubts within Pharma about their ability to win using this argument while maintaining the illusion that companies do science. The argument was a bitter blow to the self esteem (amour propre) of FDA and EMA who liked to claim they based their actions on science. But medicine predictably noticed nothing.

2). The 2017 Amendments to the Food & Drugs Act

Regulation needs to be disentangled from science, but this cannot easily be done while the 1962 Amendments to the Food and Drugs Act contain an effectiveness criterion. This was a well-intentioned but unfortunate accident – a simple solution to a complex problem that has made things worse.

In the new regulations to mark the 55^th anniversary of the 1962 regulations the word effectiveness needs to be replaced by phrasing to the effect a drug should have a clear effect on a structure or function of the body. This falls back on language already in the regulations so should not be unduly problematic.

This would have the merit of making it a lot cheaper to develop new drugs. As a result, the cost of drugs would fall, more new drugs would be brought on the market and after marketing a lot of discoveries would be made. We could look forward to a new era of Wonder Drugs to rival the 1950s.

There would be comparatively little clinical trial data and campaigns like BMJ and the Cochrane collaboration to access the data would likely wither on the vine. It would be safe to appoint Peter Doshi and Tom Jefferson as data access Csars.

3). Evidence based Medicine

The determination of treatment effectiveness is critical to the rational practice of therapeutics. It cannot be left to industry; it should not involve industry. If undertaken properly by medicine, as for instance in trials like the Women’s Health Initiative study of HRT or NIH studies of drugs from tolbutamide onwards, it would likely mean that a full appreciation of the risks and scale of the benefits to be obtained from a treatment would only be realized five years after the initial launch of a new compound.

4). Prescription-only Arrangements

Quite simply these need to be dismantled. Anyone who doesn’t understand this doesn’t understand marketing.

If prescription-only privileges are to be retained, only those who do understand the need to abolish them should be involved in any modification. There are a range of possible modifications such as requiring doctors to have a training post in a company marketing department before qualification. There is talk of rewarding them for reporting adverse events – better to penalize them if they do not report them at a certain rate per year.

Another is to maintain certain drugs on prescription-only status such as chemotherapies for cancer where patients are particularly vulnerable and the treatments particularly toxic.

5). Abolish Medicine

Although companies are engaged in exercises that are simply bureaucratic, they have captured the appearances of science, more successfully than alchemists, homeopaths or others, and using these appearances they have been able to infect the body of scientific therapeutics. The insertion of what are essentially sophisticated adverts into the medical literature has triggered a Clinical Auto-Immune Deficiency reaction leading many doctors and scientists to attack those who question the results of ghostwritten articles that purport to represent “studies” whose data is withheld.

Physicians have had decades to find a way to get this cuckoo’s egg out of the nest of science. They could have based clinical practice only on investigations whose data is publicly available. They could have used the Human Rights of their patients as a lever – it is not for instance possible for any doctor to prescribe any branded medicine with informed consent as things stand at present.

But they haven’t done anything like this. The branches of medicine linked to the prescribing of branded products are finished as a profession. They have no brand value. The market has now developed so that nurses, pharmacists, clinical psychologists and others could take over the role of prescribing and will be far less expensive.

If we believe in the market place, abolishing medicine will lead to a solution in that people and governments will realise that they need a set of experts who have brand value when it comes to good quality information on drugs and a new profession will be called into being.

There already was an effort in this respect by a Hungarian emigre to Canada, some ten years ago, to form a First Multinational Corporation of Physicians. This prototype could be dusted down, or another assembled.

Other physicians practicing in areas of medicine where branded products have had little penetration could be allowed to continue. One caveat here is that I have not considered whether areas of medicine that are heavy users of medical devices or medical procedures are as badly affected as mainstream medicine.

A further option might be a promotion of patient co-operatives. Groups like ACOR.org are making a significant difference to healthcare. They might find it far easier to work with nurse and pharmacist prescribers than with doctors.

6). Boycott

One of the few things that might have influenced my behavior as CEO of GSK would have been a boycott. Record fines and even jail time are not deterrents. Almost everyone views these as a cost of doing business already. A jailed CEO might even boost share value.

We in GSK know that boycotts can hurt. The crisis over making ARVs available to South Africa for AIDs and the threat of a boycott was the only time our Board substantially altered its position.

Tied as they usually are to disease indications that don’t exist, and surrogate markers, and produced as they are for bureaucratic purposes only, company efficacy data are frankly close to worthless and are not what companies have been trying to hide anyway. The key data have always been the adverse event data.The boycott would be aimed at getting companies to hand over Adverse Event data.

7). Boycott – 2

In 1962, all of the wrong options from Kefauver’s proposals were picked – the effectiveness criterion, prescription-only arrangements, and controlled trials. The change he most favoured, a revision to the patent arrangements, was rejected.

Modifying patent arrangements is an indirect form of boycott that Congress should consider. Companies need to be rewarded but the current product patents reward them excessively for treatments that often shorten life and increase disability. There are alternate arrangements, such as process patents, that would make the various Panalbas less valuable and put a premium on diversifying the portfolio of compounds companies hold rather than have them dependent on a small number of blockbusters.

8). Access to Data

There are at present thousands or hundreds of thousands of drug trials that remain completely unregistered, where there are no issues of clinical confidentiality. These are studies undertaken in healthy volunteers – normals. There is a compelling cases for ensuring these data are made fully available. Companies will need an amnesty for some of the abuses of people that will come to light as these studies come into view.

9). Independent Adverse Event Reporting

This is the key step. The steps companies have taken to prevent decent reporting, or to denigrate reporting when it happens, and to manage the perception of risk rather than risks themselves, make everything else they have done pale in comparison.

For instance companies supported the development of an FDA MedWatcher App in 2013. Widely applauded, this was in fact a way for companies to reduce the expense of maintaining a pharmacovigilance department, reduce their legal liabilities, and transform adverse events into anecdotes. Companies you see have a duty to follow up and decide if their drug caused the problem – FDA don’t have this duty.

But what was astonishing about all this was that pretty well everyone completely bought the idea that when it comes to working out whether a drug has caused a problem, a bureaucrat in FDA who is there because they don’t like meeting patients, has never treated the condition you have and never used the drug you are on, would be better placed than a good team of doctor, pharmacist and informed patient perhaps in touch with other good teams, to work out what’s going on.

If you can get people to buy this, who knows at a push they might even buy the idea the earth is flat.

Unless a patient organization gets involved in assembling real-time data and both doctors and patients combine to put risk mitigation programs in place, none of the other changes will work.

The bottom line is the average drug has at least 100 effects. Using clinical trials we have been hugely successful in hypnotizing doctors and patients to focus on one effect and to miss the other 99. This pharmagnosia is a major driver of Pharmageddon (See Marilyn’s Curse). If the climate change encroaching on healthcare is to be rolled back, we need to manage pharmagnosia.

We can still have a market solution but it needs to be a Comparative Safety market rather than a Comparative Efficacy market.

You and your meds Give the real story. Get the real story.

© David_Healy for Dr. David Healy, 2013.

Faced with questions about the $3 Billion fine imposed on GSK – Is it just the cost of doing business? Andrew Witty, GSK’s CEO, snapped back:

“Although corporate malfeasance cases end up looking very big, they often have their origin in just… one or two people who didn’t quite do the right thing. It’s not about the big piece. The 100,000 people who work for GSK are just like you, right? I’m sure everybody who reads the BMJ has friends who work for drug companies. They’re normal people… Many of them are doctors”.

This interview came about after an earthquake. For 50 years since 1962, the tectonic plates of regulation and science had been grinding up against each other. This led to an eruption in 1987, a quarter of a century after 1962, when pressure to get drugs on the market for AIDs led to a regulatory crisis. Lou Lasagna was called in to chair a committee to find a way forward. This ultimately led to speedier drug approvals and the Prescription Drug User Fee Act (PDUFA), whereby to the dismay of many industry ended up paying the FDA piper. This crisis played a significant part in the development of GSK, whose rise to global dominance was linked to AIDs treatment.

A quarter of a century later again there was a further eruption. For years there had been evidence of growing pressure on the fault-line between regulation and science with a range of campaigners pressing for access to clinical trial data. Then Peter Goetsche from Copenhagen hit pay dirt when he secured a ruling from the European ombudsman that the European Medicines’ Agency had no option but to make trial data available to anyone who applied for it. For a brief period, researchers could access the data from any trials held by EMA. It was other companies who in fact applied most often for the data.

The BMJ launched a campaign to ensure that rights of access to trial data would be maintained. The centrepiece of their campaign was Peter Doshi and Tom Jefferson’s efforts to get access from Roche to the data on Tamiflu.

Witty appeared to give a boost to the campaign by promising access to GSK’s trial data. The BMJ featured him on their front cover in Barack Obama political poster Shepard Fairey mode with the word HOPE underneath and a strapline – GSK’s Andrew Witty…The acceptable face of big pharma? They noted inside that, in response to his commitment to make data available:

[Witty] was singled out for praise by one of the industry’s harshest critics with Ben Goldacre calling it a “cartwheel moment”.

Many thought Pharma appeared split. Witty, the acceptable face of big pharma, appeared to be in favour of transparency but other companies filed an action against EMA in the European Court for infringing among other things their right to privacy, right to confidentiality, copyright and violation of legitimate expectations. The first time Pharma has taken the regulator to a Supreme Court since the Panalba case (see Tragedy and Witty A).

So if the problem is not bad people what is it that needs treating? Andrew made the point that there are few differences between him and us. But he wasn’t asked to take off a GSK hat, and answer as someone with a healthcare problem whether any of the points below that concern some of us would concern him. He wasn’t asked to distinguish between the efficacy of the current system in getting GSK’s drugs to market rather than its effectiveness in maintaining your and his health.

Neo Fascism

“This is your last chance. After this, there is no turning back.  You take the blue pill – the story ends, you wake up in your bed and you believe whatever you want to believe”.  Morpheus to Neo in The Matrix.

Having taken the Red pill, Neo wakes up to find the following:

1. A Gulag Archipelago:

Trials in branded pharmaceuticals from 1960 to 2000 were done in Western clinical centers where the patients did not always exist. Publications based on these non-existent patients litter the academic literature without retraction or even a cautionary note in the case of trials where it is known the patients didn’t exist or the investigators have been jailed.

Since the mid-1990s trials have increasingly been done in South Africa, Russia, India and other countries were patients have little idea what is going on and where if the patients exist and are injured they are routinely lost to follow-up.

2. The Disappeared:

In this case the Disappeared are those suffering from treatment induced deaths and disabilities. The means of disappearance range from elaborate methods to avoid collecting the data, to concealment of evidence and of company determinations that our drug caused that, to statistical and controlled trial techniques to make deaths and injuries vanish.

Treatment induced death has become at least the 4^th leading cause of death, perhaps even the normative mode of death, but there are no concerted efforts to tackle this.

The lengths to which companies go to get an efficacy message out – ghostwriting trials, hiding data, and legal threats – pale in comparison to what they are prepared to do to hide or deny responsibility for the bodies of the Disappeared (See American Woman, American Woman 2).

This now extends to a growing number of children with birth defects miscarried or born to suffer and be stigmatized. We seem very unlikely to get a religious leader, Papal or other, willing to speak out about this.

3. Upper Volta with Biologicals:

Effective treatments should lead to a reduction in healthcare costs and in levels of disability but healthcare costs and levels of disability are rising. We have some very sophisticated drugs but behind the high tech façade healthcare is crumbling with patients in some cases more scared to go into hospital or even see a doctor than they have been for close on a century or would be in a Developing Country

(Helmut Schmidt in the 1980s described the Soviet Union as Upper Volta with Missiles).

4. TRIPs Pact Bloc:

Most Western countries have signed up to TRIPs which maximises pharmaceutical company profits to an extraordinary extent. It also puts in place a range of punitive sanctions should a country deem the needs of their citizens outweigh the right to profit of a pharmaceutical company.

Aside from the punitive sanctions, if a country does not support their marketing, companies threaten to relocate their operations elsewhere. Countries (viz. the UK) will do almost anything to keep a company operating within their borders – even offering up their citizens as all but involuntary participants in company trials that are run by doctors whom the taxpayer has educated and salaried. And these clinicians  who used to be the critics and conscience of society have been told they must partner industry.

5. Tuskegee-es-kay:

Consent forms were put in place in industry studies by Louis Lasagna in 1962 as a means of safeguarding patients. These have been transformed into an instrument of legal jeopardy, with patients unwittingly consenting that their data will be hidden from everyone for ever.  This means that even when people have been injured in trials companies will say in public and in court we have no evidence for any injury on our drug.

Studies are undertaken on drugs that almost certainly have been undertaken in the knowledge that the drug causes death or injury and detailed knowledge of this hazard has been used to construct RCTs that will help hide the hazard. Neither the patients nor other doctors involved in such trials have any idea what is going on.

6.  Ministry of Truth:

Close to all of the published literature about on-patent drugs is ghostwritten. Prestigious medical journals have encouraged this for the last 30 years. In terms of ensuring the integrity of the primary sources of a story and ensuring the authors are who they appear to be we would all be safer if clinical trials were published in the New York Times than in the New England Journal of Medicine.

7. Censorship:

Even the most prestigious medical journals are scared to publish articles raising hazards about drugs, or even articles by anyone identified as someone who raises issues about treatment, for fear of legal action from companies. The situation is every bit as bad as the level of censorship in the former Soviet Union.  Anyone who has tackled pharmaceutical companies on the one hand or Dan Brown’s Angel and Demon Vatican, knows that the Vatican is kids play compared to Eli Lilly or Pfizer.

Academic journals and societies show an auto-immune response to what should be the life-blood of therapeutics.

8. Propaganda 101:

Not only has most of the academic literature become one big advert for branded pharmaceuticals but when hazards are raised, companies have learnt how to use any concerns about a drug as a means to increase sales of the drug, and as a means to bind even more doctors ever more closely to the company bosom.

After lecturing about the suicide risk on Prozac a decade ago, I was greeted warmly by a woman who said she was responsible for PR for Prozac in the UK and she was really pleased to meet me as I was doing more for the sales of Prozac than anyone else.

9. NewSpeak:

Regulators never take it upon themselves to establish if a drug has a hazard. Their role is to manage risks. This does not mean that they warn about a hazard a drug might pose.  It means they manage public perceptions or beliefs about a risk. Doubt is their product.

In the case of thalidomide the possibility that it caused birth defects met a regulatory response as to whether we have ruled out the possibility that it prevents the miscarriages of babies with birth defects. In the case of Matt Miller, a 13 year old boy who hung himself a week after going on Zoloft, it met a response that we cannot rule out that this was auto-erotic asphyxiation gone wrong and until we can it would be a mistake to blame the problem on Zoloft.

10. Una Duce, Una Voce:

Guidelines depend completely on the published ghostwritten literature on which all data has been withheld. Once guideline makers treat company articles as though they are science they allow their guidelines to be captured by Pharma. By skilful publication strategies Pharma can always ensure that their latest on-patent drug features on top of the most independent guidelines. Economic pressures have forced a standardisation of healthcare in an effort to contain costs and this has transformed what was guidance into tramlines. These tramlines increasingly dictate what doctors have to prescribe.

11. Stasi-Style:

Anyone raising the profile of a drug’s hazards is likely to get harassed, marginalized or terminated. The harassment will include having people in the audience to challenge everything said, reviewing everything written to see does it provide the basis of a legal suit, actively targeting and spreading malicious gossip and disinformation through PR networks, calling colleagues or friends to “get the dirt”, “reading everything you have ever written Dr”, triggering tax inspections etc.  We just need a viral video clip to compete with Gangham-Style.

12. Medical McCarthyism:

Anyone talking about the hazards of a treatment is marginalized by their clinical colleagues and any group seeking a balanced approach to treatment is likely to be stigmatised as Scientologists or as Ideological.  This creates a Spiral of Silence where others observing what happens learn to remain silent.

13. Scienceology:

The norm in science is that there is free access to the data underpinning experiments. If free access is denied, it’s not science. In the case of branded pharmaceuticals, we do not even know what trials have been done. There is a denial of access to any raw data from any clinical trials. We have even less knowledge of what drug trials (healthy volunteer trials) are done and again no access to data even though there are no issues of clinical confidentiality. What is put in the public domain is not data. What will be put in the public domain under Andrew Witty’s proposal is managed access which is likely to be worse for everyone than no access.

The selected highlights of a football game and the comments of the pundits afterwards don’t change the score. The selected highlights of Pharma studies and the comments of pundits routinely change the score.

Any attempt to seek substance behind the rhetoric is likely to lead to vilification, intimidation and harassment.

14. Biobabble:

Clinicians and the public are routinely sold a biobabble about drugs and diseases that is as ideological as anything found in Soviet Lysenkoism. The problem in this case doesn’t lie in the biological sciences it lies in the social sciences and anthropology as well as the humanities which have been used to produce an informational reductionism and standardization on the one side and to develop marketing on the other. (For a first use of Biobabble – see 1999).  

15.   The Five-Year Plan: 

Instead of the old-Soviet style Five Year plan we have the rolling marketing campaign linked to patent expiration. In sequence people have to be persuaded they are anxious, then converted to depression, and after that converted to bipolar disorder, or moved from pain plain and simple to fibromyalgia, or from ulcers to GERD.

Linked into the same processes, doctors are rewarded with financial incentives for adhering to guidelines for illness that may have only been invented a few yeas before – seen as The Method to good health by governments. Many of these incentives relate to targets like ‘the proportion of patients taking Brand X or Y.’ Doctors are coerced with targets to persuade patients into taking drugs, incentivized by payments with the quality care measured in volumes of pills or vaccines and adherence to policy.

16.   Homeland Security:

Few are aware that almost all drugs are made available under police state provisions and supervision. The availability of medicines on a prescription-only basis was introduced as a means to control heroin and cocaine addicts in 1914. The War on Drugs initiated then has become a permanent War in which all citizens are treated as addicts and all doctors as police.

Extending prescription-only privileges to all drugs was sold to the wider population as a means through which medical scepticism would temper patient zeal for treatment. But doctors now funnel drugs to people in the Matrix in amounts that have many of pleading for respite or else surreptitiously dumping our medicines.

Rachel Liebert outlines how recent school shootings have led to the creation of a Homeland Security apparatus in our schools and colleges aimed at detecting any signs of abnormality in any students and getting them on medication.

17. Good Germans:

There are lots of Good Germans in the system. All tyrannies  have passed – up till this anyway. You have to survive till then, and life is more comfortable in the Matrix than outside. Unless they have come to take you or someone you know away, its better keep your head down and eyes averted.  Keep taking the blue pills.

The Post-Fascist State

“The 100,000 people who work for GSK are just like you, right? I’m sure everybody who reads the BMJ has friends who work for drug companies. They’re normal people… Many of them are doctors.”

Any German in the 1930s or 40s could have said the same of his fellow-countrymen. And the subjects in the famous Milgram experiments were no doubt just like you and me also.

In the 1960s, there was great concern at the development of medical techniques that looked likely to lead to a control of behaviour. These concerns played a large part in the rise of post-modernism which was a protest before the event against the ideas that took shape in the 1990s that Prozac, Genetics and the New Biology would usher in a New Man.

Astonishingly, these concerns reached the level of a Congressional Hearing as far back as 1967. Seymour Kety, then the head of the NIH, attempted to put the developments in context for Congress:

“The manipulation of the brain by any of the biological techniques which can be developed in the foreseeable future would involve such drastic invasions of privacy, integrity and the unalienable rights of the individual that in their application behavioral control would already have been achieved even if the electrodes carried no current and the pill were placebo”.

Our pharmacological and biological techniques have not moved on much since then. The therapeutic armamentarium is in many respects weaker now rather than stronger but in its weakness it reveals that what has changed is that control has been achieved even when the electrodes carry no current and the pills are placebo or more harmful than placebo.

This was an outcome predicted by some in the 1960s, such as Jacques Ellul in The Technological Society, in which he argued that the techniques to really worry about were our public relations and marketing techniques rather than our engineering or biological techniques. The social scientists and students of rhetoric (media studies) of the 1960s, coached in post-modernism, migrated from universities to populate the marketing departments of pharmaceutical companies (see Factories of Post-modernism). They brought with them a means of control through a set of techniques first pioneered by Edward Bernays but greatly developed since then.

We operate now in a post-fascist state. Back in the 1960s the totalitarianism of the Soviet Union was a horror but Soviet citizens could very clearly see the enemy. The problem in the West now is that control can be far more complete because the mechanisms and levers are invisible. We volunteer into rather than are coerced into running the apparatus of repression. We live in a Benevolent Fascism.

From this point of view there are lots of reasons to think we might be better off if Pharma’s current legal action against EMA succeeds leaving us clearly able to see Bad Pharma withholding data than if data access is maintained but we get our access through a proposal put forward by someone just like you or me.

Illustration: HOPE: Pills You Can Believe In, 2013 created by Billiam James

You and your meds Give the real story. Get the real story.

© David_Healy for Dr. David Healy, 2013.

In 1954 soon after his article with Beecher put the placebo on the map, Lasagna was recruited from Harvard to Hopkins. Beecher pleaded with him to stay in Boston.

“Now that I am faced with the unhappy fact that you are gone, I find it more depressing than I can say…. If your future career is anything like your performance here it is bound to be spectacular.”

Lasagna ended his days back in Boston, leading a Center for the Study of Drug Development, whose brief was to foster the development of specific treatments for specific conditions. In 1980, he was made president of the American College of Neuropsychopharmacology. The placebo had vanished from his working life.

Michael Shepherd had at one point been expected to take over the lead of Britain’s Maudsley Hospital when Aubrey Lewis retired but his style was too much at odds with the developing medico-pharmaceutical complex for this to be possible. He had been Vice-President of the World Psychopharmacology College (CINP) but by the mid-1960s he was persona non-grata within psychopharmacology.

He turned to primary care research and accidentally created a market for the SSRIs in the process. He grew increasingly opposed to the notion of specificity in medicine, and turned to exploring the placebo.

The two men met for the last time in 1992 at the 50^th American Psychosomatic Society meeting in New York. Lasagna was chairing, Shepherd speaking. His topic – The Placebo (see Empire 1).  [Shepherd is on the left]

When the lecture finished, Lasagna said: “this paper is now open for questions”. Nothing happened. Half a minute elapsed, a minute elapsed and nobody said anything at all. In Holland this would be normal – in America it was plain bizarre. Lasagna then said that in the circumstances they would have to move on to the next paper but he couldn’t refrain from commenting on this unnatural silence.

“There are 3 possible explanations” he said. ”First you were all asleep and therefore you heard nothing. Secondly it was so bad that since this speaker has come 3,000 miles you didn’t want to embarrass him. Third it is genuinely so original and new that you don’t quite know what to make of it. I’ll leave you to decide which it was”.

What had Shepherd said?

Mirage in 1962

The key point is that little was known about RCTs or effectiveness in 1962. RCTs appeared in a late night political haggling session as a simple solution to an extraordinarily complex problem. But to paraphrase HL Mencken, like Lasagna also based in Baltimore, every complex problem has many simple solutions – all of them wrong.

Coming as he did from a position of running studies on internal states such as pain or on sleep induction, the inclusion of controlled trials late night in ’62 may not have hit Lasagna as problematic – even though in his hands imipramine, a far more potent antidepressant than any SSRIs, could not be shown to work in a controlled trial.

Analgesic and hypnotic effects were determined by means of rating scales. These effects were demonstrations of efficacy rather effectiveness against a pathological state. A demonstration of analgesic efficacy is consistent with FDA regulations that a drug be demonstrated to have an effect on a structure or function of the human body and analgesics are licensed on this basis to this day, as are hypnotics, oral contraceptives and a range of other treatments.

It would have been entirely possible to bring antipsychotics, benzodiazepines and SSRIs on the market by demonstrating their tranquilizing or anxiolytic properties. This focus would have put a premium on later teasing out what is distinct about the anxiolysis in each case – something that clinicians today quite astonishingly still cannot do although the experience you or I have of these drugs is entirely distinctive – we can easily tell them apart.

In contrast the SSRIs have performed so miserably in effectiveness trials that there is intense debate about whether they work. Half of  the trials undertaken show a rating scale only differentiation from placebo. The other half shows nothing.

If in contrast, SSRIs had been licensed on the basis of an anxiolytic effect, the question of how and when to use these drugs as a therapeutic principle for depressive or anxious states would have been a separate matter that could have been tackled by the medical profession after these drugs came on the market.

Instead the effectiveness criterion has made medical conditions into a target for treatment and in so doing it set these conditions up for capture by pharmaceutical companies and their marketing departments. The effectiveness criterion created the inevitability of what is now called disease mongering.

To have to fish for possible effectiveness in some heterogeneous clinical condition is not what controlled trials were designed for. Controlled trials discover nothing. Even worse, the effectiveness claims for many drugs rest on minor surrogate marker or rating scale changes in trials that are powered to ensure that clinically insignificant changes achieve statistical significance. It would be entirely possible to prove Snake Oil was effective on this basis.

Meanwhile in the real world

Meanwhile in the real world, there are in fact more dead bodies in the active treatment arms of most blockbuster studies than in the placebo arms. The claim that these surrogate or rating scale changes demonstrate effectiveness therefore as a matter of logic does not stack up.

Aside from dead bodies,we know that many of those who “benefit” will have enduring problems from physical dependence and other legacy effects from treatment. This is not effectiveness as the 1962 regulations envisaged. We have ended up instead in a world in which hints of an effect are used to gain market entry for drugs and when we use these drugs mindlessly on the basis that they are effective, if the RCT evidence is to be believed, we produce greater disability in the long run than if we never had them. The effects may turn out to be worse than if we had encouraged chronic alcohol intake.

The only thing that stands in the way of this outcome at the moment are the dwindling number of doctors who pay no heed to guidelines and try to be discriminating in their prescribing and the patients who simply don’t take the treatments when their experience tells them this is not for them.

Trial Perversities

So far the argument is consistent with a view that controlled trials are gold standard processors into which we have fed garbage and have got garbage back.  And that many people have a great capacity to greet garbage as gold.

In fact, we are cursed like Midas and everything to do with this gold standard, rating scales and surrogate markers, has produced an informational reductionism and rigid standardisation that is destroying medical care.

Little noticed is the fact that the RCT processor malfunctions badly in a number of ways.

Whenever a drug and an illness produce superficially similar effects from pain, to nausea, to suicide, it is possible to hide drug-induced problems. Antidepressant trials can be “gamed” so that drugs known to cause suicide will show up as preventing suicide rather than causing it. Perverse outcomes like this are built into RCTs (See The Best Bias that Money can buy, Heads we win, tails you lose).

In all these cases, the Christmas tree lightbulb test is better than clinical trials ever could be. When the lightbulbs don’t work after they have been laid up for a year, you unscrew each in turn, till unscrewing one leads the lights to come on, screwing it back in causes them to go off again and removing it turns them on. In this case, we have as definitive a result as Martin Teicher had with Prozac and suicide in 1990. Lilly claimed their clinical trials showed no problem. Teicher’s observations can now clearly be seen to be much more valid than Lilly’s.

When we get clearcut results from celebrated trials such as the Women’s Health Initiative study of HRT, it’s often because these are conducted in essentially healthy volunteers so that excess rates of breast cancer stand out – this was a drug trial rather than a condition trial.

Confused outcomes also happen when the clinical condition being investigated is heterogeneous as for instance in back pain, depression or asthmatic states or even Parkinsonian syndromes. In the case of SSRIs and suicide, GSK were able to use the different background rates of suicidal acts in borderline personality disorder patients compared to major depressive disorder patients to hide the suicide risk on paroxetine. The same can be done on purpose or by accident for many if not most medical conditions.

Finally in the case of the antidepressants, although in Lou Lasagna’s hands imipramine didn’t beat placebo, it is relatively straightforward to design trials to get imipramine to beat SSRIs – all that is needed is to pick a group of more severely depressed patients. But in this case, what would FDA license imipramine for? For severe depression only or for all depressions and what consequence if any would there be for the licensing of SSRIs?

Panalba & Combination Treatments

It was the issue of relative efficacy that blew Lasagna’s career off track in the fiercely contentious Panalba case in 1969.

Panalba, as mentioned (see Tragedy) was a combination antibiotic. FDA wanted to pull it off the market – on the basis of efficacy not safety. They claimed that the test of effectiveness for a combination antibiotic was a demonstration of effectiveness over and above the effectiveness of each of the individual components.

If we compare the regulation of drugs with the regulation of butter, FDA never takes a position on the comparative merits of butters. In similar fashion, FDA does not now allow, and likely never will allow, comparative effectiveness claims to stand within a therapeutic domain.

But in the case of combination antibiotics, FDA chose to remove all such treatments. Lasagna publicly contested the issue, not as a believer in Panalba, but on the point that the basis for the decision appeared arbitrary. He argued it was bad medicine to use Panalba. But was it up to Medicine or up to the FDA to sort this out? And, although philosophically against Panalba, he wasn’t prepared to completely deny some place for clinical wisdom in its use.

Panalba was an obvious combination drug. But many drugs embody several therapeutic principles – they are cocktail drugs rather than combination drugs. Imipramine contains an alerting norepinephrine principle, an anxiolytic serotonergic principle, a euphoriant anticholinergic principle and a sedating anti-histaminic principle. In just the same way some antibiotics embody more than one antibiotic principle. Indeed Prozac has antibiotic effects. When it comes to the licensing of cocktail compounds like this, FDA does not and cannot require a demonstration of greater effectiveness.

In fact a good case can be made that it is imipramine’s cocktail nature that makes it difficult to run an RCT on it. It has an anxiolytic effect, but not so marked as Prozac, an alerting effect but not so marked as a stimulant, and a sedative effect but not so marked as an hypnotic. This cannot be brought out in milder depressions but imipramine is clearly better than Prozac in severe depressions and in clinical practice a discriminating clinician can deploy its many facets to good advantage, regardless of what a purist might prefer. Good practice with this drug and many other drugs will never be RCT based.

If so for imipramine, to return to Lasagna’s point, what about Panalba?  Imipramine is just one drug – but FDA have since licensed many combination treatments from Fen-Phen to Symbyax (Prozac and Zyprexa) none of which met 1969 standards for efficacy.

Compromising Safety

When it comes to safety the problems get more acute. The effectiveness requirement is enshrined in regulation for the contribution it makes to safety. If all drugs are poisons then there is a better risk-benefit trade off if we have some confidence there is a potential benefit to trade against. The wording of the regulations continues to put safety first – safety and effectiveness.

But in using RCTs to demonstrate effectiveness Congress compromised safety. Here’s how. RCTs necessarily have a primary endpoint for purposes of calculating statistical significance. The assessment instruments and trial design hinge on getting the best possible data on the primary endpoint – which is always the demonstration of effectiveness. This focus on one endpoint means that other outcomes (safety issues) are side-lined.

As a result, if in the course of a study a safety problem happens at a greater rate on drug than on placebo, it will be poorly characterized, will be hidden under multiple codes and will almost always be dismissed as not statistically significant – even by FDA. Under oath, Andrew Witty will swear we had no evidence that our drug caused this problem, and he may not be lying in the conventional sense of that word.

The 1938 act FDA clearly took effectiveness into account. It used to be impossible to discuss safety without efficacy. For example, the early sulfonilamide drugs were dangerous but in view of their effectiveness in saving lives, there was little question but that they should be allowed on the market. A hypnotic shouldn’t cause birth defects or peripheral neuralgia and under the 1938 Act, thalidomide wasn’t licensed.

But under the 1962 Act, the claim that effectiveness has been demonstrated now means that some of the most problematic drugs in medicine, such as dopamine agonists like ropinirole that cause gambling, sex addiction and personality change, can be brought on the market for conditions like restless legs syndrome. Common sense doesn’t seem to apply any more.

As a means to promote safety, the effectiveness criterion fails. This might be acceptable if the criterion ensured we got effective treatments but comes close to lunacy if the drugs are not in fact effective, and is even more lunatic if doctors can be brainwashed into thinking they are effective.

Is the Effectiveness Criterion Unconstitutional?

In July 2012, GlaxoSmithKline paid a record $3 billion fine for off-label promotion of several of their drugs. A few months later, and they might not have had to pay anything.

In December 2012, in the Caronia case a Second Circuit court ruled that stopping a company representative from talking about off-label uses of the company’s drug was a breach of their First Amendment rights to free speech. There was consternation among supporters of regulation.

The case involved Alfred Caronia, then a sales representative for Orphan Medical, which sold Xyrem, a drug approved for narcolepsy. He had been caught on tape discussing the use of the drug as a treatment for insomnia, fibromyalgia and other conditions with a doctor who was a government informant. He was convicted in 2008 but appealed on the basis of the First Amendment.

Since 1962, companies have for the most part supposedly demonstrated drug A is effective for condition X in order to get a license. They are then restricted to promoting the use of A for X, while doctors can use A for anything. It is more rational for instance to use SSRIs for premature ejaculation than for depression, as SSRIs are extraordinarily efficacious for this. But if a company representative suggested such a use when his company had not applied for a license to market the drug for this purpose, the company could be penalized.

The ruling in Caronia stated:

“The government clearly prosecuted Caronia for his words — for his speech,” but “the government cannot prosecute pharmaceutical manufacturers and their representatives under the FDCA for speech promoting the lawful, off-label use of an FDA-approved drug.”

Judge Debra Ann Livingston disagreed, arguing that

“[this] calls into question the very foundations of our century-old system of drug regulation.”

In a statement to send a shiver up the spine of most “liberals”, the Pharmaceutical Manufacturers Association said:

“PhRMA believes that truthful and nonmisleading communication between biopharmaceutical companies and health care professionals is good for patients, because it facilitates the exchange of up-to-date and scientifically accurate information about new treatments.”

Whatever about politics and preferences, it’s intellectually difficult not to side with the judges and PhRMA here. As things stand, anyone on the planet can discuss off-label uses of most drugs except the company that has made them. Worse again, when it comes to other drugs it makes no sense to say a company could only talk about the use of an opiate analgesic for gall-bladder but not for lung cancer surgery. This is an artificial debate created by the effectiveness criterion.

Just as with drugs, Olive Oil has to meet a regulatory criterion to be let on the market. The criterion doesn’t specify use of Olive Oil as a salad dressing as opposed to its use as a cooking oil. If the criteria did specify this, once on the market, if it was discovered that Olive Oil was wonderful for massage purposes, it would clearly be an infringement of the right to free speech to stop a company representative talking about these benefits, especially of Extra Virgin Olive Oil.

The Pied Piper

So what had Michael Shepherd said in his lecture on The Placebo that reduced an American audience to silence?

At dinner after the symposium in New York, Lasagna told Shepherd the placebo had been completely eclipsed within American medicine. No-one had any idea what it meant – and no-one was likely to grasp the issues he had raised.

What Shepherd told his audience was that bizarrely the awareness most doctors have of placebos stems from controlled trials. But the RCT placebo has almost nothing to do with the Powerful Placebo of the 1950s. It’s a stochastic effect. It’s meaningless. In any particular trial no-one knows or can know whether it refers more to the biases of doctors or of patients or to the natural variability in the condition.

When it comes to treating an individual patient or evaluating what is likely to be going on, the fact that there is a placebo response in population studies of medical conditions tells us next nothing.

The placebo response in controlled studies looking for an effect on a structure or function of the body would be quite a different matter and is something that could be usefully explored for learning or other effects that might in their own right form a basis for other or additional therapies.  Just as placebos in testing for analgesia can show profound conditioning and other effects, so too they could in testing for anxiolysis for SSRIs.  In depression studies the role of the drug and placebo tell us nothing other than a regulator can possibly approve this drug.  Its almost anti-evidence based medicine.

Lasagna and Shepherd were at one on this. As Lasagna put it:

“Evidence Based Medicine has become synonymous with randomized placebo-controlled clinical trials even though such trials invariably fail to tell the physician what he or she wants to know which is which drug is best for Mr Jones or Ms Smith – not what happens to a non-existent average person”.

He went further, noting that all drug discovery in psychopharmacology had been made by men like Fritz Freyhan who had been so skeptical of clinical trials in 1956 (Empire of Humbug 1), rather than through trials:

“The days when a drug company would go to skilled and sophisticated psychiatrists and give them a supply of a new drug and ask them to try it on some different patients seem gone forever. Is this a cause for celebration or depression?”

When asked in 1996 about the developing “craze” for Evidence Based Medicine, Shepherd responded that if we went down this route:

“We would also, of course, never make any advances because all advances depend on guesses which we call hypotheses – most of which are wrong but some of which are right. In terms of the logic of the scientific process the evidence comes after the hypothesis. You must begin with a hypothesis and that is a guess.

I knew Cochrane but [Evidence Based Medicine] is pushing the thing to, I think, an absurd extreme. Of course, it’s true that the whole discipline is cluttered up with procedures for which the evidence is meagre at best and there is a case for trying to make quite certain that that is minimised. If that’s what meant by it – certainly – but it eventually stiffles everything else”.

In fact where the placebo had once seemed a form of hypnosis, the focus on effectiveness and specificity has turned RCTs into a form of hypnosis. Doctors are now in thrall to the spell of the hypnotist from Oz, who’s RCTs can even make Snake Oil to be effective.

Hypnotized by the Piper’s tune, doctors and patients are lured to consume 6, 8 or 10 drugs at the same time – what could be wrong with taking drugs that work. Infants, elders are lined up and medicated. The only ones who may be saved are those who have been previously crippled or injured on whom the music has ceased to work. Few can see what is going on around them or the name of the theatre in which they are being duped – The Empire of Humbug.

You and your meds Give the real story. Get the real story.

© David_Healy for Dr. David Healy, 2013.

The first RCT

In 1956, two of the creators of the modern RCT, Lou Lasagna and Michael Shepherd, met. The randomization in randomized placebo controlled trials came from Bradford Hill in Britain and placebo controls from Beecher, Gold and Lasagna in the US. In 1956, Michael Shepherd, Bradford-Hill’s representative in all things psychiatric, came on sabbatical to stay with Lasagna at Hopkins’.  [Lasagna is on the left].

In 1947 Bradford-Hill ran the first randomized trial. In 1955, Shepherd added in Lasagna and Beecher’s placebo to the original randomized design and published in the Lancet the first ever RCT of the type used today in drug trials submitted to FDA for regulatory approval. His trial compared reserpine to placebo in a group of outpatients with mixed anxiety and depression – similar patients to those later given Prozac and other SSRIs. Reserpine was better than Prozac and other SSRIs later were, and indeed did better than imipramine did a few years later in a trial run by Lasagna. There was no sign in Shepherd’s trial of the suicide hazard for which reserpine is now best remembered.

The two articles that immediately preceded Shepherd’s study in this issue of the Lancet described hypertensive patients being treated with reserpine who became suicidal. When later asked why his trial had almost no impact, Shepherd’s off-the-cuff response was that doctors were not used to seeing results being presented in this way. But there was in fact no commercial incentive for any company to use his results to relegate the accounts of suicide on reserpine to the status of anecdotes.

Evaluating Drugs

Just as Shepherd’s paper was published in 1955, chlorpromazine was taking the American market by storm and looked set to change psychiatry as much as penicillin had changed medicine. This earthquake in therapeutics led to a landmark Evaluation in Psychopharmacology meeting convened by Jonathan Cole and Ralph Gerard in Washington in September 1956, at which Lasagna was a key note presenter. Shepherd attended.

Critically just 6 years before it became a legal requirement to use controlled trials and only controlled trials to evaluate drugs, there was no controlled trial section to these proceedings. Instead, there were notes of caution about clinical trial methods from the grandees in the field – positions that years later Lasagna endorsed.

Fritz Freyhan criticized a naïve faith in technical objectivism:

“the time, we hope, has not come when the clinician abdicates and the rating-scale marker takes over as a judge”. “While one can easily spot the potential and actual shortcomings of nonexperimental studies, it appears to be tremendously difficult for multidisciplinary groups to acknowledge limitations and sterility in rigid experimental design”.

Nate Kline said a rating scale approach to clinical evaluation risked creating a rabbit-out-of-the-hat illusion. Pulling a rabbit out of the hat depends critically on getting the rabbit in there first – which was what rating scales did for drugs.

Ed Evarts noted that if chlorpromazine and controlled trials had been invented a few years earlier, chlorpromazine would have been shown to “work” for dementia paralytica (neurosyphilis) and its use would likely have inhibited recognition of the fact that penicillin was a cure.

Shepherd and Lasagna’s faith in controlled trials was a minority taste within psychopharmacology.

The two men born in 1923 had contrasting styles. Shepherd was aloof, drew lines in the sand and made enemies. Lasagna was sociable, worked to find areas of agreement and retained the affection of many who took opposite points of view. Shepherd’s insistence that controlled trials were absolute embroiled him in a set of bitter disputes about lithium that derailed his career. Lasagna viewed controlled trials as a pragmatic option, but his pragmatic insertion of controlled trials into the 1962 amendments led to a bureaucratic absolutism that also derailed his career (see Tragedy).

Although not a psychiatrist, Lasagna ended up with a wider following within mental health than Shepherd for two reasons – his work on placebos and on rating scales.

The Humble Humbug

While Lasagna was not the creator of the placebo, Gold, Beecher and others did earlier work (see Tragedy), his 1954 paper with Beecher ended up in Medicine’s top 30 cited articles ever and put placebos into RCTs. The placebo for most people, lay or medical, at this time was a form of hypnosis – a bridge between psychodynamics and pharmacology.

The hypnosis myth was fostered by a 1954 editorial on the placebo in the Lancet entitled The Humble Humbug. The phrase stuck. At a time when magazines were emblazoned with titles about miracle drugs, a Readers’ Digest piece in Sept 1956, coinciding with the Washington meeting, ran a piece on “perhaps the most remarkable of the miracle drugs” under the heading of “Medicine’s Humble Humbug: The powerful role in sickness of mental attitude”. By the time the Readers’ Digest piece came out, however, both Lasagna and Shepherd were reaching for a more unsettling understanding of what placebos might mean (see forthcoming Empire of Humbug: Not so Bad Pharma).

The second contribution came in demonstrating that rating scales could be used to test analgesics and hypnotics. This persuaded the field it was possible to objectively study internal mental states and in so doing Lasagna laid the basis for the insertion of controlled trials into psychiatry.

But there’s a rub. When we think about effectiveness, what do we mean? Without rating scales we might have to show treatments saved lives or got people back to work.

Lasagna was one of the first to appreciate the ambiguities in what seems like a simple question. It could mean – how good is this drug? Alternately it could mean – have the benefits of this drug been proven to be greater than the harms?

In 1962, although Lasagna appreciated these ambiguities more than anyone else, with the thalidomide crisis the pragmatic need was to find some basis for inserting an effectiveness criterion into regulation. The Democrats whom he was advising wanted one. The Republicans and business didn’t. The struggle came down to a battle over words – whether the preponderance of the evidence should support the application or whether the existence of a substantial amount of supporting evidence would suffice.

Lasagna came up with a winning formula – the application should be supported by evidence from adequate and well-controlled trials conducted by suitably qualified experts. This became two adequate and well-controlled RCTs, because ordinarily in science if a finding is replicated we can rely on it.

Based on Science

The 1962 amendments to the Food and Drugs Act and in particular the effectiveness criteria form the centerpiece of FDA’s proudest boast, repeated widely, that these amendments were the first example of regulation based on science.

The claim gives rise to a myth – that “scientists” from FDA are supposedly keeping the public safe. The myth is found everywhere from academic commentators on the FDA, as in Harvard’s Daniel Carpenter’s Reputation and Power, to views from the popular end of the spectrum, as in Philip Hilt’s Protecting America’s Health. There is no questioning of the mantra.

Not since the Wizard fooled the citizens of Oz into thinking that he was keeping them safe from the Witches of the West and the East and all dangers in between have we been so misled.

Controlled trials are based on a null hypothesis. Their early use was to debunk claims that treatments were effective. The trials we celebrate most, such as the Women’s Health Initiative Study of Hormone Replacement Therapy, continue to be ones which show how powerful this debunking can be. They are not a natural means to test for effectiveness.

If the controlled trial formula had been restricted to rejecting applications for treatments that didn’t work, companies who thought they had a good treatment but whose compounds failed in clinical trials might have had to go back and pick out a sub-group of patients the treatment clearly did benefit, for instance.

Testing for a negative is an unnatural frame of mind. The gestalt flips into viewing a disconfirmation of a null hypothesis as evidence that something positive has been demonstrated. When this happens, RCTs become a potentially invalid and certainly ambiguous metric.

The idea that what they were doing was based on science appears to have engendered a bureaucratic hubris. Regulators certainly don’t act like they have let a drug on the market because they cannot say it’s not effective.

But what if there have been five studies – two positive and three negative? In both cases the science has been replicated. In this instance the drug is let on the market, as the regulatory criterion has been met. When this happens the regulator demonstrates he is solving a regulatory problem rather than engaging in science and that regulation is about the mindless application of a bureaucratic rule.

As regulating takes place against a background bristling with the legal resources a pharmaceutical company can bring to bear on decisions that are not congenial to their interests, while it was briefly different leading up to the Panalba case (see Tragedy), FDA staff now learn quickly that regulation is unquestionably about the mindless application of a bureaucratic rule.

The rule says that it takes two positive studies to approve a drug. In law, if there were only two positive studies out of 100, the regulator would approve the drug. They have in fact approved applications where only 1 in 5 studies were positive. A variety of justifications are brought to bear on the issue, never found in science, such as the notion of failed trials. The bottom line is the studies in which the null hypothesis is upheld and the claims for drug are not upheld, do not count.

One consequence of this is that there are now tens, perhaps hundreds, of thousands of trials in pharmacotherapeutics, while there may still be less than one thousand trials in surgery and as few in preventive medicine. But where the practice of surgery has made dramatic strides, in many areas of pharmacotherapeutics the field has gone backwards.

Catch 62

Aside from the fundamental confusion between the scientific process and regulation, there are a series of profound misunderstandings that have made the 1962 amendments close to a disaster.

The word effective is a key problem. The regulations call for demonstrations of effectiveness while a great deal of the talk in 1962 featured the word efficacious. Treatments meanwhile also have effects, both beneficial and adverse.

Since 1962, effectiveness has come to be defined as evidence that treatments work in the real world. Virtually no drugs brought on the market demonstrate effectiveness in this sense. Almost by definition effectiveness cannot have been shown to be present whenever a study uses a surrogate marker or a rating scale score as its outcome measure.

Efficacy is used when a treatment does something useful in controlled trials but benefits are not necessarily realized in the real world. Almost all industry trials have to fall under this heading, if only because they come with so many real world exclusions and involve samples of convenience rather real patients.

An effect is an action on a structure or function of the body that may be beneficial and is something that may or may not take a controlled trial to demonstrate.

The 1962 Act uses the word effectiveness. There are other definitions of these words but whatever definitions are used there is no way to semantically solve the issues we are tackling here. The 1962 amendments are fatally flawed.

A subsequent regulation (CF 310.3 (4)) is more ambiguous:

The newness of use of such drug in diagnosing, curing, mitigating, treating, or preventing a disease, or to affect a structure or function of the body, even though such drug is not a new drug when used in another disease or to affect another structure or function of the body.

Randomized placebo controlled trials have not shown any drug within the mental health domain is effective. If a treatment were effective virtually every RCT undertaken would show a positive result.

Some psychiatric drugs are extraordinarily effective, for instance benzodiazepines for catatonia or SSRIs for premature ejaculation. These treatments are so effective that controlled trials are an irrelevance. Every trial conducted would show a positive result. The point here, developed below, is not that it is impossible for a treatment to achieve effectiveness but rather that controlled trials have little useful to contribute to the issue of effectiveness.

The public and legislators have been baited with effectiveness and sometimes efficacy but sold something else that doesn’t fit neatly under effectiveness, efficacy or effect. Some of these issues are now the subject of consumer fraud actions.

The Kefauver hearings centered on analgesics, hypoglycemics, tranquilizers and steroids. With each of these drugs there is an obvious effect but is there effectiveness? Hormone replacement therapy has an obvious effect but when a proper study was undertaken it turned out to be ineffective for the benefits claimed for it. For most doctors in the 1960s, Upjohn’s oral hypoglycemic, tolbutamide, clearly worked – it lowered blood sugars. But when a large controlled trial was undertaken in the late 1960s tolbutamide led to more deaths than other forms of treatment – was it effective?

The tolbutamide and HRT trials took 5 or more years to run. No one would ever suggest companies should go through trials like this to get on the market – certainly not Lasagna. This is what trials are for though. They are not for getting drugs on the market. The difference between WHI and NIH trials and company trials not about one set of trials being independent and the other not - it’s about the purpose of the trial.

If a short-term hypoglycemic or tranquilizing effect seems on the surface beneficial, it might be possible to talk of efficacy but this falls short of effectiveness, not because of something mysterious that happens when we move from clinical trials to the real world, as the definitions above suggest, but because while useful in both trials and the real world these effects are not effective in the sense of curative.

Analgesia and tranquilization are therapeutic principle rather than Magic Bullets.

Therapeutic Principle or Magic Bullet?

Part of the problem is that antibiotics have skewed our notions of what drugs should do. They have created a Magic Bullet template. It is all but assumed that if a treatment is approved it maps onto this template when in fact most treatments in medicine are helpful rather than curative – they are therapeutic principles rather than magic bullets. Analgesia, tranquilization, temperature reduction, or all sorts of other things can be helpful within a therapeutic relationship.

The idea of a Magic Bullet suggests a treatment that works regardless of setting or circumstance. Therapeutic principles in contrast have always been recognized to be dependent on constitutional or temperamental factors and on setting. Agreeing that a treatment “works” or “is effective” (Magic Bullets: MBs) rather than this treatment has an effect that may be beneficial for you (Therapeutic Principle: TPs) risks condemning many to the wrong treatment for them.

Condemning is too mild a word for the forcible medication of many mental health patients with what were once called tranquilizers (TP) but are now called antipsychotics (MBs).

One consequence of Lasagna’s 1962 wording has been to move us from a world of Evident Based Medicine, which he agreed with, to Evidence Based Medicine, which he didn’t agree with. “Evidence of effectiveness” is now used to persuade or all but force patients to take and doctors to give treatments even when they are evidently not doing you good (see False Friends).

If trials indicate treatments are effective, it’s in the interest of the State (as well as pharmaceutical companies) to “persuade” or force as many of the citizenry to take treatment as possible, as clearing up diseases should make the population more efficient. To this end, a certain amount of casualties en route can be accepted as collateral damage. In the case of the antidepressants and suicide, regulators again and again made clear that they would not warn of this hazard, in case people might be deterred from seeking treatment, or doctors deterred from putting them on treatment.

Coming back to Lasagna’s question – what does effectiveness mean? Even when controlled trials show a net loss of life on a treatment, regulators now almost always state that the risk benefit ratio remains favorable. This view can only be sustained on the basis that they believe if the treatment is effective, as for instance in the case of the antidepressants, even if there is a net loss of life from suicide in short term trials, that somehow in the longer run an effective treatment will lead to lives saved.

This is not an evidence based position. It can only begin to possibly make sense on the basis of some belief about an effectiveness that conveniently for regulators is rarely put to the test – the WHI HRT and NIH tolbutamide trials were monumentally inconvenient for regulators but even they didn’t lead to the drugs being pulled. That’s a medical issue not a regulatory issue.

Truly effective treatments should be self-funding or even lead to a fall in healthcare costs. If lives are saved and people are put back to work, or become more efficient at work, then national economies will perform better and wealth will increase. But not only are healthcare costs increasing exponentially, morbidity and mortality from treatment is increasing so that treatment induced death is heading toward being, may even be, the normative way of dying.

None of this should be happening if our treatments are effective. RCTs, as used by companies, may be efficacious to get drugs on the market but for the most part they aren’t effective in leading to better health.

Conversations in the Speakeasy

The irrationality of what has happened can be brought out by comparing antidepressants with alcohol. In the case of imipramine, a much more potent antidepressant than Prozac, Lasagna who ran the first RCT on imipramine recognized that it was difficult to even prove efficacy in an RCT.

In the case of the later SSRIs, there is distinct psychotropic “effect” – they emotionally numb. SSRIs “work” in the sense that alcohol “works”. Using the same testing approach that brought SSRIs to market that supposedly demonstrates their effectiveness we could bring alcohol to market as an antidepressant or anxiolytic if it could be patented so that it was worth our while. All it takes is a result in two of ten short 6-week trials, in which it would have almost certainly produce a “benefit” on the right rating scales and with fewer serious side effects than SSRIs – there would not be a doubling of suicidal acts, with up to 5% of patients having suicidal ideation as there is with SSRIs (see Shadow Dance).

Because everyone knows what alcohol does, they can see that such a demonstration for alcohol is not a demonstration of effectiveness, but they seem unable to see that this is also the case for SSRIs, for every other psychotropic drug, and for a majority of drugs in medicine.

If we were to try and bring alcohol on the market, we would do so on the basis of its effect on a structure or function of the body rather than for supposed effectiveness. What would the world have looked like if the same had been done for the SSRIs?

At the end of his career, Lasagna mused “The days when a drug company [developing a drug] would go to skilled and sophisticated psychiatrists [like Fritz Freyhan] and give them a supply of a new drug and ask them to try it on some different patients seem gone forever. Is this a cause for celebration or depression?”

Before an effectiveness criterion was brought in, under the 1938 Act, several classes of antibiotics, diuretics, antihistamines, hypoglycemics, anticonvulsants, steroids, antihypertensives, major tranquilizers (antipsychotics), minor tranquilizers, analgesics, antidepressants, stimulants, oral contraceptives, the first chemotherapies for cancer and a range of other highly effective or efficacious treatments were brought to the market, all without the help of controlled trials.

Since 1962, it is doubtful if as many effective medications have been brought on the market. It is likely that more relatively ineffective but highly dangerous drugs have been marketed since 62 than before 62. This is an almost completely predictable consequence of what we have done.

(See Empire of Humbug: Not so Bad Pharma.  ”Andrew Witty” will also offer a view on what the right wording of Drug regulations should be in Witty A: Report to President).

You and your meds Give the real story. Get the real story.

© David_Healy for Dr. David Healy, 2013.

In 1956, Lou Lasagna was on his way to being the most famous doctor in the United States.

His career had lifted off four years before when he was recruited to Harvard from an Atlantic City boardwalk by Harry Beecher. Beecher got the money to support Lasagna from the US Army by telling them there was no-one in the universe more qualified than Dr Lasagna to undertake this research of critical importance to the military.

The top-secret research was happening in the department of anesthetics, where Beecher had collected a small group to work on the placebo response. The idea of a placebo response had implications for notions of suggestibility and hypnosis. Militarily, it fed into American concerns about brain washing born in the Korean and Cold Wars.

The placebo response was also the key American contribution to the idea of randomised placebo controlled trials. Randomization came from Britain, where it was pioneered in clinical trials by Austin Bradford-Hill, but it was Beecher’s team of Lasagna, Von Felsinger and others who brought the placebo to the table and helped create the controlled clinical trial we have today.

In 1954 Lasagna moved to Johns Hopkins to create the first Department of Clinical Pharmacology in the country. The boom in new wonder drugs called for new scientific evaluation methods and for a new kind of specialist, who could cut across disciplines.

Lasagna had a ready turn of phrase and was soon a media favourite using radio and TV in the way that others might now use Twitter, Facebook or other social media.   The New York Times, the New Yorker, the Readers Digest and a huge range of periodicals opened their pages to his comments on the issues of the day from nuclear disarmament to women astronauts but in particular medicines.

He engaged in controversies as they arose from the question of whether the new oral contraceptives caused thrombosis, to the effects of the first “statin”, and the question of whether smoking causes lung-cancer. In all these cases he made what we can now see were the right calls: yes – contraceptives caused thrombosis, no – cholesterol lowering was unlikely to be of much benefit, and yes – smoking caused lung cancer.

In the most golden era ever for new Wonder Drugs, his focus was on evaluating them from new opiate and non-steroidal analgesics through to hypnotics.

“Is it such an horrendous leap from the present position to one
where evidence for a drug’s therapeutic potency must be provided
by the manufacturer before a compound is released?”

In 1956, when reviewing the issue of the safety of over-the-counter hypnotic antihistamines, he raised the question of drug effectiveness:

“It is unfortunate that the Food and Drug Administration cannot take regulatory action against a drug whose efficacy for the conditions for which it is offered has not been demonstrated. Adequate toxicity data are required from manufacturers before introducing new drugs: similar requirements as to effectiveness should be included in our federal statute. It appears to be an accepted fact that toxicity and efficacy cannot each be considered separately, in vacuo as it were. Is it such an horrendous leap, therefore, from the present position to one where respectable, reliable evidence for a drug’s therapeutic potency must be provided by the manufacturer before a compound is released?”

For Lasagna this meant something quite different to what it meant for anyone else at the time in that controlled trials offered a means of testing claims about efficacy in a way that had not been possible previously. As of 1962, he had run many of the first placebo controlled trials of antidepressants, analgesics and hypnotics. In his hands the leading antidepressant, imipramine, didn’t differentiate from placebo. Most strikingly he had at that point run the only placebo controlled trial of a drug that had still to be marketed – thalidomide.

The move to a new more critical pharmacology and therapeutics led in 1959 to the creation of The Medical Letter by Arthur Kaller of Consumers’ Research. All of the stars in the new field of clinical pharmacology, Lasagna, Louis Goodman, Walter Modell and others, were on its Advisory Board and wrote for it. Their evaluations of new drugs and trends were hugely influential with medical prescribers.

At this point Lasagna had written more on controlled trials and the necessity for them than anyone else in America. His contributions on these and on how clinical practice could be improved or cleaned up led to recruitment offers from NIH, Langley Porter and elsewhere. The Squibb Institute offered to quadruple his Hopkins’ salary. But he stayed put to continue a mission to put Clinical Pharmacology on the map.

Informed consent

He took another radical step in early 1962, when with Beecher he laid the basis for introducing informed consent to medical research. Informed consent first appears in medical practice after a series of court cases in the late 1950s involving patients being treated for breast cancer or with ECT.

By 1960 an increasing number of patients were being given investigational new drugs with no idea that these drugs had not been approved. Lasagna flagged up the need for informed consent in such cases, produced the first consent forms and had them built into FDA regulations. In so doing he brought informed consent into research and later into mainstream medicine.

The Kefauver Hearings

The 1950s were a glory decade for the pharmaceutical industry. But despite articles everywhere proclaiming a cornucopia of Wonder Drugs, a new set of discontents with the practices of the pharmaceutical industry emerged. The discontents were brought to public focus by a Democratic senator from Tennessee, Estes Kefauver.

Kefauver’s interest was stimulated when members of his staff found that several versions of the same antibiotic, marketed by different companies, had identical prices, and that the prices being charged were of the order of a 1000% of the price of manufacture.

As they explored the issues, Kefauver’s staff found evidence companies were secretly engaging in cartel practices to maintain the price of medicines, and corrupting doctors with backhanded payments to prescribe on-patent and more expensive drugs.

Lasagna was on Kefauver’s team. He briefed on advertising, the AMA, drug development, testing for efficacy and safety. He had not been scheduled to testify but was pressed into it at the last minute as a previous expert was withdrawn because of a suspect political background. He testified on advertising, pricing, efficacy and other issues.

Advertizing had become a key concern. There was the sheer volume. As Walter Griffith of Parke Davis told Kefauver “the ethical pharmaceutical industry of this country” had turned out “3,790,908,000 pages of paid journal advertising” and “741,213,700 direct mail impressions”.

“Madison Avenue discovers Medicine Avenue”

But of greater concern was that Madison Avenue in Lasagna’s words had discovered Medicine Avenue.  The new marketing campaigns were much slicker and adverts were commonly misleading and in many cases downright fallacious.

Kefauver’s staff unearthed one advert for an antibiotic which featured two chest x-rays giving the impression of clinical improvement when the x-rays in fact came from two different patients neither of whom had had the antibiotic featured.  As Dale Console, of the Squibb Institute put it: “If an automobile does not have a motor, no amount of advertising can make it appear to have one.  On the other hand, with a little luck, proper timing, and a good promotion program, a bag of asafetida with a unique chemical side chain can be made to look like a wonder drug”.

Yet other concerns lay in drug company practices of withholding safety data on drugs, along with their lack of testing of new drugs on animals prior to marketing to humans. As one wag put it, companies didn’t do animal testing believing that it was less expensive to test a drug on humans.

There was another niggling issue – the regulators had no procedures in place to ensure a drug worked. The 1938 Act solely required companies to demonstrate safety in a number of patients without even basic toxicology testing in animals. As Kefauver’s staff noted, if a drug didn’t work for a condition for which it was marketed or worked less well than an already available product, then it was inherently unsafe.

These discontents led, in 1959, to the establishment of the Kefauver – Harris Senate hearings, which began on December 7 1959. Kefauver’s main target was the patent system, which he thought was responsible for the artificially high prices American patients uniquely faced. Kefauver’s staff produced figures to show that out of 77 countries they surveyed, 28 allowed product patents and in these countries the prices of drugs ranged from 18 to 255 times higher than in the non-patent countries, with both American-made and European-made drugs costing far less in Europe than in America.

“anyone who dares seek the truth
will be accused of being a persecutor”

But as Kefauver found, “These drug fellows pay for a lobby that makes the steel boys look like popcorn vendors. … anyone who dares seek the truth will be accused of being a persecutor”. Up for re-election in 1960, he found himself branded a “socialist hellbent on ruining healthcare”.

He was re-elected comfortably, but he had few friends. Despite Kefauver having been the 1956 Democratic vice-presidential candidate, Kennedy was not a friend. The administration was trying to get Medicaid through Congress and did not want to antagonize the pharmaceutical industry.

Prior to 1960, the American Medical Association (AMA) had run a unit to evaluate new drugs and maintained a list of drugs to avoid. This in the late 1950s was leading to falling advertising revenues in the Association’s Journal, the Journal of the American Medical Association (JAMA).

The AMA was gearing up to fight Kennedy’s plans for Medicare and Medicaid and was dependent on the revenue from advertising in its journals. It disbanded its evaluation unit.

Kefauver had no support from the AMA for a requirement that companies prove their drugs work before they are let on the market. Everyone agreed that new drugs should be effective but there was incomprehension on the question of an explicit test for effectiveness. The dance was subtle, as these exchanges show.

Sen Kefauver: If you want a drug to be efficacious before it is placed on the market, why not make that a condition as to placing it on the market? I do not understand.

Dr Hussey (AMA): It seems to me it is a condition under existing practice before it is placed on the market.

Sen Kefauver: But if that is what the law means now, then why do you object

What Hussey and others were saying was that when doctors gave a drug to a patient prior to its official marketing and saw the patient improve in some way that this was evidence that it worked. Most drugs obviously work but controlled trials had begun to cast doubt on the validity of medical testimonials of this type.

Sen Kefauver: The FDA has had a very satisfactory experience in evaluating the efficacy as well as the safety of antibiotics and diabetic drugs, is that so?

Dr Lasagna:  Yes sir.

Sen Hruska (Rep): If that is true, why do we need another law?

The Kefauver hearings centered on 4 drug groups – the steroids, tranquilizers, anti-diabetic drugs and antibiotics. Diabetic drugs obviously lower blood glucose levels and antibiotics obviously kill germs in a petri dish or not. A decade later as it turned out, one of the first oral anti-diabetic drugs, tolbutamide, whose efficacy FDA had no reason to doubt, ran into serious problems when a large independent controlled trial showed it led to a greater loss of life than other treatment options.

By 1962, the debate about efficacy however appeared academic. Without allies, Kefauver’s bill (S. 1552) was eviscerated by his congressional opponents to make it more company friendly. His hearings came to a stop.

The Doctors’ Dilemmas

Lasagna’s role in briefing Kefauver’s committee and in testifying gave him access to a huge amount of material on the state of play between medicine and the drug industry that was grist to the mill of a book he was writing “The Doctors’ Dilemmas”.

His agent had made a first overture to Harper Brothers about a possible book in 1958 getting a response from the boss, Evan Thomas, who said that: “I don’t see what holds the Lasagna material together as a book but I really like this guy. Why not get him to write a book. He’s good.”

The Doctors’ Dilemmas was published by Harpers in Spring 1962. It got all the razzmatazz of a big trade launch.

The reviews were glowing. Beecher wrote:

“The Doctors’ Dilemmas has my awed admiration. I cannot think of anybody in this country or Europe who could have written this book other than Dr Lasagna. I am sure it will lead to a great deal of discussion in the areas he has dealt with so beautifully.”

Mike Gorman, the leading K-Street lobbyist of the day, gave it to President Kennedy and assured Lasagna that Kennedy had read it and that in particular Lasagna’s chapter on the AMA had shaped Kennedy’s thinking on the forthcoming Medicare bill and that his material on psychiatric drugs would also shape Kennedy’s mental health legislation scheduled for 1963.

Not everyone was enthusiastic. The front cover of the British edition of the book made it clear that “Dr Lasagna examines his profession describing its follies, fads, frauds – and achievements”. The American Medical Association was one of his primary targets and a review of the book in The Lancet concluded with the statement:

“The book has quite a good index, though for no obvious reason.”

Adequate & well-controlled trials

By the time The Doctors’ Dilemmas was launched in March 1962, Kefauver ‘s hearings had been consigned to the dustbin of history. But on May 19 the Daily Journal reported rumblings from Europe about birth defects on a sleeping pill, thalidomide, scheduled for launch by Richardson-Merrell in the United States.

The rumblings were picked up by the Washington Post whose leading healthcare reporter Morton Mintz reported on July 15 that Frances Kelsey of the FDA had kept thalidomide off the American market. This inspired piece created the myth of Frances Kelsey. It also did more than Kelsey had done to make it impossible for the FDA to approve thalidomide.

Three weeks later on August 5 Marilyn Monroe died from an overdose of  barbiturate sleeping pills.

On August 13 Newsweek ran an article ‘Tragedy from a pill bottle: some sad lessons learned’ featuring pictures of limbless babies born in Britain along with bottles of thalidomide from different countries, a picture of the German doctor Siegfried Lenz who had nailed down the link between the drug and birth defects and pictures of Frances Kelsey and George Larrick, the commissioner of FDA.

In September Kefauver’s Bill was rushed back to Congress, passing through both Houses on the one day, the only time a bill has ever passed through both houses on the same day except when the United States has gone to war. It was signed into law by President Kennedy on October 10.

Kefauver, in fact, got nothing of what he wanted on patents or pricing. The major difference in the 1962 bill compared with earlier bills was that where the Federal Food, Drug and Cosmetics Act of 1938 had given the FDA the power to evaluate the safety of new drugs they were now commissioned to evaluate the safety and effectiveness of new drugs. Where before they had been asked to look at whether the drug was safe, they were now asked to look at whether it was safe and effective.  And where before they had been asked to look at whether the drug was safe for use they were now asked to look at whether the drug is safe for use and whether a drug is effective in use.

Regulation CFR 310.3(4) states FDA is concerned with the new use of a drug in diagnosing, curing, mitigating, treating, or preventing a disease or to affect a structure or function of the body.

But how was effectiveness to be determined? The key issue was the role that evidence would play in determining the safety and effectiveness of new drugs. The FDA was pushing for a wording that stated that the preponderance of the evidence should show that the drug worked. The pharmaceutical industry wanted preponderance to be replaced by the word substantial.

The compromise position as put forward by John Blair who worked for Kefauver was to argue that the evidence should consist of:

“Adequate and well controlled studies carried out by experts with scientific training”.

This when translated into practice came to mean two placebo controlled trials. The wording came from Lasagna.

Nothing in the 1962 Amendments made a future thalidomide any less likely. The thalidomide application had already been turned down – under the 1938 Act.

If Marilyn Monroe?

There had as of 1962 only been one placebo controlled trial of any drug before it had come to market. This had been undertaken by Lasagna on Merrell’s new hypnotic, thalidomide. It showed thalidomide to be effective and safe. When the drug was held up by bureaucratic delay within FDA in 1961, Lasagna was approached by Richardson-Merrell to lobby with FDA on behalf of their drug. He did so.

Soon after the FDA hearings the media got wind of the fact that Lasagna, one of the major critics of the pharmaceutical industry, had been a supporter of thalidomide and had lobbied on its behalf. He was quizzed and defended his position by saying that:

“if Marilyn Monroe’s physician had been
able to prescribe that drug instead of barbiturates
she might still be alive.”

In the wake of the thalidomide scandal George Larrick was in time shunted to one side and the hunt was on for a new FDA commissioner. The Blue Sheet reports:

“A sigh of relief was heard in industry quarters when Lasagna, whose name was rumored to have been seen at the head of a list of candidates, indicated he was not one of them.

“The lively Hopkins pharmacologist and author told ‘The Blue Sheet’ the job had not been offered to him and anyhow his special expertise was in a limited part of FDA’s broad responsibilities. He is quoted in other quarters as feeling that a man would have to relish punishment to take the job.”

Others wondered what else might be in store for him. He was a regular attendee at White House functions and got on well with Hubert Humphrey. In 1966 Alvan Feinstein, later the founder of clinimetrics, wrote to him from Yale with a pair of side by side photos of Mr Humphrey and Dr Lasagna snipped from a local newspaper, suggesting this might be a future Democratic ticket.

He took part in forums in London and other European capitals where he was seen as a liberal revolutionary in opposition to both pharmaceutical companies and his own profession.

Lasagna’s misgivings

Despite being the poster boy of the new science of drug evaluation, Lasagna had deep misgivings about the 1962 regulations. Thirty years later he said:

“in contrast to my role in the 1950s which was trying to convince people to do controlled trials, now I find myself telling people that it’s not the only way to truth.

“My favourite quotation was taken from Austin Bradford Hill’s Heberden Lecture in 1965: “If one came to the conclusion that the only way to find out the truth about a medication was to use a controlled clinical trial, it would mean not that the pendulum had swung too far but that it had come completely off its hook”.

“In another part of the paper [Hill] comes up with something else that I have been trying to sell to people with not an awful lot of luck. What he said was that a controlled trial does not tell the physician what he would like to know which is how do I know in advance without engaging in trial and error which antidepressant is better for Mr Jones or Mrs Smith. That’s what doctors and patients would like to know. We don’t do that”.

Hill and Lasagna had similar roles in the US and UK but Hill hadn’t enshrined clinical trials in legislation or in a bureaucratic apparatus. Lasagna had and could see the problems. This may have played a part in his involvement in the Panalba case and in what many see as his downfall.

The Panalba Affair

Following the 1962 Amendments, FDA put in place the Drug Efficacy Study Initiative (DESI), to review older drugs on the market to determine whether there was adequate evidence of their effectiveness. This involved panels of experts drawn from the National Academy of Science and National Research Council, who adjudicated on drugs licensed from the 1950s or earlier. It led to a large scale culling of many effective older drugs if companies invited to run clinical trials to demonstrate their efficacy chose not to. (See E.Shorter: Before Prozac)

In 1969, FDA’s DESI process made its most controversial decision when it recommended the removal of Upjohn’s Panalba from the market. Panalba was a combination antibiotic comprising novobiocin and tetracycline. FDA was then pharmacologically puritan. It disapproved of combination antibiotics in principle. They encouraged lazy medical practice – rather than work out what the patient actually had, doctors just took a scatter-gun approach.

There were grounds to think novobiocin simply added to the burden of side effects of the combination. There were a number of deaths – 12 to 15 more per year than might be expected. Was the number excessive? Panalba sold in vast quantities – in 1969 it accounted for 12% of Upjohn’s income.

But did the new 1962 amendments give FDA a basis to remove Panalba from the market? Congress had specifically rejected any consideration of comparative efficacy.  If a drug was thought to be possibly weaker than older drugs on the market, but still met criteria, it had to be licensed. Without this Prozac and Zoloft would likely never have been licensed.

The DESI experts argued that while the criterion for licensing an antibiotic was superiority against placebo, in the case of a combination antibiotic the criterion must be adequate and well-controlled trials showing superiority against each of the individual components of the combination. There were no RCTs at the time in which any combination of drugs had proven superiority to each of its individual parts.

The experts recommended removal. FDA requested Upjohn do so. Upjohn fought back, engaging the Nixon administration on its side, and taking the issue to the Supreme Court.

Lasagna was on the record as viewing fixed dose combination antibiotics as irrational. He was also in favor of regulation being open to input from experts outside the regulatory apparatus and not just leaving it to the bureaucrats, as was happening with DESI.

So it was then a jaw-dropping moment when Lasagna rode to Upjohn’s rescue arguing that FDA’s regulations on fixed combination therapies were scientifically unreasonable. The drug was in such widespread use, that while it had evidence for adverse effects, aggregated medical wisdom suggested it was certainly efficacious.

FDA’s general counsel responded that Lasagna’s rhetoric:

“stands in bold contradiction to every scientific precept he has advocated publicly and to his profession”.

Perhaps used to handling the media, he thought he could ride the storm. He wrote to the editors of The Medical Letter that:

“I have never prescribed Panalba in my life, and probably never would have.  My main objection to the way this problem was handled was that it did not represent due process”.

In his view the problem was that the matter was being decided behind closed doors and apparently arbitrarily. Nevertheless, The Medical Letter publicly dropped him from its Advisory Board. Close collaborators like Louis Goodman distanced themselves from him and expressed dismay at his position.

The Supreme Court ruled in favor of FDA. Upjohn lost. FDA lost its commissioner. Lasagna also lost. He left Hopkins’ for Rochester University a year later. There he set up the Center for the Study of Drug Development. It was a time when Institutes like this were being set up – Silvio Garattini set up the Mario Negri Institute.

From this position he argued that FDA had become the slowest agency in the world to license new drugs and Americans were losing out. He provided the first estimates of the development costs of new drugs. He chaired a committee that tackled the crisis that the licensing of drugs for AIDs posed FDA – this led to an accelerated approval process and later the Prescription Drug Users Fee Act (PDUFA).

All these positions were regarded as favoring industry, and industry funding for the Center was noted. By the 1980s it had become customary to view him as a business-friendly conservative – an astonishing transformation.

You and your meds Give the real story. Get the real story.

© David_Healy for Dr. David Healy, 2013.

To celebrate May Fool’s Day last year The Scientist ran an article on Data Diving. This featured the work of Peter Doshi and Tom Jefferson and their efforts to get clinical trial data on Tamiflu from its makers Roche. Data access has become an even bigger saga in the last eleven months with BMJ leading a charge to demand access to trial data.

The other person featured in Data Diving was Robert Gibbons, who was supposedly given unfettered access to patient level data from the trials of Lilly’s Prozac and Wyeth’s Effexor (see Coincidence a fine thing, May Fools’ Day). Just as Doshi and Jefferson’s access overturned a myth – that Tamiflu has a significant clinical effect – so also Gibbons’ access to the “data” according to The Scientist seemingly overturned myths. In this case, the myths that antidepressants don’t really work and that they cause suicide. It was, it turns out, lack of access to the data in the first place that led us to these mistaken beliefs. Companies don’t engage in conspiracies, we are being told, they are masters of the cock-up, and if given a choice of feet to shoot themselves in will opt for both feet. It needs independent academics like Robert Gibbons to wade in and put a stop to their self-injurious behavior.

Gibbons in fact didn’t have access to anything the original authors of the Prozac papers hadn’t already had access to. The original authors were all Lilly personnel with even fuller access than Gibbons was later given. Gibbons also managed to steer clear of other data in the public domain that could be readily accessed that show incontrovertibly that Prozac and Effexor can not only trigger suicide but that the clinical trial data shows that they have led to a net loss of lives – more lives have been lost than saved.

By ignoring relevant accessible data in favor of data no-one else can access, Gibbons has turned the standard access to data argument on its head and made access to data that comes through companies a potential liability for all of us. It’s hard to call the Gibbons version of data access anything less than a perversion.

April Fool

Keeping a straight face, last May I suggested that the give away that this was a May Fool’s Day joke was that very few articles in recent years in the psychiatric or any other literature have received such withering critique as the Gibbons’ articles to which The Scientist refers. The journal’s fact checkers would never have missed this, and by picking such an egregious piece are clearly letting us in on the joke.

The best response, I suggested, was to carry on in joke mode and invite Dr Gibbons to chair an interview panel to recruit academics to whom companies would be prepared to make data available in the manner Lilly and Wyeth had done with him.

What began as a joke took shape later in the year. In contrast to Roche’s resistance to data access, GSK facing a $3 Billion fine fought back with a press release that got them great kudos. Andrew Witty, their CEO, said they were going to make their clinical trial data available. The Gibbons experiment began to look more and more like a trial run for company efforts to manage calls for data access. And there is considerable evidence that academics and FDA explored controlled data access as a way to close down debate on treatment related adverse events (Access to data)

This has now led GSK to set up a portal for researchers to access recent trial data (GSK data access). To do so they will have to submit an analytic protocol to an independent panel (Independent Panel) whose job is to decide if this application for access to the data is going to be sanctioned.

It is of course only responsible to put the proper research governance in place. We don’t want people able to get in and fish around in the data and start making irresponsible claims that will alarm the public. We, in GSK, are completely committed to proper analytic procedures, as advocated in Bad Pharma and we take a leaf out of Bad Science when it comes to concerns about alarming the public as Andrew W did with MMR vaccines. Ah if Andrew Wakefield hadn’t existed we’d have had to invent him.

When does Yes mean No

Here is what’s happening. In 1962, Louis Lasagna introduced the first consent form into clinical trials involving new drugs. It simply asked the patient to sign that they had been told that the drug they were being treated with either was or might be an investigational new drug. One consequence of the thalidomide crisis of 1962 was that FDA made these “informed consent” forms mandatory.

All industry trials now have informed consent forms but their purpose is just the opposite to Lasagna’s original intention. We now have slippery forms that hide the riskiness the original form conveyed. Of greater importance to companies, they tell anyone who reads them that the company will make sure that no-one gets to see their data other than those who are authorized. This may sound good but it means we only show data to the regulator – and only then when we chose to. It’s doubtful if any patients spot that they are consenting to their data being hidden for ever when they sign.

GSK decides America doesn’t exist 

Just as the meaning of consent forms was turned inside out, Andrew Witty’s new proposal turns the meaning of data access inside out. If “fishing” is not allowed, and the only way to look at the data is on the basis of a predetermined protocol, then essentially outside investigators can probably only come up with the same answers that GSK came up with in the first place. Rather than being a well paid inside outsider like Gibbons, anyone applying for the data will be an unpaid outsider and even more valuable to companies accordingly.

There is no proposal to turn the data over to someone like me and let me fish. The data will be retained within GSK while I and others will be able to access the variables we pre-specify – with our every key stroke monitored (for quality control purposes). The data won’t move over to my computer where I might be able to look at it one way this week and another way next week or where it could be combined with other data from other drugs in its class.

Thirteen years ago, a US court mandated me to go into GSK’s healthy volunteer trials archive in Harlow. I was looking for evidence of suicidality in these studies, but what leapt off the page was that these volunteers were having withdrawal problems. Under the new arrangements, there won’t be any pages for anything to leap off.

The US Supreme Court has ruled on this issue in the Matrixx case stating that investors have a right to fish in the data and make their own minds up as to what it shows. The Supreme Court has ruled against the kind of data access on offer now from GSK and other companies.

More generally, as Jack Scannell puts it, Christopher Columbus didn’t reach his pre-specified primary endpoint.  If we take GSK’s recommended approach we would not now accept that America exists.

The plural of anecdote is data

Fishing as any good angler will tell you is an art. It is also critical to science. Just as they turned the meaning of Consent inside out, companies have made Fishing a term of abuse.

When you catch a fish you know what you’ve got. In contrast we don’t know what clinical trials can do to data. For instance, when the SSRI trials began first, it is quite possible that companies didn’t know they could hide suicides and suicidal acts by selecting the right patients.  Every time both a drug and the illness it treats produce the same problem, whether heart attack, homicide or diabetes, clinical trials risk hiding a drug induced problem rather than revealing it.

In just the same way, by repeating the mantra that the plural of anecdote is not data, as Dee Mangin spotted, companies have obscured the fact that the original phrase was “The plural of anecdote is data”.

If the plural of Anecdote were not Data, Google and the entire Big Data movement would be out of business. This is a good example of how conflicts of interest can be helpful – it was clearly critical for the currently intensely fashionable Big Data movement to demolish the idea that anecdotes are not useful by discovering the original version of the quotation.

From a Big Data point of view, Andrew Witty’s Data Access proposals look like efforts by the Chinese government to censor the Internet. But for his efforts, Andrew is portrayed by BMJ as the candidate of Hope and Ben Goldacre has apparently described his offer as a “cartwheel” moment.

End of the Line

What happened next in the Gibbons story is a cautionary tale. Several sets of academics wrote to Archives pointing out the lethal flaws in the Gibbons’ papers that ranged from inappropriate data inclusion to incompetent mathematical calculations to biased interpretations. Letters like this would once have been published in a good journal – science depends on robust debate about what the data shows. Without debate, error is propagated and the self-correcting function of science is disabled, as Barney Carroll has said. But Archives refused to print.

Archives were forced to back down – perhaps only because it didn’t seem to be a good idea to draw too much attention to what was going on.  In future a journal editor would have a perfect defense against publishing letters from any critics of industry. Why publish when on the face of it, Gibbons or Witty or Wakefield are claiming access to data that their critics don’t have?   Of course, science depends on debate about data – but it does not depend on publishing the rants of people who are unhappy about something but have not analyzed the data. From an editor’s point of view allowing letters that were not based on the data seems to be tackling the man (Gibbons, Witty or Wakefield)  rather than the ball.

Tackling the man is not cricket.  But provided you play the ball all is fair, even eleven lined up against one as in cricket – the English epitome of fair-play.

Illustration: Glaxo Buys Open Science (PDF), 2013 Billiam James

You and your meds Give the real story. Get the real story.

© David_Healy for Dr. David Healy, 2013.

The invitation from the London Review of Books to review Ben Goldacre’s Bad Pharma™ reads:

“We were unsure, at first, what a review could add that isn’t already in the book – scrappy summaries and bits of praise are not for us. The book is of sufficient importance that the main thing is to get someone who knows what they’re talking about to present the material confidently.. frame the discussion”.

My head said it was inconceivable that the LRB wouldn’t take a review, even if it was at odds with the invitation to praise Bad Pharma. But my gut told me the inconceivable was about to take flesh.

Sure enough LRB turned down the review. Because, they said, their readers would be baffled by it – piquant given that LRB specializes in complex reviews of the esoteric and the obscure.

Now it is unfair to say that if Ben Goldacre didn’t exist, Andrew Witty, the CEO of GlaxoSmithKline, might have had to invent him. But it needs something like this to flag up how perilous our position is and how paradoxical – seemingly beyond the capacity of the editors of LRB to follow. This rejected review will puzzle some, and perhaps annoy those it doesn’t puzzle because it leaves answers for another day.

The review

Ben Goldacre made his name with an earlier book Bad Science. Bad Pharma is equally well written. It will be accessible to anyone interested in health and its politics. It strikes the right note of outrage. It tackles the problems pharmaceutical companies pose to medical care and Evidence Based Medicine. The risk is that the solutions it proposes will aggravate rather than resolve our problems.

Data gone missing

The central problem it targets in the opening section is the clinical trial data missing in company vaults. The story is bang up to date, covering Roche’s withholding of key data on Tamiflu, leading governments worldwide to hand over billions of dollars of your money to stockpile Tamiflu in recent years.  The more of this data academics like Peter Doshi and Tom Jefferson have got hold of the more questionable this decision to buy the drug has looked.

Regulatory capture

The next section deals with what is widely called regulatory capture. The regulatory agencies that approve drugs, such as the US Food and Drugs Agency (FDA) contain many bright and good people. But somehow the system fails patients and doctors, and simply can’t be trusted to ensure that medications on the market are safe and effective.

RCTs & EBM

The third section introduces randomized controlled trials (RCTs) which form the basis for evidence based medicine (EBM). RCTs and EBM sound as good as motherhood and apple pie to most people. After outlining how RCTs and EBM should work, Ben offers a compendium of ways in which companies game RCTs including selected reporting, selected patients, and selected comparators, in trials that are too short, too long or too small, that yield outcomes that are surrogate, composite, incomplete, or stem from subgroup analysis, with clinicians misled by talk of dramatic relative risk reductions when the absolute risk reduction is close to non-existent.

The big picture – RCTs are critical to good medicine and everything would be fine if only companies didn’t “game” them.

Marketing

The final section entitled “Marketing” contains the juiciest details and the reddest meat. It outlines how advertising to patients works, how companies recruit celebrities to endorse products, sell diseases to sell medication, create patient groups, and employs PR agencies to get their message out and bury their critics.

It covers drug adverts in medical journals, the tune to which journals profit from drug company articles, the corrupting power of trinkets and free lunches, how sales reps track the personalities of doctors, and how companies like IMS Health sell data on the scripts that doctors write so companies know exactly what pitch will work with your doctor.

Ben’s searchlight switches to ghostwriting and how companies now run the continuing education of doctors. This leads to the knotty issue of conflict of interest. He draws complex distinctions between situations and behaviors, and the merits of greater or lesser puritanism, and to his credit is not an extreme puritan.

The wrap

The book ends with a scene, a question and a plea.

• The scene is Ben being told at a party that Andrew Witty, GSK’s current CEO, is a good guy, who bangs the table in his efforts to ensure things are done better.
• The question is, how will industry respond to the challenge he poses?
• The plea is to any of us who have any other ideas on how to solve all this, to let him know.

Framing the issues

Many readers of Bad Pharma will know much of what is here from books such as Marcia Angell’s The Trouble with Drug Companies or Jerome Kassirer’s On the Take. Where is the problem in re-iterating it eloquently? The central problem is the premium Ben puts on controlled trials not found in other books.

Marketing 101

Ben’s Marketing chapter shows how doctors just don’t get it. It confuses sales for marketing. Marketing means understanding doctors better than they understand themselves, and shaping their thinking so that the drug becomes the unquestioned answer to any problem a doctor faces. There is no better way to do this than with clinical trials in eminent journals.

Bad Pharma cites all the research showing that companies get the results they pay for but ignores the research showing that on all quality metrics, whether adequacy of trial design, transparency of procedures, or declaration of conflicting interests, industry trials routinely come out better than academic studies.

Ben cites studies about how doctors don’t believe they can be influenced by sales trinkets. Doctors say they follow the evidence. Ben believes they are influenced by the gifts (sales), and would prefer them to be influenced by the evidence. Andrew believes that swayed by books like Bad Pharma, doctors are increasingly influenced by the evidence (marketing). Andrew uses gifts as decoys.

Bad Pharma spots the sneaky little sales gnats and swallows the marketing camel, and while the advocates of evidence based medicine do just this, the only outcome can be growing perplexity at worsening indigestion and ever shriller calls for more regulation and policing of conflicting interests – which pleases Andrew.

Regulation 101

Bad Pharma calls for more regulations but the more regulations there are the stronger industry becomes. The Chinese sage Chuang Tzu caught the dilemma beautifully in 323 BC:

“For security against robbers who snatch purses, rifle luggage, and crack safes, one must fasten all property with ropes, lock it with locks, bolt it with bolts. This is elementary good sense. But when a strong thief comes along he picks up the whole lot, puts it on his back, and goes on his way with only one fear; that ropes, locks and bolts may give way.”

The problem for healthcare worldwide goes back to a set of regulations – the 1962 amendments to the US Food and Drugs Act put in place following Thalidomide.  These were later adopted everywhere else. They had three critical components to them:

1. Product patents supersize profits and risks

The first component involved maintaining the US system of product patents on drugs rather than the German system of process patents (Dancing in the Dark). Congressional staffers in 1962 had demonstrated that process patents led to more innovation in pharmaceutical development and produced cheaper drugs than product patents but instead the Germans were persuaded to change to product patents.

Universal product patents laid the basis for the development of blockbuster drugs pioneered by Glaxo two decades later. Blockbusters are drugs that earn a billion dollars or more per year for a company. They are not life-saving compounds. They are highly marketable products that are literally worth more than their weight in gold. This distorts company priorities. It puts a premium on hyping the benefits and concealing the hazards of a few unimportant drugs like: Prozac for depression, Lipitor for cholesterol lowering, and Fosamax for osteoporosis, all of which we could have easily managed without.

But companies can now go out of business if a significant hazard of their blockbuster comes to light. So company ingenuity is funneled into hiding hazards. Bad Pharma is silent on the role of patents in creating this perverse incentive. By putting the premium it does on clinical trials, it plays straight into pharma’s hands.

2. Prescription-only status addicts doctors 

A second set of bolts put in place in 1962 was prescription-only status for medicines (Dance of the Sugar Plum Fairies). The idea that drugs should be prescription-only fits Ben’s worldview – no matter how health literate you are doctors have spent more time being educated in these things than you and they’re here to manage you.

But prescription-only was a mechanism designed to control addicts and it makes doctors rather than their patients the consumers of medicines. And pharmaceutical companies bring more money to bear on influencing this small band of consumers – $50,000 per annum per doctor – than other companies bring to bear on influencing an entire population. When they slip on the Ring of Prescription Privileges, doctors become visible to Eye of Sauron and shrivel.

The hazards of thalidomide came to light in Germany because it was over-the-counter there and doctors didn’t make a living out it. Ditto with tobacco and alcohol.

In contrast, the significant hazards of prescription drugs now take 15 – 20 years to be accepted. The combination of trials and prescription-only status has fashioned doctors into a risk-laundering service for companies. Bad Pharma mentions nothing about this.

3. The capture of medicine 

Controlled trials were the third set of ropes and bolts put in place in 1962, and Andrew is praying they don’t give way (Dance to the Music of Time).

Louis Lasagna was the Ben Goldacre of his day. He was the first Professor of Clinical Pharmacology, the author of the version of the Hippocratic Oath that many doctors take on qualifying, and one of the earliest exponents of controlled trials. In 1962, almost by accident, he slipped the use of controlled trials as a test for efficacy into the FDA amendments and set us on the road to tragedy.

Regulations up till 1962 had been about safety. Forcing companies to show a drug worked for something was intended as an additional safety step. Eliminating drugs that don’t work seemed the perfect way to “first do no harm”. Except that’s not what happened.

All of a sudden this new scientific tool, whose uses and quirks are still not fully understood, became a tickbox for bureaucrats – if there are some positive studies regulators can let a drug on the market and no-one can criticize them afterwards no matter what goes wrong.

This is the point at which Bad Pharma makes a category mistake. It treats a box ticking exercise as though this could inform the practice of medicine.

Regulators deal with both food and drugs. All they want is a way, in the case of food, of determining if this yellow slab that could be lard colored to look like butter meets criteria for butter. If it does they can let companies label their product as butter. It’s not the regulators job to decide if this is good butter, what butter might be used for, whether it’s healthy for you – that’s up to consumer groups and physicians.

For drugs, the criterion is two positive trials. These regulations were not designed to have anything to do with the practice of medicine, they regulate adverts. The FDA in the US, along with regulators in the UK and elsewhere, are ticking boxes perfectly well – and as the law stands cannot do otherwise. It is hardly surprising that pharma have found many ways around the regulations. Consumer groups and physicians step up to the plate when it comes to butter but not when it comes to medicines. Who’s captured?

Introducing trials into the regulatory apparatus has created a mess.  What’s been captured is the production of evidence and the more books like Bad Pharma fetish clinical trials the more captured medicine becomes.

The limitations of RCTs  

RCTs can give the wrong answer

RCTs can be very helpful when they disprove claims that a drug works. This can rein in the unscrupulous huckster, the credulous physician and protect the vulnerable patient.

But RCTs can also be unhelpful. For many conditions they simply do not produce a meaningful outcome. For instance, where superficially similar problems can be caused by both drug and illness, such as suicidality on antidepressants, RCTs may perversely show that drugs that clearly cause a problem seemingly don’t cause it.  Within the mental health domain it’s debatable if RCTs can show anything “works”.  Using the clinical trial procedures used to bring Prozac on the market, alcohol could have been shown to be as effective an antidepressant as and safer than Prozac (Shadow Dance).

Rather than being used as initially intended – to first do no harm – trials have given rise to an efficacy fetish. As a result we are now all put on an increasing number of drugs that have been approved by regulators and there seems to be no way to limit the number of drugs we end up on. End up on because these drugs that work have not been shown to save lives. The result is that drug induced death is now the third leading cause of death. This is a tragedy of mythic proportions.

RCTs tell us almost nothing about cause and effect. They discover nothing. They likely block the discovery of many treatments. But for the fact that Barry Marshall in 1980 took a laboratory rather than a clinical trials approach to showing ulcers were caused by h pylori and could be cured by antibiotics, Glaxo would have used RCTs to bury the evidence that antibiotics cure ulcers to defend the very first blockbuster drug, their H2 antagonist for ulcers, Zantac.

More generally in a 400 page book about treating illnesses and drugs, Bad Pharma has only 3 pages (101-104) that come close to dealing with biology, even though biology is the primary driver of the superficial associations that controlled trials throw up.

Disease mongering

Efficacy for something is another component of the tragedy. This element restricted companies to selling medicines to doctors for diseases only. In 1962, no-one foresaw that if constrained in this way companies would convert what had been a series of vicissitudes of everyday life and normal variation in terms of beauty and functionality into a set of diseases.   And so we have all become depressed, osteoporotic, with hypercholesterolemia where otherwise we might have had burn-out, aging bones that could be managed by exercise, and a diet-related issue that is only significant against a background of more important cardiac risk factors.

Companies now speak the language of medicine to an extent that doctors fail to appreciate.  Not only have vicissitudes been transformed into illnesses, but acute illnesses have become chronic and the moral imperative to treat that is brought to tuberculosis has been co-opted to sell products for restless legs and fibromyalgia.  In 1962, the drive was to temper patient enthusiasm for treatment with medical skepticism.  Fifty years later skeptical patients try in vain to temper the zeal of doctors following the supposed evidence embodied in the latest guideline based on published trials.

Fixing a bad system

Bad Pharma describes the superficial features of the problem but it fails to analyze how we got here. It just assumes Pharma is Bad and that everything else follows from this.

This analysis in contrast appeals to an historical moment – things that might have been otherwise. Some might argue the insertion of controlled trials into drug regulation was an accident waiting to happen. Others might say this is an unparalleled demonstration of the perils of interfering with the market. Whatever frame you opt for, the result is the strangest market on earth in which mega-corporations spouting a rhetoric of market freedom operate in a totalitarian way to control the least free market ever seen.

Ben locates missing data as the key problem and access to the data as the solution. This is a hot issue in Europe with the British Medical Journal leading a campaign for access to clinical trial data.

Is Andrew feeling nervous? Probably not. Companies have been managing this scenario for years. When recent calls for access to trial data emerged (access to trial), GSK immediately offered access to their data once the right academic board and governance is in place. With control of the analytic approach to the data, GSK can achieve both the result they want from “independent” analysis and the kudos of transparency all in one go.

Andrew has patient groups lined up – not paid for by companies as Bad Pharma would have you believe – to recast the argument in terms of academic dilettantes versus patient rights to privacy and confidentiality. For most casual readers there can only be one winner to this argument. Andrew has politicians on board with the need to manage the communication of risk in the public domain – and in a supreme irony on this issue the primers for politicians cite Ben’s Bad Science as their number one text.

It’s like pitting a major league outfit against a set of minnows. If the minnows win they are likely to make a bad situation worse. Good intentions aren’t enough. Unless the good guys understand the system they are up against they can make things a lot worse – just ask Lou Lasagna. Access to trial data on GSK’s terms will make the days of Bad Pharma look halcyon. The good guys don’t think there could be any adverse effects to good clinical trials. If the outcomes aren’t right, like a religious belief it will always be because the trials weren’t good enough, not because there are so many things for which trials aren’t the answer.

“If the outcomes aren’t right, it will always be because
the trials weren’t good enough, not because there
are so many things for which trials aren’t the answer.”

Missing data

Missing data are critical but Bad Pharma misses the critical data. Andrew probably purrs at Ben’s dismissal of adverse event reports, at his missing company perversities around hiding adverse event data that are more astonishing than ghostwriting. For instance companies in the US now encourage patients and doctors to report adverse events directly to FDA rather than to the company. Enlightened? Very – companies have a duty to follow up adverse event reports and to establish causality whereas FDA doesn’t. Diverting reports to FDA saves money, reduces legal liability and relegates adverse event reports to the status of anecdotes (See AW and AW2).

The ultimate perversity is when in the face of hundreds of compelling reports of a treatment induced problem, when employees using standard causality algorithms have said their drug caused this problem, companies will under oath deny there is any link between the problem and their drug (Burn in Hell). Thanks to EBM, they can get away with this. How? Well built into RCTs is the notion that the only findings that count are those that are statistically significant. And because RCTs are designed to see whether one event is statistically significant or not – whether the drug works – they cannot properly look at what else the drug might be doing and so the safety of drugs which was in 1962 the primary goal of regulation has been eclipsed.

The fetishing of clinical trials means it’s now difficult for doctors or patients to believe the evidence of their own eyes. Restoring this ability – which clinical trials almost by definition attempt to undermine – is more important to the practice of medicine than access to data about “butter”.

“The plural of clinical trials is not medicine.”

The individual patient once sat at the top of the EBM hierarchy – but no longer – following a relentless repetition of mantras like “the plural of anecdotes is not data”.  Well the plural of clinical trials is not medicine.

The candidate of hope 

At times you have to stand back and admire how good Andrew is at his job. Is he really banging the table just to get GSK to be a bit more like what Ben would like? Ben calls for more industry whistleblowers but most of what he cites comes from industry whistleblowers in the US and very little from doctors anywhere. If I was one of the many ex-pharma employees whose whistleblowing cases have not worked out, I would feel bitter and ask just where have doctors been in all this?

The problems could be settled without trying to make Pharma good. Doctors could but don’t take the simple step of banning industry “trials” from their journals.  Because the New York Times takes the checking of the primary sources of an article more seriously than the New England Journal of Medicine does, we might all be safer if clinical trials were published in the NYT rather than the NEJM – which is a damming indictment not of pharma but of doctors.

Bad Pharma is relentlessly British in its focus. Ben wants the Royal Colleges to stand up and make a difference. Within the terms of the debate he outlines, there is almost nothing Britain can do. The one thing that might rattle Andrew would be an exhortation to doctors and patients to start believing the evidence of their own eyes again – but this Ben cannot say.

Instead Andrew offered controlled access to clinical trial data. In response as the BMJ noted “[Witty] was singled out for praise by one of the industry’s harshest critics.  Ben Goldacre called it a “cartwheel moment”.

The BMJ issue in which this comment features had a three-page spread on Andrew Witty featuring his image on its front cover in political poster format, resembling no-one more than Barack Obama, with a single word Hope underneath.  Making the case for GSK, as Not so Bad Pharma, he says “the 100,000 people who work for GSK are just like you, right?  I’m sure everybody who reads the BMJ has friends who work for drug companies…  They’re normal people. Many of them are doctors”.

Professional suicide

EBM like Freud has been wonderful in bringing the biases of both doctors and patients to light. But just as the Catholic Church has learnt there comes a point where routine dismissal of what people say to you because some of it is mistaken leads to a crisis, medicine needs to realize that EBM has led us into a comparable crisis.

Doctors need to realize their profession is at stake (Professional Suicide, Model Doctors). If clinical judgment and discretion no longer matter, nurses and others will be far cheaper prescribers and can more readily be ordered to stick to guidelines than doctors. Anyone can get you on a drug; it takes an expert to get you off. How does an expert know when or how to do this? Not from clinical trials.

Bad Pharma™ hypes the RCT and EBM brand, and denies the existence of any side effects. The only other place in medicine where this is done to a comparable extent is with blockbuster™ drugs. A Freud might think the™ revealing.

Lou Lasagna stands as an extraordinary symbol of how misguided this approach might be. He pushed for an inclusion of placebo-controlled trials in the 1962 Food and Drugs Act in the belief that establishing the efficacy of a drug would make a contribution to the safety of all us. But as of 1962, only one drug prior to marketing had been demonstrated in a placebo-controlled trial to be safe and effective – thalidomide.

You and your meds Give the real story. Get the real story.

© David_Healy for Dr. David Healy, 2013.

A year ago this month – March 28, 2012, to be exact. British Colomubia’s office of the auditor general told the B.C. Ministry of Health about a complaint someone made about the way contracts were being awarded and how research was being conducted within the ministry’s Pharmaceutical Services Division (PSD).

You and your meds Give the real story. Get the real story.

© David_Healy for Dr. David Healy, 2013.

In the England and Wales there are roughly 5000 suicides in roughly 60 million people per year. This would until recently have led to around 2000 hangings per year, 34 hangings per million people per year, 3.5 per 100,000 people per year.

Bridgend in South Wales has a population of 40,000. The greater Bridgend area has a population of 130,000. There should be 18 hangings per 100,000 people over a 5 year period, 24 per 130,000 per year.

In recent years however in both the US and UK there has been a rise in the number of hangings so that this mode of death now accounts for 50% of cases. If this applies in the Bridgend area, we might expect 28 hangings per 130,000 over a 5 year period, roughly 6 per year.

There were in fact 79 hangings in Bridgend between January 2007 and February 2012. The hangings continue unabated, so the true figure may be in the 90s. This means there have been 16 per year – an excess of 10 or more hangings per year.

Vanishing Suicides

There have likely been a lot more self-destructions than this in Bridgend. Coroners have considerable discretion and recently a great deal of encouragement to use narrative, open or death by misadventure verdicts rather than to record a verdict of suicide. To record a suicide verdict they should be satisfied that the person intended to kill themselves. One of the primary indicators of intent is a suicide note. In the Bridgend cases, there have been few suicide notes. This has made it easy for coroners to manage perceptions of what might be going on.

Having a narrative or open verdict can be extremely important for families. I have written reports in over 20 inquests arguing that it would be appropriate to return a narrative rather than a suicide verdict, in the case of people whose suicide has been triggered by an antidepressant.

But this use of narrative verdicts has produced a situation where suicide figures are close to worthless. The British suicide rate is comprised of cases recorded as suicides along with a proportion of narrative, open or other verdicts, with the proportion chosen down to bureaucratic whim. We do not have a self-destruction rate and absolutely no idea as to how many verdicts, either suicide or narrative, are linked to antidepressant or other drug intake.

A website antidepaware was recently set up to track deaths by suicide or misadventure or related that are related to antidepressants. It has logged over 1600 UK suicides involving antidepressants of which 43% were recorded as suicides by the coroner, 26% as narrative verdicts, 19% as open verdicts, 5% as death by misadventure and 7% as accidental.

Hanging & Kneeling

While the suicide rate has become ambiguous, it is not possible to conceal the number of hangings.

Bridgend has had an unusual number of hangings. An apparently odd feature is that these hangings have involved a lot of kneeling. The fact that many victims have been found hanging but with their feet on the ground or close to kneeling has given rise to speculation about internet or other cults, and about serial killing rather than self-destruction.

I had been exposed to relatively few SSRI suicide cases when Linda Hurcombe came to me telling me of her daughter Caitlin, who after 6 weeks on Prozac hung herself using her horses’ lanyard (see Let Them Eat Prozac).

Soon after that with colleagues I ran a healthy volunteer study designed to test how antidepressants work. In this study, two completely normal women while taking the SSRI sertraline (Zoloft) became suicidal. One of these two had vivid imagery of hanging herself.

Around this time too I got involved in the Miller case. Matt Miller was a 13 year old boy who had just changed schools and was feeling nervous. His parents prompted by the teacher brought him to a doctor who put him on Zoloft. Seven days later he hung himself in the bathroom between his parent’s bedroom and his bedroom.

Pfizer, the makers of Zoloft argued that this was not suicide but auto-erotic asphyxiation gone wrong. As evidence, they pointed to the fact he was not suspended several feet above the floor but had his feet on the ground, almost kneeling. They went so far as to scour the carpet in the bathroom to collect potential evidence for seminal stains.

It was Yvonne Woodley’s case in 2010 that explained the hanging issue to me – something that anyone with an interest in the area could in fact have found from Wikipedia.

Yvonne Woodley was a 42 year old woman who was having marital difficulties. She presented to her doctor with sleep problems. The doctor viewed her as being under stress, and as posing absolutely no suicide risk. She gave Yvonne citalopram. A week later the doctor noted that Yvonne was more agitated and there were fleeting thoughts of suicide – so she doubled the dose of citalopram. After a suicide attempt, she doubled it further and a short while afterwards Yvonne hung herself.

She hung herself in the attic of her house. Given the kind of person she was, the rest of her family found it unbelievable that she would have hung herself in the house with her two daughters downstairs but a common feature of SSRI suicides is the apparent lack of concern for the effect on others.

The fact that Yvonne was close to kneeling enabled the coroner to return a narrative rather than a suicide verdict. The pathologist explained that when people are weighing up the possibility of hanging themselves, wondering about it, they might put a rope in place and test themselves against it. If they do this, it is in fact very easy by putting pressure on the carotid sinuses that are in the side of the neck to slip out of consciousness and falling forward to end up asphyxiated. If you have begun with your feet on the ground you can end up kneeling or close to kneeling.

The First Cases in Bridgend

Dale Crole, 18 Found hanged, 5 January 2007 David Dilling, 19 Found hanged in his home, February 2007 Thomas Davies, 20 Found hanged from a tree, 25 February 2007 Allyn Price, 21 Found hanged in his bedroom, April 2007 James Knight, 26 Found hanged at his home, 17 May 2007 Leigh Jenkins, 22 Found hanged, June 2007 Zachery Barnes, 17 Found hanged from a washing line, August 2007 Jason Williams, 21 Found hanged at home, 23 August 2007 Andrew O’Neill, 19 Found hanged at home, September 2007 Luke Goodridge, 20 Found hanged, November 2007 Liam Clarke, 20 Found hanged, 27 December 2007 Gareth Morgan, 27 Found hanged, 5 January Natasha Randall, 17 Found hanged, 17 January Angie Fuller, 18 Found hanged, 4 February Kelly Stephenson, 20 Found hanged on 14 February while on holiday Nathaniel Pritchard, 15 Kelly’s cousin, found hanged, died 15 February

 Reports in the Media

Jenna Parry was the next person to die. She was found hanging, almost kneeling. Her death triggered the list above and this account in the Independent in February 2008:

“Bridgend was yesterday mourning yet another addition to the alarming number of suicides in the area, after a 16-year-old girl was found hanged in a wood five miles from the town.

Police insisted there was no link between the 17 deaths in the past 13 months and no evidence of a suicide pact or an internet cult.

Jenna’s death came just days after two cousins died after apparent suicide attempts. Kelly Stephenson, 20, was found dead in a bathroom during a family holiday. Hours earlier she had learnt that her 15-year-old cousin, Nathaniel Pritchard, had hanged himself. The two lived a few doors away from each other in Bridgend…….

Following the deaths, a suicide prevention strategy has been announced for Wales. The Welsh Assembly has said it wants a 10 per cent reduction in suicides by 2012.  [As of 2012, the rate has in fact gone up despite the many abilities of coroners and bureaucrats to lower it].…

However, despite the spate of suicides around Bridgend – a county with a population of 130,000 people – police have said there is nothing to link the deaths….

[The coroner] Mr Morris criticized the media’s reporting of the deaths. “The media reporting is influencing young people in the Bridgend area.

“I have noticed an increase in sensationalist reporting, and the fact that Bridgend is becoming stigmatised. The link between the deaths isn’t the internet – it is the way the media is reporting the news.”

Death by Coroner?

Fourteen deaths in Bridgend are logged on antidepaware. There are nine hanging verdicts in which antidepressants are mentioned. There are no hanging verdicts where antidepressants or other prescription medications are ruled out.

What’s happening? One contributory factor to these deaths is coroners. I have been writing to UK coroners for 15 years making the case that they should note where people have been on antidepressant or other drugs at the time of death. The list of drugs now linked to suicide and homicide up to and including school shootings includes anticonvulsants, weight loss pills, some asthma medications, some analgesics, some contraceptives, some medication for acne, a number of antibiotics, medications for malaria, in addition to antipsychotics and antidepressants. See below.

But coroners often do not record drug intake, unless the person has actually died from a drug overdose. In the case of Liam Clarke above he had had some cannabis, and alcohol and was on antidepressants.  The coroner decided that the alcohol he had had affected his judgement. Coroners are under no obligation to explain their thinking on a matter like this and are rarely if ever challenged. There is little doubt that antidepressants can lead to a craving for and increased consumption of alcohol – did this happen in Liam Clarke’s case?

Many of the cases listed above were on antidepressants but we only know this because the police or families mentioned it at the inquest and reporters from the media then reported it. Unless the antidepressant or other pill was the cause of death by poisoning coroners typically don’t mention medication.

In Bridgend, the coroner seemed to play down the role of antidepressants. In one of the inquests involving antidepressants, he refers to “lack of anything in the system that would have altered his judgement”. In others he makes similar comments.

Gary Speed the former manager of the Welsh soccer team is Wales’s most famous recent suicide. A common feature in the extensive reporting of his death was that family and friends found it baffling. The coroner opted not to reveal if there were prescription drugs in his system. Why?

The Role of the Media

The idea that the media reporting of suicides might cause copycat suicides in Britain stems in part from the work of Keith Hawton in Oxford. As a result students in Cardiff University, which is near to Bridgend, are steered to regard the report in the Independent above as sensationalist. Other countries have more striking suicide cohorts – Japan being the most famous – and in the case of copycat suicides by pairs of lovers jumping into Mount Fuji there is a good case for thinking the media might fuel events.

But equally decent and proper media reporting may do just the opposite and bring to light what is going on. There is probably more chance that a good journalist, or someone who has lost a family member or a friend to suicide, is going to solve this rather than bureaucrats or experts brought in to work out what is going on. In this case neither the experts nor bureaucrats linked to this case seem interested to respond to emails from me.

Having coroners refuse to keep a public record of drug intake and browbeat the media into keeping silent seems like the worst of all possible worlds.

What’s Happening?

We have an excess of 60 hangings to explain in Bridgend. The number is growing by the month. If some have happened by accident as outlined above, it needs a public education campaign through the media to alert people to the risks.

Some of these suicides may be copycat. In the same way school shootings may have a copycat component to them. But a copycat needs an original or several original examples to get them going. The distress that leads to school shootings or clusters of hangings needs an original exemplar to shape it into more shootings and hangings – an original event to open this door to others.

There are obvious factors to explain some clusters like a pair of well-known Japanese loves committing suicide together by jumping into Mount Fuji. In the Bridgend case, if we are going to invoke a chemical – a medicine – the scale of the problem almost suggests that some factory in the Bridgend area must be pumping out some chemical that is having the same kind of effect as drugs like Cymbalta or Pristiq. This might seem improbable. But looking at the list of drugs that cause suicide and homicide, below, the improbable begins to look possible. It almost looks probable that this array of drugs will give rise to a cluster like this somewhere if not in Bridgend.

What to Do Next?

The problem of drug induced suicide and homicide is not vast like climate change or famine in Africa. You can make a difference. As things stand your Human Rights are being infringed.  The supposed rights of some unspecified group of people to use (doctors) or take (patients) without having to be deterred by warnings that these drugs can cause suicide or homicide are being used to justify the deaths of people that you know that could be avoided with proper warnings.  This is a breach of the Human Rights Act.

The drugs listed below are not listed as a matter of personal judgement. They are either drugs that companies are obliged to state can cause suicide or for which there is convincing evidence that they have in fact caused suicide. There are likely many more drugs that some government officials and company personnel know cause suicide but about which they keep quite.

1. Some coroners are wonderful. Others are misguided. You do not want to assume your coroner knows what they are doing. You need to establish if they are bringing biases to bear on the issue. You have a right to interview them before an inquest.
2. Drug regulators deal in the wording of advertisements. Public health is not their brief. If you are waiting for a regulator or a drug company to suggest a drug may have contributed to a death, you will be waiting for ever.
3. These problems are rarely solved by outside experts. Communities need to take the issues into their own hands and to this end the media are their allies not the enemy.
4. Contribute details of any deaths by someone’s own hand, accidental or on purpose, to Antidepaware. Contact brian@antidepaware.co.uk
5. Be aware that the following drugs and likely many others can all cause suicide and in many cases homicide. The statement cause here is based on compelling challenge-dechallenge-rechallenge cases – see Doxycycline causes suicide - or clinical trial data or legal requirements for companies to agree their drug can cause suicide for instance

Drugs that can Trigger & Cause Suicide or Homicide

You and your meds Give the real story. Get the real story.

© Jo for Dr. David Healy, 2013.