JMIR Human Factors

Understanding Barriers to Effective Injury Care by Medical Trainees and Traffic Law Enforcement First Responders in Low-Income Contexts in Uganda (Motor Registry Project Part 2): Convergent Mixed Methods Analysis

2026-06-10T14:30:14-04:00

Background: Trauma-related mortality exhibits a marked social gradient, driven by access barriers and health inequities worldwide. These barriers jeopardize progress toward Sustainable Development Goals 3 and 4. Objective: This study aimed to investigate the prehospital and in-hospital barriers to timely injury care as perceived by frontline trainee physicians and traffic law enforcement professionals during real-time treatment execution in Uganda. Additionally, we aimed to highlight the potential impact of these barriers on trauma outcomes. Methods: This study used a convergent mixed methods approach. Qualitative data were collected through structured interviews and face-to-face focus groups with diverse teams of 500 frontline trainee physicians, including surgical residents, interns, medical students, and traffic law enforcement professionals. Directed content analyses for structured interviews and focus groups were conducted in NVivo (version 14, release 2023; QSR International). Quantitative data were concurrently collected using a survey questionnaire from the Motorcycle Trauma Outcome Registry, which included 1003 patients with trauma. We categorized barriers as prehospital or in-hospital barriers and as trauma team-related, patient-related, or health system–related barriers. Multilevel restricted maximum likelihood logistic regression analyses of factors associated with barriers to injury care were analyzed using Stata (version 15.0; StataCorp LLC). Odds ratios (ORs) and 95% CIs were reported; statistical significance was defined as <.05. Results: Qualitative analyses identified key prehospital barriers, including delays in emergency medical services activation, ambulance arrival, and transportation. In-hospital barriers were primarily shortage of supplies, delays in identifying life-threatening injuries, and insufficient critical care services. Quantitatively, among the 1003 audited patients with trauma, 42% (416/1003) faced barriers during treatment. The most common obstacles were delays in treatment decisions (232/1003, 23%) and securing necessary supplies (180/1003, 18%). The presence of barriers was independently associated with a 3-fold increased likelihood of unfavorable Glasgow Outcome Scale scores (OR 3.15, 95% CI 2.23‐4.66; <.001) for neurological injuries and was linked to a 4-fold increase in odds of 90-day mortality (OR 4.20, 95% CI 2.25‐6.94; <.001). After adjusting for injury severity and clustering effects by hospital teams and resources, the presence of barriers was associated with arrival by public means (adjusted OR [aOR] 1.62, 95% CI 1.09‐2.41; =.02), increasing age (aOR 1.01, 95% CI 1.00‐1.03; =.01), sustaining 1 or more injuries requiring admission (aOR 1.92, 95% CI 1.18‐3.14; =.01 vs aOR 3.69, 95% CI 1.95‐6.98; <.001), and a severe Kampala Trauma Score of ≤6 (aOR 2.71, 95% CI 1.37‐5.37; =.004). Conclusions: Multiple barriers to trauma care are more frequent for severe injuries and are associated with poorer neurological outcomes and higher mortality. These findings indicate the need for targeted, multifaceted interventions that incorporate frontline health workers’ perspectives to improve trauma care delivery in low-resource settings facing both prehospital and in-hospital barriers. International Registered Report Identifier (IRRID): RR2-10.2196/55297

Large Language Model–Based Simplification of Digital Therapeutics Explanations for Insomnia and Nicotine Dependence: Two Randomized Online Experiments

2026-06-10T14:15:13-04:00

Background: Digital therapeutics (DTx) are evidence-based software interventions with the potential to treat health conditions. However, uptake remains limited by low public awareness and overly complex patient education materials that exceed recommended readability levels. Large language models (LLMs) may simplify such content; however, their effects on users’ understanding have not been empirically demonstrated. Objective: This study aimed to examine whether LLM-based simplification of DTx explanatory materials enhances perceived understanding and subjective evaluations of readability, clarity, and comprehensibility compared with manufacturer-provided documents. Methods: We developed a simplification tool using the GPT-4o application programming interface (API), configured for deterministic outputs and guided by structured readability instructions. Original DTx explanatory materials about insomnia and nicotine dependence were obtained from manufacturers and transformed into simplified versions. Two randomized, between-subject online experiments were conducted (n=1000, with 500 participants in each experiment). Participants were stratified by age and sex and screened for relevance (Insomnia Severity Index ≥8 for the insomnia experiment and smoking ≥5 cigarettes per day for the nicotine dependence experiment). Within each experiment, participants were randomly assigned to review either the original or the LLM-simplified explanatory material. Perceived understanding was assessed before and after exposure. Postexposure evaluations of ease, clarity, and comprehensibility were also collected. Results: Repeated measures ANOVA revealed significant group×time interaction effects on perceived understanding in both experiments: insomnia (=24.8; <.001) and nicotine dependence (=14.1; <.001), with greater improvements observed in the LLM-simplified groups. Mann-Whitney tests further showed that LLM-simplified explanations were rated as easier, clearer, and more comprehensible than the original versions in both experiments (all <.05), with small to moderate effect sizes (=0.11-0.24). Conclusions: Compared with manufacturer-provided original materials, LLM-simplified DTx explanations led to greater improvements in perceived understanding and subjective evaluations of readability among lay audiences, even after a single exposure. This finding highlights the potential scalability of LLM-based simplification as a strategy to improve the perceived accessibility of health information for lay audiences. Integrating such tools into patient education may enhance how lay audiences perceive and engage with DTx, although further research using objective comprehension measures is needed to confirm these benefits. Trial Registration: Clinical Research Information Service KCT0011459; https://cris.nih.go.kr/cris/search/detailSearch.do?seq=32221

Good Clinical Practice Guidance for Line Materials, Filtration, and Light Protection in Intravenous Medication Administration: Modified Delphi Consensus Study

2026-06-10T13:30:03-04:00

Background: There is an unmet need for reliable medication stability information to avoid suboptimal administration of intravenous medications, which may lead to reduced efficacy of therapy and potential patient harm through medication degradation or incompatibilities that cause vascular access issues. Objective: This study aimed to develop evidence-informed guidance for pharmacists and nurses on the use of administration line materials, in-line filtration, and light protection during storage and intravenous administration of medications commonly used in critical care and oncology. Methods: An initial list of 181 medications was compiled in consultation with pharmacist stakeholders from critical care and oncology specialties. A modified Delphi study was conducted over 3 rounds with a panel of 8 expert pharmacists selected for their clinical expertise, professional experience, and geographic location to ensure representation of diverse health care settings and medication administration practices. Panelists anonymously ranked statements on a 5-point Likert scale developed from a review of the literature with respect to the requirement for a specific administration line material for each medication; the need for, and type of, filtration required during administration; and the need for light protection during storage and administration of medications. After each round, items achieving 80% consensus were finalized. Those that did not achieve consensus were carried forward to the next round. This iterative approach allowed panelists to reconsider their ratings based on emerging group consensus and additional evidence shared by panelists between rounds. Results: A total of 1044 administration and storage requirements were assessed for a final list of 174 medications. In round 1, consensus was reached for 613 (58.7%) statements, with every statement being addressed and scored by the panelists. Panelists provided additional evidence sources for their decisions, and these were distributed to all panel members for round 2. All items were addressed and scored by the panelists. By the conclusion of round 3, consensus had been achieved for 697 (66.8%) statements, with all items being addressed and scored by the panelists. Conclusions: This study developed consensus-based recommendations for the selection of administration line materials, the use of in-line filtration, and light protection for the administration and storage of a range of medications administered intravenously. The guidance will aid medication stability and efficacy and promote good clinical practice; it currently underpins a prototype bedside app for correct intravenous administration line selection for nursing and pharmacy staff in critical care and oncology units.

Effectiveness of a Brief Digitized Contact-Based Intervention in Improving Mental Health Stigma and Help-Seeking in Young Adults: Mixed Methods Study

2026-06-10T13:00:22-04:00

Background: Contact-based interventions, where individuals share their lived experiences of mental health difficulties and recovery, appear effective in reducing stigma. Objective: This study examined the effectiveness of a brief digitized contact-based intervention in reducing mental health stigma and improving help-seeking intentions in young adults. The study also sought a deeper understanding of the perspectives of young adults toward the contact-based intervention. Methods: A mixed methods study, using quantitative and qualitative analyses, examined mental health public stigma, self-stigma, and help-seeking attitudes in undergraduate psychology students (N=328) before, immediately after, and 1 week following the contact-based intervention, compared to an active control. The intervention comprised a brief video (8 min) of a mental health consumer sharing their lived experience of mental health difficulties and their recovery. Participants were invited to participate in a subsequent semistructured interview (n=12) that further explored their perspectives on the contact-based intervention. Results: Relative to control participants, those in the intervention group reported small improvements in mental health public stigma and help-seeking intentions using formal sources of help; however, this was not maintained at 1-week follow-up. There was limited evidence that the intervention improved self-stigma or help-seeking intentions using informal sources of help. Improvements in self-stigma were not evident following the intervention, but were observed 1 week later. Additional exploratory analyses showed that participants with high mental distress were more likely to provide negative evaluations of the intervention in terms of the helpfulness of the videos, relatability to the speaker, and showed a decrease in their desire to seek help from friends and family following the videos, compared to those with low mental health distress. Conclusions: Although this brief digitized contact-based intervention holds promise as an easily disseminated strategy for young adults to reduce mental health public stigma and improve formal help-seeking intentions, these effects show that overall improvements in public stigma and formal help-seeking intentions were short-lived. Furthermore, the potential negative impact of the intervention on informal help-seeking intentions in those with high mental health distress suggests a need to tailor interventions for young adults with high levels of anxiety or depression. The study has important implications for designing brief contact-based interventions and what young adults would benefit from the most over time. Trial Registration: ISRCTN Registry ISRCTN65081246; https://www.isrctn.com/ISRCTN65081246

Exploring Factors Influencing Nursing Task Prioritization for Supportive Information System Design: Qualitative Study With Thematic Analysis

2026-06-05T13:30:16-04:00

Background: Nurses are required to perform multiple tasks concurrently, which leads to multitasking situations, and they have to continuously determine which tasks should be prioritized. This is particularly challenging for novice nurses. Although IT-based systems supporting prioritization have begun to emerge, research on the types of information required when prioritization is processed computationally is scant. Despite the clear need for a supportive information system to assist nursing task prioritization, such systems are not yet sufficiently developed. Objective: This study aimed to explore the appropriate granularity and structure of information that should be provided to computational systems to support decision-making based on the influencing factors of nursing task prioritization. Methods: Semistructured interviews were conducted with 10 nurses working in general wards to examine the factors they consider when determining task prioritization during clinical practice. Data were analyzed using an inductive, semantic approach based on a thematic analysis framework. Results: Three themes and nine categories including (1) medical condition assessment factors (signs of acute physiological changes and indicators of clinical status and conditions), (2) patient-related nursing care factors (physical status, psychological condition, and personal characteristics; care needs during hospitalization; and treatment goals and care preferences), and (3) organizational and operational work factors (temporally structured tasks, requiring collaboration partners for task execution, environmental factors affecting task performance, and institutional- and ward-level policies) were identified. Conclusions: Analysis of computational tractability of the identified factors indicated that medical condition assessment factors are relatively quantifiable. In contrast, patient-centered care and organizational and operational work factors rely on contextual and experiential judgment, limiting standardization and formalization. Regarding such ambiguous and context-dependent elements, flexible information-processing approaches, such as large language models, in addition to conventional rule-based methods, may be effective. Furthermore, the appropriate level of information granularity should be determined by the nature of the prioritization outputs required in actual nursing practice rather than the degree of abstraction itself.

C8 Health, a Platform for the Implementation of Best Practices: Survey-Based Usability Study

2026-06-05T11:45:16-04:00

Background: Mobile health (mHealth) apps are increasingly integrated into clinical workflows to support decision-making and adherence to best practices. Usability is a critical determinant of adoption, engagement, and long-term use. Objective: This study aimed to evaluate the usability of the C8 Health platform deployed in the Department of Anesthesiology at MetroHealth in 2024. Methods: A quality improvement initiative was conducted using the mHealth App Usability Questionnaire (MAUQ). A total of 142 anesthesiology clinicians participated by completing the questionnaire. This study was reported in accordance with the SQUIRE (Standards for Quality Improvement Reporting Excellence) guidelines for quality improvement reporting. Results: The overall MAUQ scores indicated high usability, with mean scores greater than 5.5 across core items (overall mean MAUQ score 5.73, SD 0.81). These findings suggest strong user satisfaction and positive engagement with the C8 Health platform among anesthesiology clinicians. Conclusions: The C8 Health platform demonstrated high usability in an anesthesiology setting. These results support its integration as a clinical decision support tool to enhance workflow efficiency and adherence to best practices.

Evaluating a Digital Mental Health Tool for Implementation Into New Zealand’s Integrated Primary Mental Health and Addictions Service: Usability Study

2026-06-04T14:45:17-04:00

Background: Rising global demand for mental health services strains traditional care models, a trend evident in New Zealand, where the Integrated Primary Mental Health and Addictions (IPMHA) model was introduced to improve access to care. While the IPMHA model shows promise, significant service-delivery challenges undermine its scalability. Digital mental health tools (DMHTs) present an opportunity for digital optimization, yet their effectiveness is often limited by low practitioner adoption, a persistent implementation barrier. To ensure these tools are impactful, a user- and context-centered DMHT design approach may help mitigate practitioner adoption barriers and create solutions that can be seamlessly integrated into clinical workflows. Objective: Reporting on the Test stage of the 5-stage Design Thinking framework, this study aimed to evaluate the usability and acceptability of a DMHT software prototype intended to support health improvement practitioners working within New Zealand’s IPMHA model. Methods: Five health improvement practitioners from a single primary health organization participated in semistructured usability interviews. Data were collected using a think-aloud protocol during mock clinical sessions and analyzed using affinity diagramming to identify key software feature requirements necessary to promote usability, adoption, and workflow integration. Results: Feedback was obtained for all software minimum viable product features. While practitioners found the clinical support features valuable, 2 system-level requirements were identified as prerequisites for adoption. The first was administrative optimization: the DMHT must reduce workload by automating tasks, such as clinical note entry, data reporting, and psychometric scoring. The second was seamless integration with existing clinic patient management software to eliminate double-handling of data and resolve IT-related workflow frustrations. Conclusions: For a DMHT to be successfully adopted by IPMHA practitioners, it must primarily function to solve existing administrative and workflow inefficiencies. Clinical support features, such as the provision of therapeutic tools and exercises, though helpful, are secondary to the tool’s ability to be a practical, efficient, and fully integrated component of daily practice. These findings underscore the value of user- and context-centered design in uncovering the pragmatic, systems-level needs of end users in a complex primary care service-delivery environment.

Early Deployment of an Integrated Digital Platform (shamiriOS) for Scalable Youth Mental Health Service Delivery in Kenya: Development and Usability Study

2026-06-03T16:00:03-04:00

Background: Scaling youth mental health services in low-resource settings requires digital infrastructure that supports not just clinical delivery but the full operational, supervisory, and engagement demands of community-based, task-shifted models. Existing platforms—whether commercial health systems, open-source medical records, or consumer-facing wellness apps—address fragments of this need, but none provide the integrated, offline-capable, and affordable architecture required for lay-provider delivery at scale. Objective: We introduce shamiriOS, an open-source, modular digital platform comprising 3 interlinked suites—the Shamiri Digital Hub (SDH) for operational management, Rafi for youth engagement, and the Shamiri Provider Platform (SPP) for clinical workflows—designed for scalable, stepped-care youth mental health delivery in Kenya. Our objectives were (1) to conduct an environmental scan of existing platforms and characterize their limitations, (2) to describe the user-centered design and development of shamiriOS, and (3) to report early deployment outcomes across centralized and decentralized settings between 2023 and 2024. Methods: We conducted a structured environmental scan of 6 case management platforms and 28 youth-facing mental health apps, assessing cost, usability, open-source availability, customizability, offline capability, and suitability for task-shifted delivery. Based on identified gaps, SDH was built as a browser-based operation platform, and Rafi was developed as a native mobile app (Android or iOS) with an offline-first architecture. The SPP was adapted from an existing electronic medical record system. Development followed a user-centered design process with community consultation, including cocreation workshops with 77 university-aged youths. Deployment was evaluated using use analytics, usability ratings, and Net Promoter Scores. Results: No reviewed platform met the combined requirements for stepped-care delivery. SDH was deployed across 11 sites serving 76,344 youths via 1195 lay providers and 111 clinical supervisors by Q1 2024. Staff reported high satisfaction (usability: mean 8.36/10, SD 1.49; Net Promoter Score: mean 8.63/10, SD 1.46). Rafi achieved 74.7% (n=3737) registration at Mount Kenya University, with 50.4% (508/1008) booking therapy sessions, but sustained engagement with self-guided features declined to near 0 by 9 months. Conclusions: shamiriOS demonstrates the feasibility of building modular, open-source digital infrastructure for scalable, task-shifted youth mental health delivery. Its component-based architecture is designed for adaptation to other contexts, though extension would require participatory redesign. The most significant obstacles to impact lie not in platform design but in implementation readiness, incentive alignment, and institutional integration. Future priorities include SPP deployment, artificial intelligence–assisted supervision features (shamiriAI), and strengthening sustained engagement.

Telehealth Use Among Older Adults Receiving Home- and Community-Based Services: Cross-Sectional Analysis Using the National Core Indicators–Aging and Disabilities Survey

2026-06-02T16:15:14-04:00

Background: Telehealth was essential for maintaining care continuity during the COVID-19 pandemic, leading to its rapid adoption across the United States. Telehealth has been heralded as a strategy for improving health care access and reducing health disparities, especially for community-dwelling older adults who face significant barriers to in-person care. However, data on telehealth use among socially and financially vulnerable older adults are limited, and little is known about characteristics associated with telehealth use in this population. Objective: Guided by the Systems Engineering Initiative for Patient Safety (SEIPS) 3.0 framework, this study examined factors associated with postpandemic telehealth use among older adults living at home and receiving publicly funded home- and community-based services (HCBS), considering HCBS receipt as an indicator of social and financial vulnerability. Methods: This cross-sectional study included older adults aged 65 years or older living at home with available telehealth use data who participated in the 2021‐2022 survey wave of the National Core Indicators-Aging and Disabilities Adult Consumer Survey. We used complete-case multivariable logistic regression, adjusting for sociodemographic and health-related factors with state-level random intercepts, to examine associations between telehealth use and covariates of interest (age, sex, race/ethnicity, zip code, rural-urban commuting area code, internet access, self-perceived overall health, medical transportation access, living alone, number of known non–Alzheimer disease and related dementias [ADRD] diagnoses, known ADRD diagnosis, and HCBS program/payer type). Based on the regression results, we estimated bivariate associations between internet access and key sociodemographic variables (age, sex, race/ethnicity, and zip code rural-urban commuting area) using the Pearson chi-square test. Findings were organized and interpreted through the SEIPS 3.0 framework. Results: Of the 3680 participants, 1467 (40%) were telehealth users and 2213 (60%) were nonusers. Significantly lower odds of telehealth were observed for older adults in older age groups, males, Black individuals, those living in nonmetropolitan areas, and recipients of Older Americans Act services (odds ratios [OR] between 0.66 and 0.80). Individuals with more than one known non-ADRD diagnosis (OR 1.49, 95% CI 1.02‐2.17) and those with an ADRD diagnosis (OR 1.33, 95% CI 1.07‐1.66) had higher odds of telehealth use. Internet access was strongly associated with telehealth use (OR 2.51, 95% CI 2.15‐2.92). Follow-up bivariate analyses between internet access and sociodemographic characteristics revealed that those of younger age, females, and White individuals had higher levels of internet access. Conclusions: Differences in telehealth use among older HCBS recipients are associated with multiple individual, technological, and organizational factors. Interpreted through the SEIPS 3.0 framework, these findings underscore the importance of viewing telehealth use as the outcome of multiple features of the health care system. Future research should clarify the mechanisms driving variation in telehealth use to identify and address barriers to telehealth adoption among vulnerable older adults.

Radiologist Perceptions of an AI Tool for Intracranial Hemorrhage Detection in Teleradiology: Cross-Sectional Survey Study

2026-06-02T15:01:46-04:00

Background: Artificial intelligence (AI) detection tools for intracranial hemorrhage (ICH) are increasingly integrated into radiology workflows. In real-world practice, perceived utility depends not only on diagnostic performance but also on workflow fit, false positive burden, and how clinicians interpret and act on AI outputs. Objective: This study aimed to characterize radiologists’ perceptions of a Food and Drug Administration (FDA)–cleared ICH AI detection tool in a national teleradiology network, including perceived reliability, false positive burden, workflow impact, medicolegal concerns, and self-reported behaviors during routine use. Methods: We conducted an anonymous cross-sectional survey of radiologists in a national teleradiology practice who had access to an FDA-cleared ICH AI overlay during noncontrast head computed tomography interpretation. Survey items used a 5-point Likert scale. Results are summarized as agreement proportions (“agree” or “strongly agree”) with 95% CIs. We compared neuroradiologists with non-neuroradiologists using Fisher exact tests. One primary end point was prespecified: agreement that time spent reviewing examinations with false positive AI alerts outweighed the benefits. Remaining subgroup comparisons were treated as exploratory, with false discovery rate control using the Benjamini-Hochberg procedure. Results: A total of 65 radiologists responded, including 23 (35.4%) neuroradiologists and 42 (64.6%) non-neuroradiologists. Only 18.5% (12/65; 95% CI 10.9%-29.6%) agreed that false-positive alerts were infrequent enough to be acceptable. Agreement that the AI correctly identified most ICH cases was 32.3% (21/65; 95% CI 22.2%-44.4%), and agreement that the AI rarely missed clinically important hemorrhages was 43.1% (28/65; 95% CI 31.8%-55.2%). Trust in AI output was conditional: 50.8% (33/65; 95% CI 38.9%-62.5%) reported trusting the AI when it agreed with their interpretation, whereas 3.1% (2/65; 95% CI 0.8%-10.5%) reported trusting it when it conflicted with their interpretation. Only 10.8% (7/65; 95% CI 5.3%-20.6%) reported reduced overall interpretation time, whereas 33.8% (22/65; 95% CI 23.5%-46.0%) agreed that time spent reviewing false-positive alerts outweighed the benefits. Self-reported reduced scrutiny after an AI-negative result was uncommon (4/65, 6.2%; 95% CI 2.4%-14.8%). In subgroup analysis, neuroradiologists more often endorsed the primary end point than non-neuroradiologists (12/23, 52.2% vs 10/42, 23.8%; unadjusted P=.03), but no exploratory subgroup differences remained statistically significant after false discovery rate correction. Free-text responses emphasized artifact- and calcification-driven false positives, delayed or inconsistent AI availability, consultation burden, and medicolegal concerns. Conclusions: In this national teleradiology setting, radiologists reported substantial false positive burden, limited perceived time savings, and strongly conditional trust in an FDA-cleared ICH AI detection tool. Self-reported reduced scrutiny after negative AI outputs was uncommon but present in a minority of cases. These findings support the importance of specificity, interpretability, latency, and workflow-aware implementation when deploying radiology AI tools in practice.