JMIR AI

Spirometry is the standard physiological test defining airflow obstruction, the key criterion for diagnosing chronic obstructive pulmonary disease. It is underused in high-income settings and often unavailable in low- and middle-income countries, causing underdetection. Deep learning analysis of chest radiographs, which are widely available where spirometry is not, may complement spirometric screening, but its use in North American cohorts and across demographic strata has not been examined.

Colorectal cancer is a leading cause of cancer-related deaths in the United States, and colonoscopy remains the gold standard for early detection and prevention. However, many procedures are postponed due to inadequate bowel preparation, a preventable failure often caused by patients’ difficulty in understanding and following written prep instructions. Prior interventions such as reminder apps and instructional videos have improved adherence only modestly, largely because they cannot answer patient-specific questions. Recent advances in large language models (LLMs) raise the possibility of developing conversational assistants that can provide interactive support to patients in procedure preparation.

AI is increasingly proposed as a tool to enhance disaster medicine through improved situational awareness, decision support, and resource coordination. However, the extent to which current research has progressed beyond methodological development toward integrated, operationally validated systems remains unclear.

Enhanced recovery after surgery protocols have shortened orthopedic hospital stays but have shifted rehabilitation and safety-monitoring tasks to patients and families after discharge. In this study, AI refers to patient-facing digital systems for orthopedic transitional care, including large language model chatbots, computer vision or platform-based monitoring tools, and wearable sensor–enabled systems for education, rehabilitation guidance, motion correction, and risk alerts. However, patient-reported preferences for different AI-supported functions across the hospital-to-home transition remain underexplored.

Patient-reported outcome measures (PROMs) are central to multinational clinical research, but high-quality translation and linguistic validation remain resource-intensive. AI-powered translation may accelerate this process, but its performance relative to validated human PROM translations requires systematic evaluation.

Integrated knowledge translation still relies on static reports, presentations, and manuscripts that cannot adapt to decision-makers’ evolving questions. Retrieval-augmented large language models can add a secure, auditable conversational layer over curated program outputs and selected research materials, enabling rapid, traceable synthesis between meetings and across portfolios. Treating these tools as governed infrastructure, with mandatory provenance, privacy protections, transparent documentation, and equity by design, could help reduce friction in evidence exchange and shorten the lag between knowledge creation and use. This viewpoint paper advances a conceptual design vision and the governance it requires, rather than reporting an evaluation of a deployed system.

Synthetic electronic health record generation is limited not only by statistical fidelity but also by clinical validity. Records that appear statistically plausible may still violate hard structural, physiological, or relational constraints.

Large language models (LLMs) have the potential to provide individualized preventive care guidance at scale. Research, however, has found mixed performance among a small set of LLMs queried about select preventive care activities. These findings call for testing a larger set of LLMs on a wider range of preventive care topics.

Large language models (LLMs) can accurately classify biomedical documents, but strong benchmark performance does not establish that predictions are grounded in the supplied text. In biomedical literature tasks, titles, abstracts, digital object identifiers (DOIs), journal metadata, and trial identifiers may have been seen during pretraining and can trigger parametric knowledge or learned associations.

Relaxation techniques, such as the “safe place” imagery exercise, are simple and accessible strategies to cope with the negative effects of stress. While virtual reality (VR) has been applied in relaxation research, it is still unclear whether it enhances the relaxing effect of such exercises or is merely an alternative and similarly effective form of delivery.

Task-shifting can help close the mental health treatment gap in low- and middle-income countries, but its effectiveness depends on ongoing supervision, which is hard to scale. AI tools that process session recordings and generate structured fidelity feedback could offer a scalable alternative; yet, to our knowledge, none have been developed or validated for lay-delivered, multilingual, group-format interventions in low-resource settings.

Anxiety disorders are highly prevalent among adults with autism, with 20%‐65% experiencing at least one diagnosable anxiety disorder. While mindfulness-based interventions have demonstrated efficacy for anxiety reduction, treatment response varies considerably across individuals. Machine learning approaches offer potential for identifying who is most likely to benefit from smartphone-based mindfulness interventions, enabling personalized treatment recommendations.