Genomics, Medicine, and Pseudoscience

Poison for pain, the homeopathic way

noreply@blogger.com (Steven Salzberg) — Mon, 13 May 2013 20:43:00 +0000

At my local mega-grocery store last weekend, I happened to stroll down the aisle dedicated to homeopathic treatments. I saw shelf after shelf of brightly colored packages, all claiming health benefits. Most of these "medicines" were not cheap.

Amazing. To an average shopper, all of these products look like real medicine. The packaging is similar, the claims are similar, and it's all on display at a respectable grocery store. The difference, though, is that none of these products do what they claim to do. Thanks to a special exception for homeopathy created all the way back in 1938, none of the claims on these medicines need to be tested. The homeopathy aisle is an organized, state-sanctioned scam.

The 1938 law was the brain child of a U.S. senator, Royal Copeland, who happened to be a homeopath. Sen. Copeland inserted language into a major food and drug law that declared homeopathic preparations to be drugs. It also allowed homeopaths themselves to maintain the official list of these drugs, called the Homeopathic Pharmacopeia. Talk about the fox guarding the henhouse! Thanks to aggressive lobbying by homeopaths, homeopathic ingredients are not subject to the normal review required of real drugs. Most importantly, homeopathic drug makers do not have to prove their products are effective.

Homeopathy is based on the long-discredited beliefs of Samuel Hahnemann 200 years ago. Hahnemann thought that "like cures like," as long as you dilute the substance sufficiently. Thus caffeine will cure sleeplessness, poison ivy extract will cure an itch, and paralyzing plant toxins will cure pain. None of this is true.

The other key principle of homeopathy is that the more you dilute something, the stronger its effect. This is not only wrong, but it is exactly the opposite of what really happens. Greater dosage levels, unsurprisingly, have stronger effects. In Hahnemann's defense, science wasn't very far along when he came up with these notions.

Real medicine moved on long ago. But homeopathy persists, because there is money to be made - lots of money.

Back to my grocery store. Several shelves were filled with something called Topricin(R), which claims to relieve pain. Sounds like a medicine, right? Real drugs often use "cin" or "in" in their names because the word "medicine" itself ends with that sound. Clever! In front of me I saw Topricin for pain, Topricin foot cream, even Topricin for children. The Topricin packages and the company's website proclaim, in big letters, "Ideal Pain Relief", and in slightly less big letters: "Safe. Effective. Free of Side Effects." It also claims:

"Topricin's 11 homeopathic medicines are proven to be safe and effective for the elderly, pregnant, children, pregnant women and all skin types. Experience Topricin's relief for damaged muscle, tendon, ligament, and nerve tissue."

This is simply not true. It even seems to go beyond the bounds of what the (very weak) FDA regulations allow. The website specifically claims that Topricin is effective for arthritis, back pain, bruises, bursitis, fibromyalgia, minor burns, tendinitis, and more.

Well, what is it? Let's look at just two of the homeopathic ingredients in Topricin:

Belladonna 6X................. Treats muscles spasms, night leg cramps
Heloderma 8X................. Relief of burning pain in the hands and feet

Belladonna for pain? Belladonna is one of the most toxic plants known to man. Eating just a few small berries is lethal. And the one study I could find showed that it has no clinical effect when used in a homeopathic preparation. That's lucky for unwitting consumers: if it wasn't so diluted, Belladonna would make them very sick indeed.

Heloderma? That's the venom from a gila monster. Although rarely fatal, it causes severe pain, bleeding, nausea, and vomiting. This is not something I would take for pain - and I certainly would never give it to children.

I know that Big Pharma is often guilty of deceptive marketing, and I've criticized Pharma many times. But CAM ("complementary and alternative") pharma is every bit as bad. Big CAM takes advantage of generous laws to make medical claims with impunity, often skirting as close as possible to what the law permits. And the Big CAM companies profit handsomely in the process. Everything on the Topricin package - the name, the packaging, the claims - is designed to make the consumer think that it is an effective pain treatment. It's not. It's a modern package of snake oil.

The Physics of Golf

noreply@blogger.com (Steven Salzberg) — Mon, 29 Apr 2013 00:17:00 +0000

[Herman Erlichson was a physicist and a historian of science (he had Ph.D.s in both). He was also an avid golfer, and he was my uncle. He passed away just over a year ago, and I've been wanting to write this column ever since. We corresponded frequently when I was a teenager, in a time when hand-written letters were still common. Here is a small anecdote.]

Everyone who plays golf knows that the driver hits the ball the farthest of any club. It also has the lowest launch angle, or "loft." Clubs with high loft, such as a sand wedge, pop the ball very high up in the air, but don't hit it very far.

The universe of people who both play golf and also know college-level physics may not be very large, but everyone in this club has puzzled over this conundrum: why is it that a driver has a loft of only about 10 to 12 degrees? That seems far too low.

Exactly 30 years ago this month, my uncle Herman Erlichson figured this out. It's the spin.

He published the answer in a serious physics journal [1], but I'm guessing that most golfers don't read physics journals. So here is what he found.

Everyone in freshman physics learns that the optimal launch angle for a projectile - the angle that makes a ball fly the farthest - is 45 degrees, in a vacuum. But in the game of golf, 45 degrees is the angle of a pitching wedge, which (as every golfer knows) hits the ball only a short distance, about half as far as a driver.

Now the physics calculation assumes that the ball is in a vacuum, but still: how come the presence of air makes the optimum angle so much lower? Or as my uncle put it, in his classic understated style:

"The large discrepancy between the approximately 11 deg of loft for the golf driver club and the 45 deg maximum range angle for a vacuum was the motivation to begin a study of the question of maximum projectile range in the presence of air resistance, with particular application to the flight of a golf ball." [1]

The analysis itself is technically very complex, involving 3 forces: gravity, drag (resistance caused by air friction), and lift, caused by the backspin on the ball. All three are big factors, but the theoretical result of 45 degrees only accounts for gravity.

Air friction (or drag) turns out to have a quadratic effect, as my uncle showed. In other words, the drag increases in proportion to the square of the velocity of the ball. So hitting it harder causes a very rapid increase in drag. Here's his graph showing how the angle is affected by quadratic drag:

One consequence of "quadratic drag" is that hitting the ball a lot harder only yields a modest increase in distance. More important, though, is that if we just consider gravity plus drag, the best angle to launch a golf ball is 35 degrees. Lower than 45, but still nowhere near the angle of a modern driver. And the distance here is still too low, only 336 feet (112 yards).

My uncle Hymie figured out that backspin makes a huge difference. Backspin generates lift, keeping the ball in the air much, much longer. My uncle derived equations that allowed him to calculate how the lift force increases with the rate of spin and the speed of the ball. This produced a very different picture of how far the ball would carry at different angles, shown here:

After accounting for lift, the optimum angle is 16 degrees, and the ball flies about 200 yards. (This assumes a typical launch speed by the standards of 1983. The much longer drivers used today create a much greater speed off the tee.) The remaining different between the actual loft of 10-12 degrees can be explained by the fact that for a drive, the teed-up ball is struck just past the bottom of the swing. This makes the launch angle slightly higher than the loft of the club.

There you have it: when you account for all the forces at play, the optimum angle for a golf driver really is around 10-12 degrees.

My uncle Herman Erlichson loved the game of golf and played often, despite having a seriously weakened leg, the after-effect of a polio infection that he contracted in the 1950's. He might have struggled to master the game itself, but when it came to the physics of golf, he solved a mystery that had puzzled physicist-golfers for decades.

Reference

[1] Maximum projectile range with drag and lift, with particular application to golf

H Erlichson. American Journal of Physics 51:4 (1983), pp. 357-362.

For all 95 of Herman Erlichson's scholarly papers, including his paper on the physics of golf, see his Google Scholar page.

Myriad Genetics CEO Claims He Owns Your DNA

noreply@blogger.com (Steven Salzberg) — Sun, 14 Apr 2013 02:00:00 +0000

With the Supreme Court about to hear a landmark case on gene patents, Myriad Genetics, the company that owns the patents under scrutiny, is going on the offensive. I've written about this case before, when the patents were first thrown out by one court, and then restored by another. Now the Supremes will have the final say.

Just last week, geneticists Jeffrey Rosenfeld and Chris Mason wrote a commentary for the Washington Post that warned about the consequences of companies owning the rights to our gene sequences.

Today, in a letter filled with non sequiturs and distortions, Myriad Genetics' CEO Peter Meldrum, worried about whether his company will be able to maintain their monopoly on a test for which they charge $4000, responded. Let's look at his claims.

First, though, let me remind readers that the genes in question, BRCA1 and BRCA2, are linked to an increased risk of breast and ovarian cancer, a risk that was first discovered in 1994 by scientists at the University of Utah. Myriad Genetics owns a patent on these genes, and as I wrote last year:

"Thanks to these patents, you can’t look these genes in your own body without paying a fee to Myriad. Sounds ridiculous, right? Well, that was the state of gene patents until last May [2011], when judge Robert Sweet ruled that the Myriad’s patents were invalid."

Myriad appealed the decision, and the appeals court overturned Judge Sweet, buying into the argument by Myriad's lawyers that "isolated DNA" is not the same as the natural DNA, and that this distinction allows companies to patent it. This is scientific nonsense for many reasons: for one thing, the process of isolating DNA does not create an artificial molecule. The body's own cells isolate DNA all the time, in the process of turning it into proteins. But the appeals court accepted the argument, perhaps just because they wanted to uphold the patents. So now the Supreme Court will re-examine this scientifically ridiculous claim.

Now let's look at CEO Meldrum's letter. He first claims that Myriad's patents

"were essential to developing diagnostic tools that have been used by more than 1 million women to understand their hereditary risks of breast cancer and ovarian cancer."

This claim is simply false. Myriad's patents made no contribution at all (and certainly weren't "essential") to the diagnostic tools used to detect mutations. I know something about these tools, which I've been using in my own research for over 15 years. Furthermore, academic medical centers were offering their own diagnostic tests on the BRCA genes, at a lower cost than Myriad, until Myriad's lawyers forced them to stop. So Myriad's patents have increased costs to patients and, if anything, slowed down progress on making the tests faster and cheaper.

Second, Meldrum writes:

"Were these molecules derived in part from natural material? Sure. But that is true of many patents. Labs routinely turn naturally found molecules into innovative medicines and get patent protection."

One's jaw drops at this irrelevant non sequitur. Myriad has never created "innovative medicine" or any other sort of medicine. And the BRCA gene tests are not medicine: they are a diagnostic test that reads your DNA and tells you if you have harmful mutations in two specific genes. Myriad's patents have nothing to do with medicines that treat breast and ovarian cancer - although it's clear that Meldrum would like us to think otherwise.

Third, Meldrum claims:

"Our tests are also accessible; some 95 percent of patients get insurance coverage, and we offer the test for free to those who cannot afford it."

This too is irrelevant, and also untrue. The fact that 95% of patients have insurance, even if true, has nothing to do with whether or not genes should be patented. And this merely hides the fact that Myriad's test is outrageously overpriced, at $4000 per patient. The actual costs of testing for this gene should be far lower: we can now sequence an entire genome for $4000, and this test only looks at 2 genes out of more than 20,000.

Meldrum also throws out the unproven claim that Myriad offers it for free to those who cannot afford it. Really? Who decides if someone can afford it? If a woman can scrape together the $4000 with great hardship, does Myriad give her a break on the price? I doubt it. And what does this have to do with Myriad's supposed right to own your genes?

Fourth, Meldrum makes the remarkable claim that

"Our patents have also promoted additional research; 18,000 scientists have studied the genes, resulting in 10,000 published papers."

This is just unfounded bragging. Even the most wildly successful scientists would be very careful about claiming that that 10,000 papers have been based on their work. In the case of Myriad, this is just false. If you do a PubMed search for BRCA1, you can indeed find over 9,600 papers, as I did today. However, there is no evidence whatsoever that these papers were even remotely supported by Myriad's patents. It is far more likely that the patents prevented additional research on the BRCA genes. The vast majority of research on these genes was supported by the public, which in the U.S. means by the National Institutes of Health. Meldrum's boastful claim is absurd.

It's worth noting that the original paper describing the link between BRCA1 and breast cancer was published by a multi-institutional team from the University of Utah and other places, who were supported by multiple grants from the NIH and from the Canadian government. Myriad Genetics subsequently licensed the patent rights from Utah, and has used them ever since to maintain its monopoly and prevent others from developing tests on the BRCA genes. To claim that its patents promote innovation is pure nonsense.

The bottom line is that no one invented your genes, and no private company should be able to tell you that you can't even read your own DNA. Today, you can get your DNA sequenced for less than the cost of the Myriad test. Using free software (developed by my lab), you can scan that DNA for mutations in BRCA1 and BRCA2. And no company should be able to tell you not to.

Peter Meldrum's letter reveals that he doesn't care very much about the truth. Meldrum made $4.87 million in 2011 as CEO of Myriad, so it's pretty clear what motivates him. Myriad's use of its patents to charge exhorbitant prices to women at risk for breast and ovarian cancer does not demonstrate innovation. It just demonstrates greed.

Dr. Oz takes a big bite of bad science

noreply@blogger.com (Steven Salzberg) — Mon, 08 Apr 2013 11:30:00 +0000

Mehmet Oz hosts a popular TV show that reaches millions of people. He offers a constant stream of medical advice, and he is popular because he makes his topics sound dramatic, or exciting, or surprising, or all three.

Unfortunately, Dr. Oz sometimes has a poor understanding of science. At least I hope so, because he promotes so many outrageous treatments, with such enthusiasm, that the only other explanation I can think of is that he is simply a fraud. I don't think that's true, so let's give him the benefit of the doubt and assume that when he makes a mistake, he is simply ignorant of the truth. His latest startling revelation is that the metal fillings in your teeth are very, very bad for you. Or are they?

Last week, Dr. Oz hosted a show called "Toxic Teeth: Are Mercury Fillings Making you Sick? The show looked at silver amalgam fillings, which contain a small amount of mercury chemically bound within them. Mercury is indeed a toxin. Should you worry?

One problem with taking a skeptical look at a Dr. Oz show is that he packs each episode with scientific claims, coming at you thick and fast, and it would take hours to critique them all. Instead, I'll just pick a few, which illustrate Oz's lack of concern for accuracy, and his apparent ignorance of the underlying science about dental fillings.

Dr. Oz opens his show with a dramatic claim about mercury:

"This thermometer contains mercury," he says, holding up a very small thermometer. "If I were to drop it, we would have to evacuate this entire studio immediately!"

Now, this is complete nonsense. If you drop a mercury thermometer, you should carefully clean up the mercury, which beads up into nice little silver-colored balls. No one in the room is in danger, unless perhaps they try to drink it.*

This opening salvo should set off anyone's skeptical alarm bells. Here's a guy who doesn't seem to mind exaggerating to make a point. Why trust anything he says in the rest of the show? I suspect, though, that after watching this episode, thousands of Oz's loyal viewers raced to the phone and made appointments to have the silver fillings in their teeth removed.

Dr. Oz continues his introduction by explaining that mercury is contained in silver tooth fillings. No one knew, he claims, that mercury vapor could be released from these fillings, but this news:

"sparked a firestorm 30 years ago [here the show cuts to a graphic of a fireball exploding] when major news reports brought to light the potential TOXICITY of mercury fillings. ... Now there's mounting new evidence showing mercury is released when you eat, and even when you brush your teeth."

Quick, run to the dentist! Get this toxic mess out of my mouth!

But hang on a minute. Why aren't people dropping like flies from the fillings in their teeth? With little effort, I determined that, contrary to Dr. Oz's statements, nothing new has been discovered lately about silver tooth fillings. I found studies going back to the 1970s that shown that we've long known for decades that mercury is released from these fillings. But Oz ignores all these. He even announces, a few minutes into the show, that

"for the first time ever, I'm going to show you what happens when you brush your teeth with mercury fillings."

No, this is not the "first time ever." As a scientist, I find it worrisome that Oz seems quite comfortable claiming, incorrectly, that he's the first person ever to tell the world about this.

Perhaps the most outrageous - and unintentionally funny - segment of the show is the "demonstration," where Oz introduces an Oz-certified expert on mercury vapor, David Wentz, who has a gizmo that looks like it was built by a sideshow huckster. The device is a plexiglass box that looks like it was meant to handle biohazards, with black rubber gloves that let you manipulate its contents. In the box: a set of fake teeth containing... silver fillings! And a toothbrush!

As he walks over to the device, Oz says "I work with Dave Wentz and his Ph.D. dad." This goes by really fast, so you would be excused for not realizing that Dave Wentz himself doesn't have a Ph.D., and for not knowing whether he has any credentials at all. Dr. Oz conveniently omits the fact that Wentz and his father run a highly profitable nutritional supplements company, USANA http://www.usana.com/dotCom/about/index, which happens also to donate money to Oz's nonprofit corporation, HealthCorps. Hmm.

Dr. Oz then reaches into the box, and while the audience watches in hushed excitement, he brushes the teeth, right on top of those silver fillings! Right on cue, Wentz proclaims that the mercury vapor reading hits 61 in just a few seconds.

"Anything over zero is toxic," Wentz proclaims. "And we're at 61."
"Oh my goodness, 61!" Dr. Oz exclaims.
"That mercury is coming off the fillings, into your mouth, going across the blood-brain barrier, into your brain," says Wentz dramatically.

Wow. I've been brushing my teeth (which have several fillings) for years. How can I not be dead?

As Dr. Oz should know, "the dose makes the poison." Even water can kill you if you drink too much of it. Wentz is clearly wrong to say that "anything over zero is toxic."

How much mercury is safe, then?

According to the EPA, 0.1 micrograms of mercury per kilogram of body weight per day is safe. For an adult who weighs around 150 pounds, that's about 7 micrograms. A 6-ounce can of tuna has about 20 micrograms of mercury, about 3 times the safe amount per day. Scientists do have real concerns that mercury in tuna and other fatty fish might present a health hazard.

Dr. Oz's device seemed to show that 61 micrograms of mercury were released from brushing teeth, which would be about 9 times the exposure that is considered safe. Is there really a risk here?

Well, no. The EPA has found that "nearly all methylmercury exposures in the U.S. occur through eating fish and shellfish." (Admittedly, though, this is not mercury vapor.) The precise question that Oz claims to be explaining "for the first time" has been examined in multiple studies, and the evidence is that silver fillings are harmless. (See the FDA summary here.)

A thorough scientific review in 2004 concluded that:

"The current data are insufficient to support an association between mercury release from dental amalgam and the various complaints that have been attributed to this restoration material. ... Individuals with dental amalgam-attributed complaints had neither elevated HgU nor increased prevalence of hypersensitivity to dental amalgam or mercury when compared with controls. The findings of these studies suggested that individuals with complaints self-attributed to dental amalgam should be screened for underlying dental, physical, and psychiatric conditions."

So no, there's no evidence that mercury from silver fillings causes any health problems. None.

But what about that device on Dr. Oz's show, which showed 61 micrograms being released in just a few seconds of brushing the teeth? My conclusion is that the device in Dr. Oz's studio was either wildly inaccurate or simply fraudulent. The setup was almost a parody of what real scientific instruments look like, and nothing about it gave me any confidence that it was reliable. I would suggest to Oz that before making a claim like this, he should ask rigorously trained scientists to make the measurements using properly calibrated equipment. A TV studio is no substitute for a real lab.

But wait: Mehmet Oz is a Professor of Surgery at Columbia University - he must know his science! Plus he has an M.D. from the University of Pennsylvania, and he did his undergrad studies at Harvard. By all appearances, he is a very smart guy. If his show were about heart surgery - his specialty - it would no doubt be professional, accurate, and probably far too technical to attract an audience.

Here's the rub: despite his credentials, Oz is not an expert on mercury amalgam fillings. He probably could have read and understood the science, but he appears to be unaware, or too busy to be bothered by, the many scientific studies on this subject. Had he done his homework, he might not have presented such a spectacularly overblown episode that seems intended to scare people into removing the silver fillings from their teeth.

So there's no need to go out and get your silver fillings replaced. It's too bad that a highly educated surgeon like Mehmet Oz, with such a big audience, prefers to present wild exaggerations rather than telling people the truth. Perhaps, though, the truth just isn't that exciting.

*Note added on followup: Even swallowing is rarely harmful. From J. Dodes: "Acute toxic exposures to elemental mercury are rare but there have been cases of elemental mercury being accidentally released directly into the bloodstream from broken rectal thermometers and when elemental mercury had been swallowed intentionally in an attempt at suicide. In all these cases there was no long-term effects from the mercury." Dodes, JE. The Amalgam Controversy:an evidence-based analysis. JADA, 132:348-56, 2001.

A breakthrough cure for acute leukemia?

noreply@blogger.com (Steven Salzberg) — Mon, 25 Mar 2013 11:30:00 +0000

This week a group of scientists from Memorial Sloan-Kettering Cancer Center published what may be a genuine breakthrough in the search for a cure for cancer. The simple word "cancer" disguises what is really hundreds of diseases, most caused by genetic mutations that make a cell start replicating out of control. The new study looks at a deadly form of leukemia, called B cell acute lymphoblastic leukemia, or B-ALL, and describes a radically new type of cancer therapy that uses genetic modification of a patient's own cells.

First a bit of background. Leukemias are cancers of the blood, which means they don't form solid tumors at all. Instead, the cancer cells circulate in the blood, going virtually everywhere in the body. The blood has many cell types within it, including white blood cells or leukocytes, which is the origin of the word leukemia. Lymphocytes are a type of white blood cell, and the two most common subtypes are called B cells and T cells. B-ALL, then, is a cancer where a B lymphocyte has suddenly turned cancerous.

Scientists have developed chemotherapies to treat B-ALL, but if the first line of treatments fail and the cancer returns, the patient faces a very grim prognosis. We really don't have any effective treatments at this point, and most patients die.

The new leukemia therapy is a technological tour de force. The scientific team at Memorial Sloan-Kettering, led by Renier Brentjens and Michel Sadelain, genetically modified T cells from each patient so that these T-cells would target cancerous B cells. The modified T cells use something called a "chimeric antigen receptor," or CAR, which they designed so that it would attach itself to a specific protein, called CD19, that sticks out of the surface of most cancerous B cells. (This technique was invented by another group at Memorial Sloan-Kettering, led by Isabelle Rivière.)

What was amazing about this study is that in all five patients, their cancers virtually disappeared in just a few weeks. As described in a The New York Times report, one of the sickest patients, 58-year-old David Aponte, saw his leukemia disappear in just eight days. But we cannot know for certain yet if the therapy alone is a cure. This is because the patients also had stem cell transplants within a few months after therapy, which may have helped eliminate any remaining cancer cells. The therapy itself was temporarily very toxic, requiring close monitoring and steroid treatments to lessen the toxic side effects. This may have been the reason that one patient died: the steroids may have hampered the therapy by destroying the genetically modified cells.

If this therapy were used as a first-line treatment of B-ALL, rather than in patients who have tried conventional therapy and relapsed, it might be even more effective (as the authors themselves suggest). In particular, it is likely to be less toxic in patients who are at earlier stages of the disease and have fewer tumor cells in their blood. Thus despite its promise, CAR T-cell therapy needs to be refined and tested further before we can declare it a success.

I'd like to make a final observation: this work, like almost all biomedical research in the U.S., was supported by the NIH, whose budget was just cut severely by Congress with its ill-conceived "sequester." If we keep cutting biomedical research, we won't see many more breakthroughs like this one. Even this dramatic result, promising though it is, needs more research to improve it and to test it on other leukemias, including chronic lymphycytic leukemia and non-Hodkins lymphoma, where it has already shown very promising results.

This leukemia treatment didn't just appear out of thin air. It uses a technology that was invented four years ago, and that technology in turn is based on other discoveries that now make it possible to re-engineer a patient's own cells and turn them into a treatment. Who knows where the next ten years will take us? Now is the time to be increasing our investment in biomedical research.

Maryland legislature scores one for science

noreply@blogger.com (Steven Salzberg) — Wed, 20 Mar 2013 12:00:00 +0000

Just one month ago, I wrote a post entitled "Naturopathic shenanigans in the Maryland State legislature," about the efforts of naturopaths to get a new law passed in the state of Maryland that would license them to practice medicine. This effort to get a set of pseudoscientific practices certified as "medicine" has been pursued by naturopaths across the U.S., and Maryland is just one of their latest targets. I was dismayed when I learned that laws had been introduced in both houses of the Maryland legislature to give naturopaths what they wanted.

Well, the votes just came in, and the law was unanimously defeated in committee in both the House and Senate. Without knowing precisely what happened (or if any of them read my article, either here or on the Forbes magazine site) I cannot explain why the legislators voted as they did, but after my previous article I want to give them a rousing cheer of approval. Hurrah! Sometimes lawmakers get it right, and when they do, they deserve our applause.

Everything in this journal is wrong

noreply@blogger.com (Steven Salzberg) — Fri, 15 Mar 2013 11:30:00 +0000

Moxibustion at work.

In real science, we agonize over every detail. When we publish a paper, we strive to get everything just right. We qualify our findings, always allowing for the possibility that we might have missed something.

Oh, to be freed of the constraints of reality. But fiction, alas, doesn't work in the real world. Fantasy medicine is, well, a fantasy. Or is it? Let's enter the world of Complementary and Alternative Medicine.

Imagine a scientific journal in which every single article was wrong. Not just an occasional mistake, as happens with many journals. No, I'm talking about a publication where every single article has at least one fundamental flaw.

No, it's a real journal, published by BMJ, the publishers of the well-known journal by the same name (the British Medical Journal). "Helping doctors make better decisions since 1840", they proclaim. Then why, among their 40+ journals, do they publish Acupuncture in Medicine?

It appears - I can't prove this, but it seems to be so - that every single article in this journal is wrong. Not just a little bit wrong, either. Let's look at the "Editor's choice" article from the latest issue, which must be one of their best. It's called "Using moxibustion in primary healthcare to correct non-vertex presentation: a multicentre randomised controlled trial".

In this study, a group of Spanish doctors looked at the use of moxibustion to correct a common problem in pregnancy known as a breech position - that's a baby that is turned the wrong way round in the mother, head up instead of down. What, you may ask, is moxibustion? Well, let me use the authors' explanation:

"The application of heat from the combustion of Artemisia vulgaris (moxibustion) for therapeutic purposes has long been used in China. Among other effects, it is believed to contribute to correcting the non-vertex presentation of the fetus when applied at a specific acupuncture point (BL67 Zhiyin) located at the outer corner of the little toenail."

That's right: you burn an herb (Artemisia) next to the little toenail of the pregnant mother, right next to an acupuncture point, and that's supposed to make baby flip right around so its head comes out first.

You can't make this stuff up.

These guys are serious. They ran a study where they divided pregnant women into 3 groups, with about 135 women in each. One group got moxibustion, another got "fake" moxibustion, where they burned the herb next to a different toe (really!), and the last group got standard care.

Amazingly, the doctors found that it works! More of the women with moxibustion had babies born the right way round, head down, than in either of the other two groups. To be precise, 79 babies in the moxibustion group came out the right way, versus 60 and 59 in the other two. By the authors' own analysis, this difference was statistically significant.

Wow. Maybe this stuff really does work. And moxibustion is cheap and easy to administer. Maybe this is the solution to our rising health care costs.

How to explain this result? I see several possibilities:

The small effect was just a random variation, not due to the treatment. Previous studies of exactly the same treatment (such as this one) showed that moxibustion did not work. So either those studies are wrong, or this one is.
There was bias in how the women were assigned to treatment, and the effect can be explained by that.
The authors manipulated the data to make the numbers come out better. (Quelle surprise! Not in a BMJ journal!) Of course we can't prove this without much more investigation.
Burning an herb next to the little toe at just the right place - and nowhere else - stimulates a mystical "qi" pathway, and zaps that little baby back around the way he's supposed to be.

Hmmm, which seems the most likely?

OK, I admit it: I haven't read every single article in BMJ's acupuncture journal. So I don't really know that they are all wrong. But who has time to read all this bad science? The latest issue has a disturbing number of articles about acupuncture for cancer, which I find particularly upsetting because that practice takes advantage of highly vulnerable patients. It also includes an article on ear acupuncture, a practice invented out of whole cloth by an Army doctor in the U.S., who has been inflicting it on injured service members, as I've written about before.

Actually there is one article that seems plausible. It reports a case of arterial hemorrhage caused by an acupuncture needle. But we don't need to dwell on that.

Acupuncture in Medicine has all the trappings of a real journal, including an editorial board whose members work at respectable medical schools. I know that BMJ wants us to believe it; after all, they make money on this stuff. As for the journal itself: I can't bear to read any more. It is just too painful. Perhaps acupuncture would help.

Whatever happened to swine flu?

noreply@blogger.com (Steven Salzberg) — Sat, 02 Mar 2013 20:29:00 +0000

What happened to the flu pandemic? In 2009, a new flu strain swept across the world. The new strain, called H1N1, emerged from pigs and jumped over to humans sometime in late 2008, and then swept through the human population starting in the spring of 2009. Panic ensued. Egypt responded by slaughtering all of its pigs, about 300,000.

Was the panic justified? If so, where are all the victims?

I first wrote about this soon after the outbreak began, and we now know that hundreds of millions of people were infected, somewhere in the range 11% to 21% of the population. That's an awful lot of sick people. However, H1N1 turned out to be a very mild flu: many people experienced little more than a few days of sniffles, much like a common cold. This surprising mildness of swine flu led to great confusion. Conspiracy theorists claimed that the threat had been overblown, hyped by vaccine manufacturers and their government co-conspirators. A wacky German lawmaker, Wolfgang Wodarg, even claimed that the swine flu vaccine caused cancer, a claim that was picked up and amplified by famed internet snake oil salesman, Joseph Mercola.

The swine flu now seems routine, just another human flu circulating among the population. As I wrote back in 2010, the seasonal flu vaccine now includes the H1N1 pandemic strain, so if you get your flu shot, you're protected. But as this figure from the CDC shows, the current season has been dominated by H3N2.

See the little tiny brown bits at the top of each bar? Those are swine flu cases. The swine flu has nearly vanished.

This is a big surprise, because in all three of the previous pandemics: 1918 ("Spanish" flu), 1957, and 1968, the new pandemic strain completely replaced the older strain. That hasn't happened this time, and it looks like the old strain, H3N2, is winning. That's rather unfortunate, because H3N2 is a much nastier flu than the swine flu. And this year we had a big spike in deaths due to flu, all because of H3N2.

So no, the panic back in 2009 wasn't justified, but the warnings beforehand, about the possibilities of a pandemic, were legitimate. All we knew in early 2009 was that a new pandemic strain had jumped from pigs to humans, and we didn't know for several months how bad (or mild) it would be. The human species got lucky this time.

Can anyone say when the next pandemic will arrive? Well, no. Look at the past century: 4 pandemics, separated by 39 years, 11 years, and 41 years. From that record it seems we should be safe for a while. But until 2009, the pandemics had always pushed out the previous flu. We're still living with the 1968 flu strain, and no one knows when a new flu will truly replace it.

Meanwhile, get your flu shot, because the flu mutates so fast that we need a new vaccine every year to keep ahead of it. Work continues to try to develop a permanent flu vaccine - one that we will only have to take once in a lifetime. If you like that idea, then keep supporting NIH, which is the biggest source of funding for flu research.

Oh right: we just cut NIH across the board because Congress couldn't get its act together. I guess we may have to wait a bit longer for a better flu vaccine.

Guest post at Simply Statistics

noreply@blogger.com (Steven Salzberg) — Wed, 27 Feb 2013 16:52:00 +0000

This week I was invited to do a guest post at Simply Statistics, the popular blog site run by three of my colleagues in Biostatistics. I wrote about the crisis in R01 funding, the most important source of funding for most biomedical scientists in the U.S. See the post here.

Naturopathic shenanigans in the Maryland state legislature

noreply@blogger.com (Steven Salzberg) — Tue, 19 Feb 2013 01:07:00 +0000

Quacks never give up. In their never-ending quest to make money from bogus treatments, they try all kinds of strategies to convince people that what they're selling really, really works, despite the evidence to the contrary.

One strategy is creating a legal licensing system. If the government licenses your profession, it must be legitimate, right? Legislators wouldn't approve a licensing system for nonsense, would they? Of course not!

So it's strange that the Maryland legislature is considering a bill in its upcoming session to allow naturopaths to practice medicine in the state of Maryland.

Some of you might be wondering, what the heck is a naturopath? As Peter Lipson explained recently in his Forbes column, naturopaths are little more than fake doctors, whose practices are a modern-day version of folk medicine. When naturopaths got licensed in Minnesota, PZ Myers suggested they be called "witch doctors." Too harsh? Well, one thing is clear: naturopaths are trying to get licensed in multiple states (Lipson described their efforts in Michigan) as a route towards legitimacy.

There's an easy way to become legitimate: practice science-based medicine. This would be awfully difficult for naturopaths, whose practices include homeopathy, colloidal silver treatments, and chelation therapy, to name but a few.

When the naturopaths tried this in Massachusetts 10 years ago, my colleague Kimball Atwood put together detailed testimony describing many of the unscientific and downright dangerous practices of naturopaths. I encourage anyone to read his full testimony or his series of blog articles. Here, though, is a brief sample of the erroneous claims made by naturopaths, courtesy of Dr. Atwood:

"... that hydrogen peroxide dissolved in a bath can provide vital oxygen through the skin of a patient suffering from an acute asthma attack [5];

that balloons inflated inside the nose can cure learning disorders [8];

that strokes in progress can be reversed by cold compresses applied over the carotid arteries [9];

that vitamin C is an effective treatment for approximately 100 conditions, including glaucoma, male infertility, and AIDS [12];

that high blood pressure and coronary heart disease should be treated with unproven herbs and chelation therapy [17]."

The numbers refer to citations that Dr. Atwood provides for each of his points.

Among other things, the proposed new law (House bill 1029 and its companion Senate bill 783) specifically authorizes hydrotherapy, stating:

"A license authorizes a licensee to ... administer or perform hot or cold hydrotherapy, naturopathic physical therapy, electromagnetic energy, colon hydrotherapy ... for the purpose of providing basic therapeutic care."

[Aside: I have no idea what it means to "administer electromagnetic energy"; perhaps you simply shine a light on the patient? I suspect the legislators who are sponsoring this bill haven't a clue either.]

Hydrotherapy doesn't sound so bad until you learn what naturopaths do with it. According to the naturopathic organization's own experts,

"One technique is to lower your body temperature, with a cold bath for example, as much as possible without inducing shivering as soon as possible after a stroke has occurred, or is suspected to have occured.... Another hydrotherapy technique with a similar rationale is to soak the feet in a hot foot bath, as soon as possible after the stroke has occurred, while applying a cold compress to the neck, face and scalp. If this technique can be applied as a stroke is happening, it may even abort the stroke."

Again, quoting Dr. Atwood: "All strokes are potentially life-threatening, and are considered to be medical emergencies that require prompt and expert evaluation and supportive care. The treatments described above will do nothing to improve the outcomes of strokes, but are certain to delay competent diagnosis and treatment.

Most disturbing, perhaps, is that the new Maryland bill would require physicians to violate medical ethics. The AMA code of ethics states that

"It is unethical to engage in or to aid and abet in treatment which has no scientific basis and is dangerous, is calculated to deceive the patient by giving false hope, or which may cause the patient to delay in seeking proper care."

By adding a naturopath to the Maryland State Board of Physicians, and by requiring them to license naturopaths to practice medicine, the legislature is forcing physicians to act unethically.

So if you live in Maryland, take a few minutes and write to your state representative telling him or her not to support this quack bill. Heck, contact them even if you don't live in Maryland, and tell them you were thinking of moving but now you want to move to Virginia instead.

Bad medicine infiltrates M.D. Anderson Cancer Center

noreply@blogger.com (Steven Salzberg) — Mon, 11 Feb 2013 13:00:00 +0000

M.D. Anderson Cancer Center in Texas is usually considered one of the country's top cancer centers, but that hasn't stopped it from promoting bad science. In Friday's Huffington Post, Dr. Lorenzo Cohen, Director of MD Anderson's Integrative Medicine program, writes that it is "time for acupuncture to become part of standard care" for cancer. He claims that acupuncture is "an appropriate treatment alongside conventional care for chemotherapy-induced nausea/vomiting."

As evidence, Dr. Cohen cites a newly published review article. There are many problems with Cohen's arguments. Let's start with what he fails to tell us.

First, he states that he is reporting on the results of "a recent systematic review conducted by researchers in the Integrative Medicine Program at the MD Anderson Cancer center." He conveniently neglects to say that he is the senior author of that review! He should have made it clear that he's writing about his own report. Unless his readers look up the original article, they may not realize that he is is merely promoting his own work, in a highly biased way. He also fails to point out that his article doesn't provide any new evidence itself; it only reviews other, earlier studies.

Second, Cohen tells us that his group found 41 studies evaluating the use of acupuncture for treating the symptoms of cancer therapy. (To be precise, he writes that "41 studies were found," still disguising the fact that he's the one who found them.) He neglects to mention that out of 41 studies, all but one were highly biased, by his own review's judgment (and therefore scientifically worthless). Rather than concluding that "it's time for acupuncture to become part of standard care," Cohen should be lamenting the fact that nearly all studies of acupuncture are badly done.

Third, Cohen does mention that his review article considered 8 symptoms of cancer treatment: pain, nausea, hot flashes, fatigue, dry mouth, constipation, anxiety, and sleep disturbance, but he doesn't explain that the only study out of 41 that wasn't excessively biased (according to his own criteria) looked at nausea. Thus Cohen should have told us that acupuncture is not effective for any of these other conditions. At best, if he insists on putting a positive spin on it, he should have explained that the evidence is insufficient to recommend acupuncture for any of these symptoms.

Let's look at that one positive study, published in 2000 by Joannie Shen and colleagues. It's a small study, with about 33 patients in each of 3 groups, where the treatment group got electroacupuncture, which means an electric current is run through the needles. This isn't the same as traditional acupuncture, and the study didn't compare identical groups with and without the electrical stimulation. So we can't know whether the electrical current was the real reason the treatment showed a benefit. The study also failed (and this is a huge problem) to "blind" either the patients or those providing treatment: obviously the patients knew they were getting electroacupuncture. Despite this, Cohen claimed in his review article that the 12-year-old study had a low risk of bias for blinding.

The patients that received electrical stimulation plus acupuncture had fewer episodes of vomiting. This suggests that something in the treatment - maybe the acupuncture, maybe the electricity - somehow reduced this particular symptom. Or maybe not: the study had a possibly serious flaw in the assignment of patients to groups: in the electroacupuncture group, only 51% had vomited during previous chemotherapy sessions, significantly fewer than in the other two groups.

Despite the methodological flaws, if acupuncture works, surely that 12-year-old study would be replicated by now, yes? Well, no. Cohen neglects to mention a much more recent study on acupuncture for nausea, published just last year, which his own reviewed graded as unbiased for 5 out of 6 criteria, including blinding. That study was negative: acupuncture was no better than sham acupuncture. When a small, problematic study fails to replicate, good scientists conclude that the treatment simply doesn't work. Cohen, though, ignores this larger (twice as many patients), better-done study in his HuffPo piece.

So based on one mediocre study from 12 years ago, involving only a small number of patients, for only one condition, Cohen is calling for acupuncture to become standard treatment for all cancer patients. Could this be because he is currently running his own clinical trial on acupuncture for the treatment of cancer patients? Could he be biased by the $777,886 he is currently receiving from NIH to study acupuncture?

Given that Cohen is its Director of Integrative Medicine, it's not surprising that MD Anderson has been using acupuncture on its patients since 2003: they even list a fee schedule, $80 on the first visit and $65 for each follow-up, and they recommend at least 8-10 treatments. MD Anderson's website offers up this gem of an explanation:

"A block in the meridians can deny the muscles and surrounding tissues of Qi, creating an imbalance of health. However, the flow of Qi can be restored by inserting needles at specific acupuncture points."

This pseudoscientific babble does not belong in one the nation's best cancer centers. What's worse is that MD Anderson is offering ineffective treatments to cancer patients - a highly vulnerable population - accompanied by claims that they should know are false. This is inexcusable.

MD Anderson's many outstanding scientists surely know that acupuncture is wildly implausible, and many of them (although not Dr. Cohen) must know that it has repeatedly failed to stand up to scientific scrutiny. US News ranks MD Anderson as the country's top cancer hospital, followed by Memorial Sloan-Kettering and Johns Hopkins Hospital. After reading Dr. Cohen's article, and looking at MD Anderson's promotion of unproven pseudoscientific treatments, I would argue that MD Anderson should be dropped many, many notches down in those rankings.

IOM to Public: Childhood Vaccine Schedule is Safe

noreply@blogger.com (Steven Salzberg) — Mon, 28 Jan 2013 12:30:00 +0000

Hey parents: if you've been taken in by anti-vaccine discussions on the internet, you might want to look at the newest report from the Institute of Medicine. After a lengthy and thorough review of the evidence, the IOM issued a report last week that found that the current childhood immunization schedule in the United States is safe.

The IOM committee specifically looked for evidence that vaccination is linked to "autoimmune diseases, asthma, hypersensitivity, seizures, child developmental disorders, learning or developmental disorders, or attention deficit or disruptive disorders", including autism. Their finding: no evidence suggests a link to any of these conditions.

The motivation for the report is the growing incidence of parents who worry that there are "too many, too soon" - a catchphrase that was the basis of an anti-vaccine campaign led by Generation Rescue and its spokesmodel, Jenny McCarthy. This concern, which sounds reasonable on its face, never had any evidence to support it.

Anti-vaccine activists have pointed out, correctly, that the number of vaccines has increased significantly over the past several decades. The current schedule has as many as 24 immunizations in a child's first two years, and up to five injections in a single visit. The reason for this is simple: the scientific community has developed vaccines against a growing number of childhood illnesses. As a result, many diseases that used to infect millions of children each year, killing or permanently injuring thousands of infants and toddlers, have almost disappeared from modern societies. This is a good thing.

Many parents have been convinced to "slow down" vaccines after hearing advice from self-proclaimed vaccination authorities, such as "Dr. Bob" Sears. Sears has published his own alternative vaccine schedule (which he apparently just made up - he certainly didn't do a scientific study) and whose has gotten rich selling his book and offering other advice. Journalist Seth Mnookin calls Sears "a first-rate huckster."

Noted vaccine expert Paul Offit, in a peer-reviewed article in the journal Pediatrics four years ago, explained how Sears ignores all the science on vaccine safety, sometimes simply replacing objective evidence with his own "facts." Offit also called out Sears for his advising parents not to vaccinate their kids, but then not to tell their neighbors:

“I also warn [parents] not to share their fears with their neighbors, because if too many people avoid the MMR, we'll likely see the diseases increase significantly.” [wrote "Dr. Bob" Sears]

In this astonishingly selfish comment, Sears admits that herd immunity works, but then says don't tell your neighbors, because then their kids might get sick and infect your unvaccinated kids.

Offit's article is a thorough, point-by-point rebuttal of Sears' numerous claims, many of them either misleading or downright false. I highly recommend it. Or read the IOM's report online, for free. Don't waste your money on Dr. Bob's book.

Let's hope all parents will follow the recommended vaccine schedule and ignore the voices of fear and unreason who are trying to scare them. If you're still in doubt, read the heartbreaking story, from just a few days ago, of 7-year-old Alijah Williams in New Zealand. Alijah's well-educated parents thought they were doing the right thing by withholding vaccines, after reading some scary material on the internet. Alijah was infected with tetanus last year and fought it for months, nearly dying in the process. His recovery will take 12 months, during which he will have to re-learn how to eat and walk on his own. His parents have now become activists trying to spread the word among their community that infections are the real threat - not vaccines.

Congress is killing medical research

noreply@blogger.com (Steven Salzberg) — Mon, 14 Jan 2013 12:30:00 +0000

Congress is killing medical research. The tragedy is that they don't want to, but they may do it anyway.

While the ridiculous posturing about the U.S. budget deficit drags on, seemingly without end, biomedical research in the U.S. is crumbling. Congress's chronic inability to pass a budget, and especially the delays this year, are deeply damaging the core of our entire biomedical research enterprise: the National Institutes of Health.

Outside the beltway, the current battle over the budget probably looks like the usual blustering drama that Congress has been engaged in for years. Somehow they always come up with another budget, don't they? They'll tout it as a compromise where no one is very happy, and we move on to the next fight. Business as usual, right?

Wrong. There are very real consequences to Congress's inaction, and they are happening right now. The "continuing resolution" that Congress passed in the fall, which allowed the government to avoid a shutdown, only runs until March. It includes a 10% across-the-board budget cut to everything. That includes most of the critical medical research in the U.S.

Every year, many NIH projects end and many others begin. (Most only last 3 or 4 years.) But not this year. Because of the budget shenanigans, NIH has been forced to cut or delay funding to almost all new projects. In other words, biomedical research that has already gone through rigorous peer review and been given top priority is on hold. And just to be clear: these are only the best projects. 80-85% of projects submitted to NIH, many of them excellent, don't make the cut because NIH just doesn't have enough funding for them.

While the budget is in limbo, many talented students, postdoctoral fellows, and research scientists who might work on these projects - some of them just beginning their careers in science - will have to find other work. Some will go to industry, and some may leave science for another field. Some of them won't come back. This is a loss that is hard to measure.

For readers who might think I'm asking for a lot, think again. The entire NIH budget comes to about $31 billion, which supports research on hundreds of diseases. The total U.S. budget last year was 3,729 billion (3.7 trillion), so the NIH budget is less than 1% of the total. A 10% cut from the NIH budget (the so-called "sequester" plan) would save 0.08% of the federal budget. This matters not a whit in the overall budget debate - but it would be a huge blow to biomedical research, crippling some research programs for years to come.

And for those who want to look at this from an economic perspective , NIH funding is a terrific investment. A nonpartisan study in 2000 concluded:

"Publicly funded research in general generates high rates of return to the economy, averaging 25 to 40 percent a year."

The same report provided detailed examples showing about how NIH-funded work saves billions of dollars per year in health care costs. But keep in mind that most of these benefits don't appear for many years. The private sector simply won't make such long-term investments.

If you are reading this, you either already benefit from medical research, or you will some day. Even if you are in perfect health, someone close to you probably uses a treatment that was supported by NIH. Virtually every major medical center in the United States depends on this funding. There are few investments with broader impact, and broader public support, than biomedical research.

Does Congress really want to kill medical research? I think the answer is very clearly no. The damage to our biomedical research enterprise is entirely unintentional: it's collateral damage in the never-ending partisan fights that consume Washington these days. Those fights are about power and politics, not science and medicine. Everyone, even the most intransigent Congressperson, wants better treatments for cancer, heart disease, genetic diseases, infections, and the many other illnesses that afflict us.

So I'm asking the leaders of Congress (yes, I'm talking to you, Congressman John Boehner and Senator Harry Reid) to put aside the fighting for a few minutes. Bring up the NIH budget and pass it. Don't cut it by 10% (the "sequester" plan), which would be devastating to biomedical research and would save only 0.08% of the budget. Don't bundle it into some omnibus "grand bargain" that everyone knows is neither grand nor a bargain.

If they will simply vote on it, I predict that both houses of Congress will pass the NIH budget with overwhelming majorities, and for a brief moment, the country might even admit that Congress was doing its job. I'll pledge right here to write a blog post titled "Congress delivers a victory to the American people." So go ahead and do it. I dare you.

[Disclosure: Like most biomedical scientists in the U.S., I receive funding for my research from NIH. And also like most biomedical scientists, all of my lab's discoveries are freely shared with the public.]

Questionable for-profit cancer center profits from alternative therapies

noreply@blogger.com (Steven Salzberg) — Mon, 31 Dec 2012 13:00:00 +0000

It sounds like a crazy conspiracy theory: a secretive businessman founds a for-profit medical center to treat cancer. His hospitals offer conventional treatments but also sell highly questionable, unscientific treatments to vulnerable patients. These treatments help to increase profits. The businessman uses the profits from his cancer hospitals to support his favorite right-wing causes. Patients have no idea that the fees they pay for treatment help support these causes.

It may sound unbelievable, but it's true. Most of this story was described in a lengthy exposé just published in the Washington Post on Christmas day. The Post revealed that Richard Stephenson, the founder of a large for-profit cancer center, is also one of the primary funding sources for Freedom Works, a right-wing Tea Party organization that played a major role in the 2012 elections. As the Post story described him:

[Stephenson is] "a reclusive Illinois millionaire who has exerted increasing control over one of Washington’s most influential conservative grass-roots organizations."

Among other examples, the Post describes how

"more than $12 million in donations was funneled through two Tennessee corporations to the FreedomWorks super PAC after negotiations with Stephenson over a preelection gift of the same size.... The origin of the money has not previously been reported."

What the Post story didn't explain was the source of Stephenson's millions: Cancer Treatment Centers of America (CTCA), a private, for-profit company with five cancer hospitals scattered around the U.S. Stephenson is the founder and chairman of CTCA.

For-profit hospitals present a big ethical problem, even when they provide proper care. The problem is that motivation to increase profits may work against the interest of patients. I don't want to debate that here, because CTCA has another, more serious problem. Alongside standard, science-based cancer therapies, CTCA also offers an array of questionable, unscientific therapies, which it proudly labels as part of its "integrative cancer treatment." CTCA advertises many such treatments, including:

Acupuncture
Acupressure
Chiropractic
Naturopathy
Homeopathy
Mind-Body medicine (including Reiki and Qi Gong)

None of the treatments in this list has any scientific support showing that they provide a benefit to cancer patients. Some of them carry a real risk of harm, as I've written about previously. Acupuncture carries a risk of infection and chiropractic treatment has a risk of stroke - very small risks, admittedly, but no risk is acceptable when the benefit is nonexistent. (See Science-Based Medicine for a summary of the science behind these and other alternative therapies.)

CTCA makes multiple unsupported, unscientific claims for its alternative treatments, such as:

"Naturopathic medicine can help reduce these [cancer-related] symptoms, strengthen the immune system and support the healing process throughout your brain cancer treatment."
"Acupuncture may help to alleviate [cancer] treatment-related side effects, such as nausea and vomiting."
"When used during your leukemia treatment, our chiropractic care services can help correct bone, muscle and joint problems and restore nerve function."

These are just a few examples. These claims, and CTCA's marketing of the therapies involved, present a huge ethical problem. Cancer patients are facing some of the most difficult decisions in their lives, often while suffering through painful treatments, not to mention the fear that their cancer will kill them. When a cancer hospital offers an "integrative" treatment with the promise that it may help, the patient is highly likely to try it, regardless of the cost. These are extremely vulnerable patients, and CTCA is taking advantage of them to sell ineffective therapies. CTCA and its owners, including Richard Stephenson, are profiting from their unsuspecting patients.

Offering treatments that are little more than snake oil to cancer patients is ethically indefensible. Believers in acupuncture, naturopathy, Reiki, and homeopathy will argue that they are not unethical, because the treatments work. This argument, though, flies in the face of overwhelming evidence to the contrary. Those who argue that these therapies really work only demonstrate that they are unqualified to offer medical care.

Cancer Treatment Centers of America presents a very welcoming, positive picture of itself through its website, and much of what it describes is accurate. However, its errors of omission are huge: nowhere does its website say that CTCA is a for-profit center, nor does it tell you that its founder is a major donor to right-wing political organizations. And most critically for patients, CTCA offers a palette of pseudoscientific treatments, making medical claims that are not supported by any evidence and that in some cases violate basic principles of physiology and biology - although the website claims that its integrative treatments are "scientifically-based supportive therapies."

Let's put aside the right-wing propensities of its owners and simply focus on the science and the ethics of CTCA's "integrative" therapies. Even if the treatments were free, there is no justification for offering treatments based on pseudoscience. In the context of a for-profit hospital, where every treatment provided adds to the bottom line, the practice of pushing illegitimate treatments onto cancer patients is even more reprehensible.

[Note: the publisher of Forbes magazine, Steve Forbes, is a board member for Freedom Works. In case it's not obvious, I don't speak for Forbes and they don't endorse the content of my blog, which appears both here and on the Forbes site.]

[Note 2: for a more detailed, critical look at some of CTCA's offerings and its claims, see this post by Orac at Respectful Insolence from mid-2010.]

Have another cup o' joe, it's good for you

noreply@blogger.com (Steven Salzberg) — Sun, 23 Dec 2012 16:44:00 +0000

My favorite science studies are the ones that tell us that what we're already doing is good for us. This story fits the bill. In the American Journal of Epidemiology this month, Janet Hildebrand and colleagues reported on a large study looking at the effects of coffee on throat cancers.

Let's get right to the good news: drinking coffee seems to reduce your risk of death from oral or pharyngeal cancer by about 50%. Drinking more coffee is better than drinking less, and drinking caffeinated (normal) coffee is better than decaf.

I knew there was something wrong with decaf.

Now for some details. This study is part of an enormous project, the Cancer Prevention Study II, with over 1 million participants who've been followed for 30 years. The participants regularly fill out questionnaires answering a variety of questions, including how much coffee and tea they drink. After excluding people with missing information about coffee drinking and those who already had cancer in 1982, the researchers still had over 950,000 people. Coffee drinking was categorized based on daily consumption: less than a cup (or none), 1-2 cups, 3-4 cups, and more than 4 cups. They asked about decaf coffee and tea drinking as well.

A study like this is hard to do well, because there are so many confounding variables, especially smoking. Smokers have a dramatically higher risk of throat cancer, and smokers also drink a lot of coffee. Hildebrand and colleagues did a good job at separating out this effect, looking at the risk of cancer in nonsmokers separately and adjusting the statistics accordingly.

Perhaps the most encouraging finding is this: in people who have been nonsmokers for at least 20 years, 1-2 cups of coffee per day corresponds to a 32% decrease in the risk of death from throat cancer. More than 2 cups per day corresponds to a 64% decrease. And among all participants (including former smokers), more than 4 cups a day seemed to provide the greatest benefit.

Decaf coffee also seems to reduce the risk of fatal throat cancer, though not quite as much. Tea drinkers, in contrast, don't seem to get any benefit, not for this type of cancer.

All this comes with some very big caveats. First, despite the very large size of the study, the number of deaths oral or pharyngeal cancer was very small, only a few hundred. (Oral/pharyngeal cancer is very common worldwide, but less common in the U.S., where this study was conducted, with about 7850 deaths per year. This includes cancers of the tongue, mouth, and pharynx.) So the absolute risk is very small. Another big caveat is that this study only looked at cancer deaths - it did not measure the risk of getting cancer in the first place.

But skepticism aside, drinking coffee seems to reduce the risk of oral cancer. This confirms my long-held view that the three major food groups - coffee, chocolate, and red wine - are all good for you. So the next time you feel like a second cup, or a third: drink up!

Congress holds an anti-vaccine hearing

noreply@blogger.com (Steven Salzberg) — Mon, 03 Dec 2012 11:30:00 +0000

I was in my car yesterday listening to C-SPAN (yes, I do that sometimes), when to my stunned surprise I heard Congressman Dan Burton launch into a diatribe on how mercury in vaccines causes autism. No, this was not a replay of a recording from a decade ago. The hearing was held just a few days ago by the Committee on Oversight and Government Reform.

Congressman Burton used this hearing to rehash a series of some of the most thoroughly discredited anti-vaccine positions of the past decade. Burton is a firm believer in the myth that vaccines cause autism, and he arrogantly holds the position that he knows the truth better than the thousands of scientists who have spent much of the past decade doing real science that proves him wrong.

In a classic political move, the committee called on scientists Alan Guttmacher from the NIH and Colleen Boyle from the CDC to testify, but in fact the committee just wanted to bully the scientists. Committee members lectured the scientists, throwing out bad science claims, often disguised as questions, thick and fast. Alas, Guttmacher and Boyle weren't prepared for this kind of rapid-fire assault by pseudoscience.

Burton himself was the worst offender, offering anecdotes and bad science with an air of authority. He stated bluntly:

“I’m convinced that the mercury in vaccinations is a contributing factor to neurological diseases such as autism."

No, it isn't. Dozens of studies, involving hundreds of thousands of children, have found the same thing: there is no link whatsoever between thimerosal and autism, or between vaccines and autism. And Burton went off the deep end with this:

"It wasn’t so bad when a child gets one or two or three vaccines… Mercury accumulates in the brain until it has to be chelated.”

Bang bang, two false claims in 10 seconds. First he claims that mercury from vaccines "accumulates in the brain", a statement with no scientific support at all. Then he claims that chelation therapy is the solution - a radical, potentially very harmful treatment that no sensible parent would ever force on their child. Unfortunately, some quack doctors have experimented with chelation therapy on autistic children, despite that fact that it can cause deadly liver and kidney damage, and one of them caused the death of a 5-year-old boy in 2005.

Burton also claimed that single-shot vials would "eliminate the possibilty of neurological damage from vaccines" - a claim that was invented out of thin air by the discredited anti-vax doctor Andrew Wakefield, whose fraudulent 1998 study was the spark that started the current wave of anti-vax hysteria.

Congressman Bill Posey from Florida was just as bad as Burton, demanding a study of vaccinated versus unvaccinated children, a standard talking point of the anti-vax movement. (Congressman Posey: do you even realize that your question is almost identical to what Jenny McCarthy asked five years ago, on the Larry King Live show?) Here's his question to the CDC's Boyle:

"I wonder if the CDC has conducted or facilitated a study comparing vaccinated children with unvaccinated children yet - have you done that?"

Dr. Boyle wasn't prepared for this. She tried to point out that many studies have been done looking at the relation between vaccines and autism, but she didn't get very far before interrupted, thus:

Rep. Posey: “So clearly, definitely, unequivocally, you have studied vaccinated versus unvaccinated?”

Dr. Boyle: “We have not studied vaccinated versus unvaccinated."

Posey: “Never mind. Stop there. That was the meaning of my question. You wasted two minutes of my time."

Dr. Boyle simply wasn't prepared for a Congressman who was parroting anti-vax activists. It's too late now, but her response should have been this:

Congressman Posey, only an extremely unethical scientist would consider conducting such a study. To compare vaccinated versus unvaccinated children in the manner you suggest, one would have to withhold vaccines from young children. We know from decades of evidence, involving tens of millions of children, that vaccines save lives. Few if any medical interventions are more effective than vaccines.

But Congressman, the scientific community has done observational studies of vaccinated versus unvaccinated children, comparing autism rates in children whose parents chose not to vaccinate. Those studies show that autism rates were slightly higher in unvaccinated children. That's right, vaccinated children had autism at a lower rate.

So no, Congressman Posey, the CDC hasn't done a study of vaccinated versus unvaccinated children. Only a corrupt dictatorship could impose a study like that on its people. Is that what you want?

To make matters worse, the House committee invited Mark Blaxill to testify. Blaxill is a well-known anti-vaccine activist whose organization, SafeMinds, seems to revolve around the bogus claim that mercury in vaccines causes autism. His organization urges parents not to vaccinate their children, and giving him such a prominent platform only serves to spread misinformation among parents of young children.

Blaxill's central claim is that that we're in the midst of an autism epidemic:

"For a long time, reported U.S. autism rates were low, estimated at about 1 in 10,000. Then around 1990 something new and terrible happened to a generation of children. Autism rates didn’t just rise, they multiplied," claimed Blaxill in his written testimony.

His entire argument builds on this. Yet multiple studies, looking carefully and objectively at the data, indicate that all or nearly all of the rise in autism cases is due to increasing diagnoses, which in turn is due to multiple factors: a dramatically broading of the definition of autism in the early 1990s, a greater awareness of the condition, and a greater willingness of doctors and parents to accept the diagnosis. For an objective summary of the evidence, see the articles by neurologist Steven Novella here and here, which summarize a dozen epidemiological studies. The weight of the evidence shows that the actual incidence of autism is either stable or possibly rising very slowly. There is no "autism epidemic."

It's also worth pointing out that Blaxill is a conspiracy theorist who claims that the "CDC has actively covered up the evidence surrounding autism’s environmental causes."

Congress has every right to conduct oversight into medical research at the NIH and the CDC. But when Dan Burton, Bob Posey, and others decide in advance what the science says, and abuse their power to demand "answers" that validate their badly mistaken beliefs, people can be harmed. Over the past decade, the anti-vaccine movement has successfully convinced millions of parents to leave their kids unvaccinated, and the result has been serious outbreaks of whooping cough, haemophilus, measles, chicken pox, and mumps around the U.S. and Europe.

Some anti-vax parents claim that these childhood illnesses aren't so bad. I wish they would talk to the parents of young children who have died in recent whooping cough outbreaks. These illnesses can be deadly.

Message to Congress: science isn't easy, and autism is complicated. Don't criticize science when it doesn't give you the answer you thought you knew. That's not how science works. Thousands of scientists are now trying to identify the causes of autism, and they've made progress, especially on the genetic front. The answer might not be simple, but we will find it.

Maryland puts football ahead of academics - again

noreply@blogger.com (Steven Salzberg) — Sat, 24 Nov 2012 14:26:00 +0000

It's holiday season, and here in the U.S. that means one thing: football! Right? I mean, what could be more important than football?

At least that's what the president and regents of the University of Maryland seem to think. This week, they announced that after 60 years, UMD is leaving the Atlantic Coast Conference, to join the Big Ten. (Note to non-football fans: the Big Ten has 12 teams. Yes, I know.)

The president of UMD, Wallace Loh, announced the deal just after the Board of Regents approved it a few days ago, in a secret meeting. "Today is a watershed moment for the University of Maryland," he said.

Wallace Loh is an accomplished academic, but he is turning out to be a disaster for the University of Maryland. His first action, just a month after joining the University in 2010, was to announce a wasteful $2 million buyout of the football coach, who had another year left in his contract. Eager football boosters couldn't wait to replace him, so Loh went along with that deal, spending over $2 million to bring in a new coach who, I should mention, has had two lousy seasons so far. Not that it should matter.

Then, less than a year later, President Loh announced that he was eliminating 8 other sports teams to save money for football, basically doubling down on his big-time football bet. Well, there goes any pretense that he's doing this for the student-athletes.

To see how deeply confused UMD's Loh is, consider what he said in his press release announcing the move to the Big Ten:

"We wanted to join this athletic conference because we also wanted to join its associated academic consortium. The extensive opportunities ... for collaborations with our peer AAU and flagship universities in education, research, and innovation will boost the University of Maryland's ascendancy in academic excellence."

Oh really? Let's look at the evidence, shall we? The ACC has 12 schools including UMD, and has just added 3 more. Using the U.S. News rankings of national universities, we can calculate that the average ACC school is ranked 48th in the country. The average Big Ten school is ranked 58th. (UMD is tied for 58th nationally.) So although the Big Ten isn't bad, a move to the Big Ten from the ACC is clearly a move down academically.

Dr. Loh is a smart man, and I doubt he truly believes that joining the Big Ten will help Maryland academically. But he does claim it will help the athletes. He claimed that:

"We will have the capability to support better our student-athletes -- in the classroom and on the field -- and compete successfully at the highest levels."

Never mind that the Big Ten schools are, on average, much further away from Maryland than the ACC schools, which will require more travel from the athletes. But travel is educational, right?

Obviously this is all about the money. USA Today's headline got it just right: "Maryland leaves ACC for more money."

Here's a question for Dr. Loh: since Maryland will make more money in the Big Ten, will you pay your athletes higher salaries? Oh right, these are "student-athletes": they mustn't get paid! Never mind that their coaches make the highest salaries in the university.

Why does no one seem surprised that a university president, a highly educated scholar with both a Ph.D. and a law degree, is spending so much time on football? Why is a university spending any time at all running a big-time sports entertainment system? As I wrote last year:

The football-industrial complex has too much power over our universities. Nothing else can explain how we spend so much money and time on football, which contributes almost nothing to students' education, while academic departments are cutting faculty and staff. The culture of football worship has gotten so out of control that I think the only solution is to get rid of it entirely.

It's not just UMD. For instance, just last spring the University of Florida proposed to eliminate its Computer Science department to save $1.4 million, while simultaneously increasing its athletic budget by $2 million. After my article about this plan went viral, UF's president reversed that decision.

Stated simply, football has corrupted America's universities. Top administrators have completely lost sight of their academic mission, and instead seem to believe that their primary job is to provide sports entertainment for the TV-watching public. There is only one way to fix this: get rid of football.

But wait! Football fans don't have to lose their beloved teams. I have a better proposal. Each university can spin off its football program as a for-profit, separate enterprise. The team can pay license fees for the use of the university's name and pay to rent the stadium. Then it can pay its coaches whatever it wants; after all, they won't be university employees. More important, these minor-league professional teams (which is what they already are) will have to pay their athletes. We should get rid of the current system, where the athletes are basically indentured servants. (For more on this problem, see Taylor Branch's remarkable piece, "The Shame of College Sports", which sportswriter Frank DeFord called "the most important article ever written about college sports".)

Let's remind university presidents, and boards of regents, and everyone else involved in running a university that their mission is to provide education, research, and training for their students and the world. They should get out of the business of providing television entertainment. And they should most certainly put an end to the practice of profiting off the labor of unpaid student athletes while neglecting their education.

How to predict an election? Ask the math geeks.

noreply@blogger.com (Steven Salzberg) — Mon, 12 Nov 2012 12:30:00 +0000

Mark Newman's rendering of the 2012 U.S. election,
weighted by population

It's time for a bit of gloating. No, not for Democrats over Republicans, though I'm sure that's going on. It's time for the math geeks to throw a bit of scorn at those insufferable, over-confident frat boys who call themselves political prognosticators, and who spent most of the past two years telling us that they knew how the election would turn out. They bloviated endlessly on talk shows, explaining why their favored candidate would win, and how he would do it.

Politicos behave just like promoters of quack treatments when things go wrong: they always have a ready answer, and somehow their "theories" can never be proven wrong. It seems that the only thing these guys are really expert at is getting themselves onto talk shows. Now that the election is over, let's hope that happens a bit less often.

Instead, pay attention to the math geeks. The statisticians and analysts who build mathematical models based on multiple polls and other data absolutely nailed this election. Nailed it! Nate Silver at FiveThirtyEight blog predicted the winner of the presidential election in all 50 states. So did Sam Wang , a biophysics professor at Princeton, over at the Princeton Election Consortium blog. And so did Simon Jackman, a political science professor at Stanford who writes for HuffPo. Nate Silver first drew everyone's attention in the 2008 election, when he correctly predicted 49 out of 50 states. Last week's success shows that this is not an anomaly, although it has the mathematically challenged pundits in a tizzy.

Hopkins statistics professor Jeff Leek wrote a nice explanation of how these models work over at Simply Statistics, so I won't explain it here. Suffice it to say that mathematical models don't work by chattering with their buddies at political rallies.

Mathematics delivered the goods. And make no mistake, this is the way of the future.

That hasn't stopped the punditocracy yet. On election night, Republican hatchet man Karl Rove was sputtering on Fox News that Romney could still win, after Fox News itself - which is little more than a media arm of the Republican party -called Ohio and the election for Obama. Rove, who predicted that Romney would win with 285 electoral voites, also orchestrated the spending of over $127 million on Romney, not to mention his spending on 12 Senate candidates, 10 of whom lost. Has he admitted he did anything wrong? Nope.

Rove wasn't the only one wrong. As Techcrunch pointed out,

"every single major pundit was wrong - some comically wrong."

The Atlantic created a detailed score sheet listing all the pundits and their predictions of the overall winner, the electoral college total, and the winner in all the swing states. And indeed, even those who predicted correctly that Obama would win got most of the swing states wrong.

Here's what needs to happen. The television networks need to realize that political expertise is meaningless when it comes to making statistical predictions. Let's treat political forecasting just like weather forecasting, using models that are demonstrably accurate (such as Silver's). Television stations can hire attractive political "forecasters" (because physical appearance matters on TV, like it or not) who will describe the latest forecasts just like today's weather forecasters do. Now that I think of it, why not let the weather forecasters do both jobs? We already have them in place at every local TV station in the country. Think of all the money the networks will save.

But what about all that air time they need to fill with talking heads arguing about who will win elections? Well, this makes about as much sense as having two self-proclaimed experts arguing about whether it's going to snow this weekend. Maybe they can find real experts who will argue about issues rather than about who's ahead in the polls.

Ha ha, just kidding! Who wants to hear about issues? But if you must know how the race is going, ask the math geeks.

Why we want to believe chocolate makes us smarter

noreply@blogger.com (Steven Salzberg) — Mon, 05 Nov 2012 12:30:00 +0000

Eat chocolate, win Nobel Prize?

The New England Journal of Medicine published a study two weeks ago showing, amazingly, that eating chocolate might make you smarter. To be precise, the author, Franz Messerli, was wondering if chocolate consumption might be correlated with the overall cognitive function of a population. He couldn't find any data on national intelligence, so instead he used the total number of Nobel prize winners per capita. The correlation between chocolate consumption and Nobels is remarkably strong, with a p-value less than 0.0001, meaning that the odds that this is due to chance are less than 1 in 10,000.

Ha ha! Dr. Messerli was just kidding. Or was he?

The article itself reads like almost any science paper. It includes a straight-faced presentation of the data and scholarly references suggesting that the brain-enhancing effect of chocolate might be due to flavanols, which may be "effective in slowing down or even reversing the reductions in cognitive performance that occur with aging."

In fact the entire article appears to be dead serious until the end, where Messerli makes the wry comment that

"The cumulative dose of chocolate that is needed to sufficiently increase the odds of being asked to travel to Stockholm [where the Nobels are awarded] is uncertain."

And then, in his disclosure of conflicts of interest, he reports "daily chocolate consumption, mostly but not exclusively in the form of Lindt's dark varieties." Hmmm, this doesn't seem like a serious science paper after all.

Word of this article swept through the halls of academia the day after it was published. I heard it being discussed among my colleagues, who were concerned that NEJM had published yet another example of misleading statistics. It took a couple of days for us to realize that it was a joke - based on real data, but a joke nonetheless.

The media reported the story widely, and a few reporters figured out the ruse, but the parody was just too subtle for most. Reuters wasn't fooled, as reported on their own site and on Fox News. They reached Messerli by phone, who confessed that

"the whole idea is absurd, although the data are legitimate and contain a few lessons about the fallibility of science."

The Associated Press reporters were slightly suspicious, opening with "take this with a grain of salt." But they went on to report it as straight news, and their story appeared on CBS News, the Huffington Post, and elsewhere.

Larry Husten, my fellow columnist at at Forbes, reported it as straight news with the headline "Chocolate and Nobel Prizes Linked in Study." Time magazine fell for it too.

Two medical websites, Medical News Today and WebMD, not only took the story seriously, but also bought into the explanation that the effect is caused by flavanols, which are found not just in cocoa, but also in red wine and green tea. Sounds like an ideal diet to me.

Slate's Brian Palmer had an interesting angle. He reported the story as straight news, but then investigated why the Swiss eat so much chocolate. (Answer: innovation in chocolate-making, and wealth.)

Why do we want to believe chocolate makes us smarter? Well, obviously because we'd love for it to be true. And as Messerli points out, there have been some serious studies linking flavonoids to better health and cognitive function. But the notion that chocolate leads to Nobel prizes is a little too good to be true. I'm reminded of the study that I wrote about back in April that claimed chocolate would help you lose weight - which was little more than wishful thinking masquerading as science.

Still, with Halloween just past, many parents are probably wondering how much to let their kids eat. Those Nobel-champion Swiss consume about 11 kilograms per year, about 30 g (1 ounce) per day. That's 3 of those little mini-chocolate bars. And parents, maybe you should have a few too - just in case Messerli is right.

Multivitamins and cancer: a mixed bag

noreply@blogger.com (Steven Salzberg) — Mon, 22 Oct 2012 11:30:00 +0000

A major new study published this week in the Journal of the American Medical Association (JAMA) came to the surprising conclusion that

"daily multivitamin supplementation modestly but significantly reduced the risk of total cancer."

The report included some caveats, such as the fact that all 14,641 participants were healthy male physicians.

But the result is still surprising, because other recent studies, some of them even larger, have concluded that vitamin supplements do not provide any significant health benefits. On the contrary, some studies found that supplements could actually be harmful. As I wrote last year, a very large study of 38,772 older women, who were followed for 25 years, showed that the risk of death INCREASED with long-term use of multivitamins, vitamin B6, folic acid, iron, magnesium, zinc, and copper. That's death, not just cancer. The authors of that study, Jaakko Mursu and colleagues, concluded that there is

"little justification for the general and widespread use of dietary supplements."

The new study, PHS II (Physicians' Health Study II) looked at overall death rates as well as cancer, and found that men on a daily multivitamin had fewer deaths, but too few to be statistically significant.

So we have a large study in men showing that multivitamins seem to reduce overall cancer, and maybe even death, but an even larger study in women showing the opposite effect.

A second study from last year, in 35,533 men, looked at vitamin E and selenium supplements. That study, also published in JAMA, found that risk of cancer INCREASED for men taking vitamin E, selenium, or both.

The media reports aren't helping to clarify things. The NY Times proclaimed "Multivitamin use linked to lowered cancer risk, and the Wall St. Journal reported that "Multivitamin cuts cancer risk, large study finds." Bloomberg News went right for the business angle, announcing that "Pfizer multivitamin reduces cancer 8% in men, study finds."

Compared to Bloomberg news, Pfizer's own website was remarkably restrained, saying only

"Centrum Silver was part of the recently published landmark study evaluating the long-term benefits of multivitamins."

No claims about reducing the risk of cancer - surprisingly, the independent media made far stronger statements than Pfizer. Not true of supplement manufacturer GNC, which was flashing a pop-up headline that "Taking a daily multivitamin could cut cancer risk", linking to a news article at the Boston Herald.

So what do we make of this new study? Are multivitamins good for you after all?

The new JAMA study appears to be very well done. It's a double-blind, placebo-controlled study in which half of the physicians received a daily multivitamin, Centrum Silver, and half received a placebo. The participants didn't know if the pill they were taking was a vitamin or a sugar pill. The authors report some minor conflicts of interest, but none of them work for or received major funding from Pfizer (PFE, the manufacturer of Centrum). So how to explain the seeming contradiction with two larger studies published only a year ago?

To answer this question, we must look at the details of the study itself. This study looked at 21 different types of cancer risk. For most cancers - colon cancer, prostate cancer, lung cancer, pancreatic cancer, lymphoma, leukemia, melanoma, and others - multivitamins did not provide a benefit. But when all the numbers were added up, the effect was just large enough to be "significant", at a level of p=0.04. More on that in a moment.

Here are the raw numbers: among the 7,317 men who took a daily multivitamin, there were 1,290 cases of cancer over the 11-year study. Among the 7,324 men who took a placebo pill, there were 1,379 cases. That's about 1.2% more - far less than the 8% reported by Bloomberg News. The statistical analysis showed that this difference had a p-value of 0.04, a result the authors considered significant. When the authors looked only at men with no history of cancer, the effect was smaller, and not statistically significant.

One explanation of the new finding is that the effects were indeed due to chance. Let's look at that p-value of 0.04. In much of the scientific literature, any p-value below 0.05 is considered "significant," but this has been widely criticized, in part because it encourages binary "true, false" thinking that is not the way scientists actually think. Also, the "0.05 threshold actually represents evidence much weaker than the number "0.05" suggests. A back-of-the-envelope Bayesian calculation shows that if the cancer-preventing power of multivitamins was a 50:50 proposition before this study, then after this study there is still a 10-26% chance that the cancer prevention claim is wrong. If we thought that prior evidence made this effect less than 50:50, (say 25:75), then the study has roughly a 25-50% chance of being wrong.* Either way, I won't be stocking up on Centrum Silver anytime soon.

Looking at this small effect, and at the contradictory results from other studies, neurologist Steven Novella writes in his blog that

"About the only thing we can say with a high degree of confidence is that there is no large risk or benefit from taking a multivitamin. There may be a small benefit, no benefit, or even a small harm."

That's a good summary. So should men take a multivitamin? Well, it's your money, but if you don't have a vitamin deficiency, it's probably not worth it. Should women? The evidence still says no.

*Thanks to Stanford biostatistician Steven Goodman (formerly of Johns Hopkins University) for crunching some numbers to produce Bayes factors.

What do the Presidential candidates think about science?

noreply@blogger.com (Steven Salzberg) — Mon, 08 Oct 2012 11:30:00 +0000

ScienceDebate.org recently posed 14 questions to President Obama and Republican presidential nominee Mitt Romney, and just a few days ago, the candidates answered all 14. Can we learn what they actually think about science from these answers? Well, maybe just a little bit.

My first inclination, on going to the ScienceDebate2012 website, was to look for the candidates' positions on the two biggest scientific topics in the political arena today: evolution and global warming. Somehow, ScienceDebate2012 only asked about one of these, which I'll get to in a minute.

The ScienceDebate2012 organization calls its list "the top American science questions: 2012", but the questions themselves are a disappointment. They're what you'd expect from a committee: lots of nice-sounding, polite questions, but nothing that really challenges the candidates. I guess SD2012 was afraid that the candidates might get all offended, or maybe that fewer scientists would sign their petition. But if you read the answers, you'll see that the candidates just answered the question they wanted to hear, as politicians love to do. Most of the answers describe policies we already know (for those who are paying attention to the campaigns), but an interesting surprise popped up: Mitt Romney has no fondness for NASA. Jump to the bottom to learn more.

Most of the questions are big fat softballs, starting with the first one: "What policies will best ensure that America remains a world leader in innovation?" http://www.sciencedebate.org/debate12/ Good tough question, guys! We only have 14 questions, and you waste one on this? Unsurprisingly, the answers to this one just repeated campaign talking points.

Before looking at some real answers, let's start with the howlingly obvious question that ScienceDebate2012 failed to ask.

The Un-asked Question: do you believe that evolution should be taught in public schools, and that it should be presented as the only explanation for how species arose?

This question has only one right answer, as any biologist worthy of the name knows. Evolution is the foundation of all of modern biology, genetics, infectious disease research, you name it. And the U.S. is one of the few advanced countries where a significant number of its citizens don't accept evolution, opting instead for an archaic religious position that claims Earth is only a few thousand years old.

We should know the candidates' answers. In 2008, ten Republican presidential candidates were asked if they believe in the theory of evolution. Only 7 said yes--but one was Governor Romney. Back in 2007, he told the New York Times that "the science class is where to teach evolution," and that intelligent design was "for the religion class or philosophy class." President Obama also supports evolution, and opposes teaching creationism in the science classroom.

So the candidates agree on this one - at least they did in the past. But Romney's fellow Republicans don't all agree. In particular, we need to ask Governor Romney: do you support the crazy religious extremism of your fellow Republican, Congressman Paul Broun from Georgia, who just announced that evolution, embryology, and the Big Bang theory are

"lies straight from the pit of hell"?

And Broun also stated that the Bible - and his wacko interpretation of it - should be used to run our government. Any candidate for president should denounce this call for theocratic rule.

And by the way, if a Democratic Congressman said anything like this, I'd throw the same question at President Obama.

Now on to one of the real questions, on global warming. ScienceDebate2012 posed the question this way:

"The Earth’s climate is changing and there is concern about the potentially adverse effects of these changes on life on the planet. What is your position on cap-and-trade, carbon taxes, and other policies proposed to address global climate change—and what steps can we take to improve our ability to tackle challenges like climate change that cross national boundaries?"

Obama's short answer acknowledges that "climate change is one of the biggest issues of this generation," and goes on to say he will "continue efforts to reduce our dependence on oil and lower our greenhouse gas emissions." Vague generalities, and nothing he hasn't said before, but consistent at least.

Romney's answer, though, tries to have it both ways. He first says that global warming is indeed happening and then says, basically, we need more research because it's controversial. Here's how his lengthy answer begins:

"My best assessment of the data is that the world is getting warmer, that human activity contributes to that warming, and that policymakers should therefore consider the risk of negative consequences."

But then he pivots in the very next sentence and claims

"there remains a lack of scientific consensus on the issue ... and I believe we must supported continued debate and investigation within the scientific community."

So there you go: yes, global warming is a problem, but let's study it rather than do something. At the end of his answer, Romney recovers a bit by saying he supports "robust government funding for research on efficient, low-emissions technologies." So it appears he would support some action on global warming. But his answer offers a troubling false claim about a lack of scientific consensus: the consensus is rock solid.

Now, I promised one surprise: a bit of new information. Question 12 covers space exploration and is another softball:

"What should America's space exploration and utilization goals be in the 21st century and what steps should the government take to help achieve them?"

I expected some vague answers about how great America is (and both candidates did indeed deliver on that), but Romney surprised me with his answer.

Here's the surprise: Romney comes right out and says he will probably cut the NASA budget. What he actually said in his answer was:

"A strong and successful NASA does not require more funding, it needs clearer priorities."

In Washington-speak, this means "NASA has too much money and I will probably cut it."

So at least we know where Romney stands on space exploration. He wants to downsize it and, apparently, outsource it to other countries. Here's how he puts it later in his answer:

"Part of leadership is also engaging and working with our allies and the international community. I will be clear about the nation’s space objectives and will invite friends and allies to cooperate with America in achieving mutually beneficial goals."

If I worked for NASA, I'd be worried.

GM corn causes cancer in rats: a study in bad science

noreply@blogger.com (Steven Salzberg) — Mon, 24 Sep 2012 11:45:00 +0000

Last week a scientific paper appeared that reported that eating genetically modified (GM) corn causes cancer in rats. Specifically, the scientists fed Roundup Ready® corn, or maize, to rats for two years, and reported that both females and males developed cancer and died at higher rates than controls.

This is very surprising. If GM corn causes cancer, why aren't Americans "dropping like flies," as one scientist asked? We've been eating Monsanto's Roundup Ready® corn for over a decade, even if most of us aren't aware of it. But our rates of cancer haven't increased more than Europeans, who eat far less GM corn. Maybe the effect is limited to rats - in which case we should also have seen dramatic increases in cancer in lab rats. But we haven't seen that either.

So what's wrong? The best way to find out is to read the paper, which I did. It turns out to be a very badly designed study, and the report itself omits many crucial details that may (and probably do) completely invalidate the findings. The scientists leading the study have a strongly biases agenda and a conflict of interest, which they failed to reveal. I'll explain below, but meanwhile this study has already been taken up by politicians as proof (proof!) that GMO crops are harmful. As Forbes blogger Tim Worstall explained, this paper is more politics than science.

Let's look at the study itself, which was led by Gilles-Eric Seralini (more on him below) and published last week in Food and Chemical Toxicology. (A copy of the full paper is here.)

The authors studied 200 rats for 2 years, dividing them into 20 group of 10 rats each. The test rats were fed a variety of diets:

Non-GM corn comprising 33% of the diet (this was the control group).
Roundup Ready corn comprising 11%, 22%, or 33% of the food.
Roundup Ready corn that had been treated with Roundup during cultivation.
Non-GM corn but with Roundup itself added to the rats' water.

So what happened? Well, in some groups, the rats got more cancer than controls. But not always. In fact, the authors had to cherry-pick their own data to support their conclusions.

One major problem is that only 10% of the rats were controls - 10 male, 10 female. The study's main claim is that rates of cancer were significantly higher in the rats fed GM corn. Martina Newell-McGloughlin from UC Davis, in an interview with Discovery News, said

"The type of statistical analysis they used is really a type of fishing expedition. One individual referred to it as 'fantasy statistics.' "

Another major problem is that there's no dosage effect. In other words, if Seralini is right and GM food is bad for you, then more of it should be worse. But the study's results actually contradict this hypothesis: rats fed the highest levels of GM corn lived longer than rats fed the lowest level.

A third problem, as Discovery News and other sources reported, is that the rats used in this study are a special laboratory strain that is highly prone to cancer.

Perhaps most damning, though, is the fact that rats fed Roundup directly had the longest survival times. As Seralini's own Figure 1 shows, the longest-living rats in the entire study, out of all the conditions, where those that drank Roundup in their water. These rats outlived the control rats.

Yum! Maybe Perrier should start selling Roundup-enhanced spring water?

Seralini and colleagues struggle to explain the internal contradictions in their study. They write,

"Interestingly, in the groups of animals fed with the NK603 [Roundup Ready corn] without R[oundup] application, similar effects with respect to enhanced tumor incidence and mortality rates were observed."

This tortured English is their way of admitting that rats did worse ("similar effects") when fed GM corn that was grown without Roundup. They don't want to admit that this result contradicts their central hypothesis.

The study was designed to fail: the sample sizes (10 rats in each group) are so small that all the results are likely just due to chance, and none of the differences are meaningful. It's exceedingly unlikely that the Roundup in the rats' water made them live longer, just as it's unlikely that Roundup Ready corn had any effect on the incidence of cancer.

I know that ad hominem attacks aren't valid, but I can't resist pointing out that Seralini's co-author, Joel de Vendomois, is a homeopath, with a "Homeopathy and Acupuncture Diploma", a double dose of quackery in a single degree. Seralini has also published a book about the supposed dangers of GMOs, and he and de Vendomois are the lead scientists at CRIIGEN, an organization devoted to lobbying against GMOs. Of course, even if Seralini and de Vendomois are bad scientists, and even if they have a strong bias, their paper isn't necessarily wrong. It's wrong simply because the science is wrong.

Not surprisingly, an anti-GMO group in California has gleefully embraced the claims of this dreadful paper to argue in favor of Proposition 37, a ballot initiative that will require labelling of genetically modified foods. And Jose Bove of the European Parliament has used it to claim that all GM crops are harmful to human health.

Let's be clear about the science here. Genetic modification of foods is a powerful technology that can be incredibly beneficial. The recent development of salmon that can grow faster is an example: these salmon (developed by a company called AquaBounty) will make fish farming more efficient, and thereby help preserve the perilously endangered wild fish species in our oceans. On the other hand, GM technology can be used, as Monsanto has done, simply to allow farmers to use more pesticides, which doesn't seem to benefit anyone other than the pesticide producers. It's unfortunate that Monsanto's behavior has been used as an excuse to give all GMOs a bad name.

Now we have a bad study done by anti-GMO scientists who have allowed their political agenda to trump their scientific judgment. What a mess.

Stabbing kids with needles: malpractice, or just a very bad idea?

noreply@blogger.com (Steven Salzberg) — Wed, 12 Sep 2012 12:39:00 +0000

Yesterday's Washington Post featured a terribly researched article titled "Kids and needles is sometimes a good match: Acupuncture can help with pain."

Imagine: a one-year-old boy arrives at an emergency room in New York at 3 a.m. with an asthma attack. He is slow to respond to a nebulizer treatment. Enter Dr. Stephen Cowan, who decides to use acupuncture. That's right, he stabs a one-year-old baby with multiple needles to treat asthma. According to Dr. Cowan, the boy "reacted calmly" and improved. The article doesn't provide any more details.

This is appalling. Sticking needles into a baby has never been shown to have any effectiveness at treating asthma, and we do have treatments that work. In all likelihood, the nebulizer did work, in the case that Dr. Cowan related to the reporter, but Dr. Cowan mistakenly credits his acupuncture treatment.

Stephen Cowan is a aggressively self-promoting doctor, who claims on his website that he can treat both autism and ADHD with acupuncture and other forms of Chinese Medicine. He also describes how he convinces children to let him stick needles into them. He states his belief in mystical "vital energy" or qi, one of the wacky pseudoscientific notions at the core of acupuncture beliefs. His claims are little more than a modern, mystical version of the claims made by 19th-century snake oil salesman.

The Washington Post story also revealed that Children's National Medical Center in Washington, D.C. recently treated a 17-year-old girl with pancreatitis by stabbing needles into her stomach and other places. There is no evidence that this works, but the girl's doctor believes it does. The girl reportedly wasn't harmed, fortunately.

The doctor at Children's Hospital, Jennifer Anderson, is an anesthesiologist who is also an acupuncturist. In the story, she said "I often treat patients with chronic issues" with acupuncture. This is frightening: a doctor at a major medical center is telling children, most of whom are too young to even think of questioning the wisdom of a doctor, that sticking them with needles will help their pain. Dr. Anderson admitted that "she often does two to three treatments a week at first on a child." So she admits to stabbing many sharp needles into children and telling them that the treatments will help their pain. She argues that the children report that this is "helpful."

This is perilously close to child abuse. Children want to please adults, and if an adult tells them something is good for them, especially if an authority figure tells them, they are extremely unlikely to disagree. They'll just swallow the medicine, or endure the treatment, and then tell the adult what she wants to hear. Dr. Anderson seems unaware of this. And Children's National Medical Center, a generally outstanding hospital, should be seriously concerned that one of its anesthesiologists is practicing quack medicine on children, who are perhaps the most vulnerable of all patients.

Let's be clear: acupuncture is based on nonsense. Scientists have gone to great pains to study it, and the conclusion can be stated simply: acupuncture does not work. (And yes, I know about the latest meta-analysis claiming that acupuncture works. Dr. Steven Novella has already explained why that analysis is "completely useless.") If acupuncture were a drug being tested by a pharmaceutical company, it would have been abandoned long ago. Its proponents are no better than any big pharma company that pushes a drug that it knows to be ineffective.

Acupuncture is worse than ineffective: because it's an invasive procedure, there is a small but real risk of harm. As I wrote last year in The Atlantic, acupuncturist sometimes cause infections, which can lead to rare but serious complications. Acupuncturists protest (often) that they use sterile needles, but this very protest reveals their ignorance: most infections are caused by bacteria already present on the skin, which enter through the puncture wound.

Parents: don't let an acupuncturist stick needles into your kids. Read the science first, and avoid - no, run screaming from - any practitioner who claims that he can adjust the "qi" in your child.

British Health Minister believes in magic water

noreply@blogger.com (Steven Salzberg) — Sun, 09 Sep 2012 14:13:00 +0000

Well, this is one way to save money on health care. The new British Minister of Health, Jeremy Hunt, is a firm believer in homeopathy, which treats disease using magic water solutions that contain - well, only water.

Just a few days ago, British prime minister David Cameron shuffled his cabinet, moving Hunt from Minister of Culture to his new position in charge of health. Within hours, Tom Chivers, a science editor at the Telegraph, reported on Hunt's belief in homeopathy:

"The man put in charge of the nation's health policy is on record as supporting spending public money on magic water to cure disease."

He went on to add:

"This is not unlike putting someone who thinks the Second World War began in 1986 in charge of the Department of Education."

Not surprisingly, Chivers' blog post was flooded with hundreds of comments, many of them from upset defenders of homeopathy. Most of their arguments boiled down to "I think it works for me, so there."

Homeopathy is one of the most absurd, wildly implausible forms of quack medicine. I've written about it many times (for example, about the bogus flu pills sold as oscillococcinum,
about NCCAM's embarrassing funding of studies of homeopathy, and about how homeopaths offer strychnine to cure children's colds), so I'll try not to repeat myself. Homeopathy is founded on two basic notinos, both of them dead wrong:

Infinitely diluted substances are more potent than substances at higher concentrations, and
"Like cures like," meaning that if a substance causes a symptom, you can use that substance to cure the symptom.

Thus caffeine can be used to help you sleep, and poison ivy can cure itching. No, I'm not making this up; homeopaths really believe this stuff.

Homeopathy is simply magical thinking. There has never been a shred of scientific evidence to support it, and the British Medical Association declared in 2010 that homeopathy is witchcraft. After pressure from science bloggers, NIH's NCCAM has corrected its website to state that

"it is not possible to explain in scientific terms how a remedy containing little or no active ingredient can have any effect."

But homeopaths make a lot of money selling homeopathic potions, and through clever marketing they keep themselves in business. Now they have a new ally, the UK Minister of Health. Andy Coghlan, writing in The New Scientist, called him "the new minister for magic." Brilliant! As Coghlan pointed out, magic is much cheaper than real medicine:

"Think of the savings if all those expensive proven treatments and drugs are phased out, and patients are offered cheap little vials of water instead."

We're desperately looking for ways to control health care costs here in the U.S. as well. The UK Minister of Magic may have a solution for us. I wonder, though, if it works for muggles?

What did the ENCODE project discover about the genome? A quick shout-out.

noreply@blogger.com (Steven Salzberg) — Fri, 07 Sep 2012 22:09:00 +0000

Does top-down science work as well as bottom-up science?

This is just a quick link-over to my friends at Simply Statistics, who interviewed me on their blog (and vodcast) about the just-published set of papers on the human genome known as the ENCODE project. Check it out here, and then follow the discussion and comments further on their follow-up post here.