Search AMIA.org

To develop and apply a reproducible methodology for evaluating generative artificial intelligence (AI) powered systems in health care, addressing the gap between theoretical evaluation frameworks and practical implementation guidance.

This study aimed to systematically evaluate and compare the diagnostic performance of leading large language models (LLMs) in common and complex clinical scenarios, assessing their potential for enhancing clinical reasoning and diagnostic accuracy in authentic clinical decision-making processes.

We used clinical decision support (CDS) to promote compliance with the 21st Century Cures Act's mandate that, with few exceptions, patients be granted timely access to their clinical notes.

We analyzed interoperability-related Real World Testing results to identify whether developers are providing meaningful results with the appropriate context to enable stakeholders to understand the Certified Health IT conformance and interoperability when deployed in production environments.

Little is known about how clinical decision support (CDS) tools can support care teams in changing clinical decisions to account for patients' social risks. We piloted a suite of electronic health record (EHR)-based CDS tools designed to facilitate social risk-informed care decisions to assess how the tools were used in practice and how they could be improved.

The main goal is to develop an automated process for connecting Research Electronic Data Capture (REDCap) instances in a clinical trial network to allow for deidentified transfer of research surveys to cloud computing data commons for discovery.

This work aims to provide a specialized template for integrating diverse study data types with varying sharing restrictions specific to NIH HEAL Initiative chronic pain and substance use research.

We survey clinical document corpora, with a focus on German textual data. Due to rigid data privacy legislation in Germany, these resources, with only few exceptions, are stored in protected clinical data spaces and locked against clinic-external researchers. This situation stands in stark contrast with established workflows in the field of natural language processing, where easy accessibility and reuse of (textual) data collections are common practice. Hence, alternative corpus designs [...]

This work evaluated algorithmic bias in biomarkers classification using electronic pathology reports from female breast cancer cases. Bias was assessed across 5 subgroups: cancer registry, race, Hispanic ethnicity, age at diagnosis, and socioeconomic status.

The objective of the study was to determine, after medication review, the patient risk score threshold that would distinguish between stays with prescriptions triggering pharmacist intervention (PI) and stays with prescriptions not triggering PI.