Matching patients to clinical trials with large language models

• Published in: Nature communications Vol. 15; no. 1; pp. 9074 - 14
• Main Authors: Jin, Qiao, Wang, Zifeng, Floudas, Charalampos S., Chen, Fangyuan, Gong, Changlin, Bracken-Clarke, Dara, Xue, Elisabetta, Yang, Yifan, Sun, Jimeng, Lu, Zhiyong
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 18.11.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1305; 692/308/2779; 692/700; Algorithms; Annotations; Clinical trials; Clinical Trials as Topic; Criteria; Humanities and Social Sciences; Humans; Language; Large language models; Matching; multidisciplinary; Patient Selection; Ranking; Recruitment; Retrieval; Science; Science (multidisciplinary)
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-024-53081-z

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. Patient recruitment is challenging for clinical trials. Here, the authors introduce TrialGPT, an end-to-end framework for zero-shot patient-to-trial matching with large language models.