Search AMIA.org

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.

Medical coding structures health-care data for research, quality monitoring, and policy. This study assesses the potential of large language models (LLMs) to assign International Classification of Primary Care, 2nd edition (ICPC-2) codes using the output of a domain-specific search engine.

Identifying patients at high risk for atrial fibrillation (AF) after cryptogenic stroke remains a challenge, particularly in settings with limited access to long-term cardiac monitoring. The AFibrisk platform, a free digital decision-support tool, integrates 19 validated AF prediction scores to support post-stroke triage. We aimed to assess the concordance of AFibrisk-supported classification decisions with expert electrophysiologist consensus and compare performance across evaluator groups with different levels of clinical experience.

To develop and validate machine learning (ML) models that predict probable cause of death (CoD) using structured electronic health record (EHR) data, unstructured clinical notes, and publicly available sources.

The expansion of artificial intelligence (AI)-enabled clinical decision support (CDS) requires nurses to interpret complex model outputs. However, their cognitive readiness remains underexplored, particularly in terms of their understanding of statistics. To assess nurses' understanding of key statistical concepts underlying AI predictions and their relationship to health numeracy.