Accessibility settings

This paper is in the following e-collection/theme issue:

Artificial Intelligence (4828) Clinical Information and Decision Making (3749) mHealth for Data Collection and Research (1742) Natural Language Processing (1302) mHealth in a Clinical Setting (1160) New Resources for Medical Education (208) Digital Health Reporting Standards, Quality and Transparency in e-Research (228)

Published on in Vol 28 (2026)

This is a member publication of University College London (Jisc)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/99597, first published .
Two business professionals reviewing financial charts and data on a tablet.

Performance, Failures, and Oversight of a Large Language Model Agent for Clinical Data Analysis: Evaluation Study

Performance, Failures, and Oversight of a Large Language Model Agent for Clinical Data Analysis: Evaluation Study

Authors of this article:

Yilan Wu1 Author Orcid Image ;   Dun Jack Fu1, 2 Author Orcid Image ;   Yukun Zhou1, 2, 3 Author Orcid Image ;   Siegfried K Wagner1, 2 Author Orcid Image ;   Pearse A Keane1, 2 Author Orcid Image
Article Authors Cited by Tweetations Metrics

Altmetric

Altmetric discovers Social Media mentions. Click the ‘See more details’ link for a full report.

Dimensions

Dimensions discovers Citations. Click the ‘details’ link for a full report.

Metrics Since Publication

Download .csv
Daily | Monthly | Annually