Back to Search Start Over

Matching patients to clinical trials with large language models.

Authors :
Jin Q
Wang Z
Floudas CS
Chen F
Gong C
Bracken-Clarke D
Xue E
Yang Y
Sun J
Lu Z
Source :
Nature communications [Nat Commun] 2024 Nov 18; Vol. 15 (1), pp. 9074. Date of Electronic Publication: 2024 Nov 18.
Publication Year :
2024

Abstract

Patient recruitment is challenging for clinical trials. We introduce TrialGPT, an end-to-end framework for zero-shot patient-to-trial matching with large language models. TrialGPT comprises three modules: it first performs large-scale filtering to retrieve candidate trials (TrialGPT-Retrieval); then predicts criterion-level patient eligibility (TrialGPT-Matching); and finally generates trial-level scores (TrialGPT-Ranking). We evaluate TrialGPT on three cohorts of 183 synthetic patients with over 75,000 trial annotations. TrialGPT-Retrieval can recall over 90% of relevant trials using less than 6% of the initial collection. Manual evaluations on 1015 patient-criterion pairs show that TrialGPT-Matching achieves an accuracy of 87.3% with faithful explanations, close to the expert performance. The TrialGPT-Ranking scores are highly correlated with human judgments and outperform the best-competing models by 43.8% in ranking and excluding trials. Furthermore, our user study reveals that TrialGPT can reduce the screening time by 42.6% in patient recruitment. Overall, these results have demonstrated promising opportunities for patient-to-trial matching with TrialGPT.<br />Competing Interests: Competing interests The authors declare no competing interests.<br /> (© 2024. This is a U.S. Government work and not under copyright protection in the US; foreign copyright protection may apply.)

Details

Language :
English
ISSN :
2041-1723
Volume :
15
Issue :
1
Database :
MEDLINE
Journal :
Nature communications
Publication Type :
Academic Journal
Accession number :
39557832
Full Text :
https://doi.org/10.1038/s41467-024-53081-z