Leveraging Generative AI for Clinical Evidence Synthesis Needs to Ensure Trustworthiness

Overview

Journal J Biomed Inform

Publisher Elsevier

Specialty Medical Informatics

Date 2024 Apr 12

PMID 38608915

Authors

Gongbo Zhang

Qiao Jin

Denis Jered McInerney

Yong Chen

Fei Wang

Curtis L Cole

Qian Yang

Yanshan Wang

Bradley A Malin

Mor Peleg

Byron C Wallace

Zhiyong Lu

Chunhua Weng

Yifan Peng

Affiliations

Soon will be listed here.

Abstract

Evidence-based medicine promises to improve the quality of healthcare by empowering medical decisions and practices with the best available evidence. The rapid growth of medical evidence, which can be obtained from various sources, poses a challenge in collecting, appraising, and synthesizing the evidential information. Recent advancements in generative AI, exemplified by large language models, hold promise in facilitating the arduous task. However, developing accountable, fair, and inclusive models remains a complicated undertaking. In this perspective, we discuss the trustworthiness of generative AI in the context of automated summarization of medical evidence.

Citing Articles

Evaluating a large language model's ability to answer clinicians' requests for evidence summaries.

Blasingame M, Koonce T, Williams A, Giuse D, Su J, Krump P J Med Libr Assoc. 2025; 113(1):65-77.

PMID: 39975503 PMC: 11835037. DOI: 10.5195/jmla.2025.1985.

Semi-supervised learning from small annotated data and large unlabeled data for fine-grained Participants, Intervention, Comparison, and Outcomes entity recognition.

Chen F, Zhang G, Fang Y, Peng Y, Weng C J Am Med Inform Assoc. 2025; 32(3):555-565.

PMID: 39823371 PMC: 11833487. DOI: 10.1093/jamia/ocae326.

Demystifying Large Language Models for Medicine: A Primer.

Jin Q, Wan N, Leaman R, Tian S, Wang Z, Yang Y ArXiv. 2025; .

PMID: 39801619 PMC: 11722506.

The doctor will polygraph you now.

Anibal J, Gunkel J, Awan S, Huth H, Nguyen H, Le T Unknown. 2025; 1(1):1.

PMID: 39759269 PMC: 11698301. DOI: 10.1038/s44401-024-00001-4.

Exploring prospects, hurdles, and road ahead for generative artificial intelligence in orthopedic education and training.

Gupta N, Khatri K, Malik Y, Lakhani A, Kanwal A, Aggarwal S BMC Med Educ. 2024; 24(1):1544.

PMID: 39732679 PMC: 11681633. DOI: 10.1186/s12909-024-06592-8.

References

Bromme R, Mede N, Thomm E, Kremer B, Ziegler R . An anchor in troubled times: Trust in science before and within the COVID-19 pandemic. PLoS One. 2022; 17(2):e0262823. PMC: 8827432. DOI: 10.1371/journal.pone.0262823. View

Chen Z, Liu H, Liao S, Bernard M, Kang T, Stewart L . Representation and Normalization of Complex Interventions for Evidence Computing. Stud Health Technol Inform. 2022; 290:592-596. DOI: 10.3233/SHTI220146. View

Chang T, Sjoding M, Wiens J . Disparate Censorship & Undertesting: A Source of Label Bias in Clinical Machine Learning. Proc Mach Learn Res. 2023; 182:343-390. PMC: 10162497. View

Turfah A, Liu H, Stewart L, Kang T, Weng C . Extending PICO with Observation Normalization for Evidence Computing. Stud Health Technol Inform. 2022; 290:268-272. DOI: 10.3233/SHTI220076. View

Gershman B, Guo D, Dahabreh I . Using observational data for personalized medicine when clinical trial evidence is limited. Fertil Steril. 2018; 109(6):946-951. DOI: 10.1016/j.fertnstert.2018.04.005. View

Levy M, Pauzner M, Rosenblum S, Peleg M . Achieving trust in health-behavior-change artificial intelligence apps (HBC-AIApp) development: A multi-perspective guide. J Biomed Inform. 2023; 143:104414. DOI: 10.1016/j.jbi.2023.104414. View

Savovic J, Jones H, Altman D, Harris R, Juni P, Pildal J . Influence of reported study design characteristics on intervention effect estimates from randomized, controlled trials. Ann Intern Med. 2012; 157(6):429-38. DOI: 10.7326/0003-4819-157-6-201209180-00537. View

Schuemie M, Hripcsak G, Ryan P, Madigan D, Suchard M . Empirical confidence interval calibration for population-level effect estimation studies in observational healthcare data. Proc Natl Acad Sci U S A. 2018; 115(11):2571-2577. PMC: 5856503. DOI: 10.1073/pnas.1708282114. View

Kang T, Turfah A, Kim J, Perotte A, Weng C . A neuro-symbolic method for understanding free-text medical evidence. J Am Med Inform Assoc. 2021; 28(8):1703-1711. PMC: 8135980. DOI: 10.1093/jamia/ocab077. View

10.

Li P, Jiang X, Zhang G, Trelles Trabucco J, Raciti D, Smith C . Corrigendum to: Utilizing image and caption information for biomedical document classification. Bioinformatics. 2021; 37(19):3389. PMC: 8504622. DOI: 10.1093/bioinformatics/btab568. View

11.

Singhal K, Azizi S, Tu T, Mahdavi S, Wei J, Chung H . Large language models encode clinical knowledge. Nature. 2023; 620(7972):172-180. PMC: 10396962. DOI: 10.1038/s41586-023-06291-2. View

12.

Jin Q, Yang Y, Chen Q, Lu Z . GeneGPT: augmenting large language models with domain tools for improved access to biomedical information. Bioinformatics. 2024; 40(2). PMC: 10904143. DOI: 10.1093/bioinformatics/btae075. View

13.

Singhal K, Azizi S, Tu T, Mahdavi S, Wei J, Chung H . Publisher Correction: Large language models encode clinical knowledge. Nature. 2023; 620(7973):E19. PMC: 10412443. DOI: 10.1038/s41586-023-06455-0. View

14.

Obermeyer Z, Powers B, Vogeli C, Mullainathan S . Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019; 366(6464):447-453. DOI: 10.1126/science.aax2342. View

15.

Poulain R, Tarek M, Beheshti R . Improving Fairness in AI Models on Electronic Health Records: The Case for Federated Learning Methods. FAccT 23 (2023). 2023; 2023:1599-1608. PMC: 10661580. DOI: 10.1145/3593013.3594102. View

16.

Tian S, Jin Q, Yeganova L, Lai P, Zhu Q, Chen X . Opportunities and challenges for ChatGPT and large language models in biomedicine and health. Brief Bioinform. 2024; 25(1). PMC: 10762511. DOI: 10.1093/bib/bbad493. View

17.

Ramprasad S, Marshall I, McInerney D, Wallace B . Automatically Summarizing Evidence from Clinical Trials: A Prototype Highlighting Current Challenges. Proc Conf Assoc Comput Linguist Meet. 2023; 2023:236-247. PMC: 10361334. View

18.

Carlisle J . False individual patient data and zombie randomised controlled trials submitted to Anaesthesia. Anaesthesia. 2020; 76(4):472-479. DOI: 10.1111/anae.15263. View

19.

Tang L, Sun Z, Idnay B, Nestor J, Soroush A, Elias P . Evaluating large language models on medical evidence summarization. NPJ Digit Med. 2023; 6(1):158. PMC: 10449915. DOI: 10.1038/s41746-023-00896-7. View

20.

Peng Y, Rousseau J, Shortliffe E, Weng C . AI-generated text may have a role in evidence-based medicine. Nat Med. 2023; 29(7):1593-1594. PMC: 11193148. DOI: 10.1038/s41591-023-02366-9. View