Search AMIA.org

Current artificial intelligence (AI) integration in patient messaging often relies on generating AI drafts for clinician review, yet this workflow has achieved limited effect.

The objective of this study is to evaluate whether ChatGPT models can reliably apply the DISCERN instrument, a 16-question human-scored rubric developed in 1999 to evaluate consumer health information, and assess the impact of prompting strategies, model choice, and scoring repeatability on agreement with human-derived DISCERN scores.

Clinical decision support (CDS) tools are designed to streamline workflows and enhance care quality in pediatric intensive care units (PICUs). Prior research has largely focused on interruptive, or active, CDS, leaving little known about the usage of passive CDS (pCDS) tools such as note writing support, order sets, and laboratory result flagging across institutions.

The objective of this study is to characterize pediatric resident documentation time using electronic health record (EHR) audit-log-data and to assess interindividual variability in documentation patterns.

Despite widespread investment in patient engagement technologies-such as mobile apps, chatbots, and remote monitoring tools-few have achieved sustained adoption or integration into clinical workflows. The persistent gap between pilot success and real-world scalability reflects not only technical barriers but also sociotechnical challenges involving people, processes, and policy.

Clinical informatics (CI) fellowship programs for physicians in the United States are growing with over 60 Accreditation Council for Graduate Medical Education-accredited fellowship programs. As a young clinical subspecialty, many have questions about the field; in addition, fellowship eligibility and structure vary significantly. Physicians apply for CI fellowships through Electronic Residency Application Service and the American Medical Informatics Association (AMIA) Match. Fellowship websites are essential resources for prospective applicants to [...]

Patient portals, as extensions of electronic health records (EHRs), play a critical role in providing patients with access to diagnoses, test results, and clinical communication. Despite their potential benefits, portals often inherit usability issues from EHRs, which can make information difficult to navigate or interpret, and errors can compromise patient safety and affect clinical decision-making.

Poor documentation quality can significantly affect health care operations, but the feedback process for clinicians to improve clinical notes is time-consuming and often insufficient. Large language models (LLMs) such as Generative Pre-trained Transformer 4 (GPT-4) have the potential to streamline this process.

Digital health physical activity (PA) programs have shown promise for improving the health and wellness of family caregivers (FCGs). However, their use among older adult caregivers remains underexplored. To address this gap, we developed TPA4You, a tailored digital health PA program that integrates videoconferencing with a health coach, a fitness tracker, and motivational messaging. The program is designed to support older caregivers, a population whose health and self-care needs are [...]

This study evaluates the performance of multiple large language models (LLMs) on specialized otolaryngology knowledge, comparing OpenAI's GPT-4 Turbo with 10 commercially available models to assess their potential utility in otolaryngology medical education.A total of 1,075 questions from OTO QUEST, the official self-assessment resource of the American Academy of Otolaryngology-Head and Neck Surgery, were administered to GPT-4 Turbo using a zero-shot approach. Accuracy was analyzed using logistic regression, adjusting for [...]