Search AMIA.org

In recent years, there has been an emerging wave of artificial intelligence (AI) and digital tools in healthcare, thereby revolutionizing clinical practice. As health systems are increasingly utilizing these tools as a means to improve clinical and operational performance outcomes, it becomes imperative to train and professionally develop key frontline stakeholders, such as clinicians, in digital health and clinical AI to ensure seamless and responsible adoption within healthcare settings.This paper [...]

Clinical informatics (CI) fellowship training equips physicians to design, implement, and evaluate health information systems in support of patient care. While core curricula emphasize academic health system experiences, fellows may benefit from exposure to industry settings where much health technology innovation originates.This study aimed to characterize the structure, perceived value, and logistical challenges of industry electives among CI fellowship programs and to synthesize best practices for integrating these experiences into [...]

This study aimed to explore the performance of ChatGPT version 4.0 (GPT-4) and Gemini Advanced (Gemini) large language models (LLMs) in addressing common patient questions after gynecology surgery with regards to accuracy, relevance, helpfulness to the average patient, and readability.In this cross-sectional study, the two LLMs were prompted to generate answers to postoperative patient questions after gynecologic surgery. Postoperative patient questions were developed to simulate common patient questions after gynecologic [...]

To explore the relationship between ambulatory physician electronic health record (EHR) use characteristics and proxies for physician efficiency.

To assess the interpretability and acceptance of Shapley values for making artificial intelligence/machine learning (AI/ML) tools more transparent, interpretable, and useful to clinicians.

Traditional clinical trial enrollment relies on manual screening and coordinator-led recruitment, creating scalability barriers in high-volume perioperative environments. This study evaluated whether a fully automated, electronic health record (EHR)-integrated clinical decision support (CDS) system could identify eligible patients and engage clinicians in real time without manual screening or dedicated research staff.

To develop and validate an agent-based Large Language Model (LLM) system for extracting structured data from breast cancer synoptic pathology reports and assess the performance gap between synthetic and real-world validation.

This study evaluates the usefulness of explicit syntactic knowledge, integrated via a neural mechanism, in improving the accuracy of named entity recognition in the domain of biomedical text processing.

[This corrects the article DOI: 10.1093/jamiaopen/ooaf134.].

Electronic health record (EHR) phenotyping often relies on noisy proxy labels, which undermine the reliability of downstream risk prediction. Active learning can reduce annotation costs, but typical heuristics do not directly optimize downstream prediction. Our goal was to develop a framework that directly uses downstream prediction performance as feedback to guide phenotype correction and sample selection under constrained labeling budgets.