Why do users override alerts? Utilizing large language model to summarize comments and optimize clinical decision support

• Published in: Journal of the American Medical Informatics Association : JAMIA Vol. 31; no. 6; pp. 1388 - 1396
• Main Authors: Liu, Siru, McCoy, Allison B, Wright, Aileen P, Nelson, Scott D, Huang, Sean S, Ahmad, Hasan B, Carro, Sabrina E, Franklin, Jacob, Brogan, James, Wright, Adam
• Format: Journal Article
• Language: English
• Published: England Oxford University Press 20.05.2024
• Subjects: Artificial Intelligence; Decision Support Systems, Clinical; Electronic Health Records; Humans; Medical Order Entry Systems; Natural Language Processing; Research and Applications; alert fatigue; large language model; clinical decision support; health personnel
• DOI: 10.1093/jamia/ocae041
• ISSN: 1067-5027

To evaluate the capability of using generative artificial intelligence (AI) in summarizing alert comments and to determine if the AI-generated summary could be used to improve clinical decision support (CDS) alerts. We extracted user comments to alerts generated from September 1, 2022 to September 1, 2023 at Vanderbilt University Medical Center. For a subset of 8 alerts, comment summaries were generated independently by 2 physicians and then separately by GPT-4. We surveyed 5 CDS experts to rate the human-generated and AI-generated summaries on a scale from 1 (strongly disagree) to 5 (strongly agree) for the 4 metrics: clarity, completeness, accuracy, and usefulness. Five CDS experts participated in the survey. A total of 16 human-generated summaries and 8 AI-generated summaries were assessed. Among the top 8 rated summaries, five were generated by GPT-4. AI-generated summaries demonstrated high levels of clarity, accuracy, and usefulness, similar to the human-generated summaries. Moreover, AI-generated summaries exhibited significantly higher completeness and usefulness compared to the human-generated summaries (AI: 3.4 ± 1.2, human: 2.7 ± 1.2, P = .001). End-user comments provide clinicians' immediate feedback to CDS alerts and can serve as a direct and valuable data resource for improving CDS delivery. Traditionally, these comments may not be considered in the CDS review process due to their unstructured nature, large volume, and the presence of redundant or irrelevant content. Our study demonstrates that GPT-4 is capable of distilling these comments into summaries characterized by high clarity, accuracy, and completeness. AI-generated summaries are equivalent and potentially better than human-generated summaries. These AI-generated summaries could provide CDS experts with a novel means of reviewing user comments to rapidly optimize CDS alerts both online and offline.