Leveraging generative AI for clinical evidence synthesis needs to ensure trustworthiness

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

doi:10.1016/j.jbi.2024.104640

Leveraging generative AI for clinical evidence synthesis needs to ensure trustworthiness

J Biomed Inform. 2024 May:153:104640. doi: 10.1016/j.jbi.2024.104640. Epub 2024 Apr 10.

Authors

Gongbo Zhang¹, Qiao Jin², Denis Jered McInerney³, Yong Chen⁴, Fei Wang⁵, Curtis L Cole⁶, Qian Yang⁷, Yanshan Wang⁸, Bradley A Malin⁹, Mor Peleg¹⁰, Byron C Wallace³, Zhiyong Lu², Chunhua Weng¹¹, Yifan Peng¹²

Affiliations

¹ Columbia University, Department of Biomedical Informatics, New York, 10032, USA.
² National Institutes of Health, National Library of Medicine, National Center for Biotechnology Information, Bethesda, 20894, USA.
³ Northeastern University, the Khoury College of Computer Sciences, Boston 02115, USA.
⁴ University of Pennsylvania, Department of Biostatistics, Epidemiology and Informatics, Philadelphia 19104, USA.
⁵ Weill Cornell Medicine, Department of Population Health Sciences, New York 10065, USA; Weill Cornell Medicine, Institute of AI for Digital Health, New York 10065, USA.
⁶ Weill Cornell Medicine, Department of Population Health Sciences, New York 10065, USA; Weill Cornell Medicine, Department of Medicine, New York 10065, USA.
⁷ Cornell University, Computing and Information Science, Ithaca 14853, USA.
⁸ University of Pittsburgh, Department of Health Information Management, Pittsburgh 15260, USA.
⁹ Vanderbilt University Medical Center, Department of Biomedical Informatics, Nashville 37203, USA; Vanderbilt University Medical Center, Department of Biostatistics, Nashville 37203, USA; Vanderbilt University, Department of Computer Science, Nashville 37212, USA.
¹⁰ University of Haifa, Department of Information Systems, Haifa 3498838, Israel.
¹¹ Columbia University, Department of Biomedical Informatics, New York, 10032, USA. Electronic address: cw2384@cumc.columbia.edu.
¹² Weill Cornell Medicine, Department of Population Health Sciences, New York 10065, USA. Electronic address: yip4002@med.cornell.edu.

PMID: 38608915
DOI: 10.1016/j.jbi.2024.104640

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.

Keywords: Evidence-based medicine; Large language models; Medical evidence summarization; Trustworthy generative AI.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Artificial Intelligence*
Evidence-Based Medicine*
Humans
Natural Language Processing
Trust