Academic Journal

Answering real-world clinical questions using large language model, retrieval-augmented generation, and agentic systems

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Answering real-world clinical questions using large language model, retrieval-augmented generation, and agentic systems
Συγγραφείς: Yen Sia Low, Michael L Jackson, Rebecca J Hyde, Robert E Brown, Neil M Sanghavi, Julian D Baldwin, C William Pike, Jananee Muralidharan, Gavin Hui, Natasha Alexander, Hadeel Hassan, Rahul V Nene, Morgan Pike, Courtney J Pokrzywa, Shivam Vedak, Adam Paul Yan, Dong-han Yao, Amy R Zipursky, Christina Dinh, Philip Ballentine, Dan C Derieg, Vladimir Polony, Rehan N Chawdry, Jordan Davies, Brigham B Hyde, Nigam H Shah, Saurabh Gombar
Πηγή: Digit Health
Digital Health, Vol 11 (2025)
Στοιχεία εκδότη: SAGE Publications, 2025.
Έτος έκδοσης: 2025
Θεματικοί όροι: Computer applications to medicine. Medical informatics, R858-859.7, Original Research Article
Περιγραφή: Objective The practice of evidence-based medicine can be challenging when relevant data are lacking or difficult to contextualize for a specific patient. Large language models (LLMs) could potentially address both challenges by summarizing published literature or generating new studies using real-world data. Materials and Methods We submitted 50 clinical questions to five LLM-based systems: OpenEvidence, which uses an LLM for retrieval-augmented generation (RAG); ChatRWD, which uses an LLM as an interface to a data extraction and analysis pipeline; and three general-purpose LLMs (ChatGPT-4, Claude 3 Opus, Gemini 1.5 Pro). Nine independent physicians evaluated the answers for relevance, quality of supporting evidence, and actionability (i.e., sufficient to justify or change clinical practice). Results General-purpose LLMs rarely produced relevant, evidence-based answers (2–10% of questions). In contrast, RAG-based and agentic LLM systems, respectively, produced relevant, evidence-based answers for 24% (OpenEvidence) to 58% (ChatRWD) of questions. OpenEvidence produced actionable results for 48% of questions with existing evidence, compared to 37% for ChatRWD and Discussion Special-purpose LLM systems greatly outperformed general-purpose LLMs in producing answers to clinical questions. Retrieval-augmented generation-based LLM (OpenEvidence) performed well when existing data were available, while only the agentic ChatRWD was able to provide actionable answers when preexisting studies were lacking. Conclusion Synergistic systems combining RAG-based evidence summarization and agentic generation of novel evidence could improve the availability of pertinent evidence for patient care.
Τύπος εγγράφου: Article
Other literature type
Γλώσσα: English
ISSN: 2055-2076
DOI: 10.1177/20552076251348850
Σύνδεσμος πρόσβασης: https://doaj.org/article/e32cc1f79b9645f3899c1190f2646bf0
Rights: URL: https://journals.sagepub.com/page/policies/text-and-data-mining-license
URL: http://creativecommons.org/licenses/by-nc-nd/4.0/This article is distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 License (http://creativecommons.org/licenses/by-nc-nd/4.0/) which permits non-commercial use, reproduction and distribution of the work as published without adaptation or alteration, without further permission provided the original work is attributed as specified on the SAGE and Open Access page (http://us.sagepub.com/en-us/nam/open-access-at-sage).
Αριθμός Καταχώρησης: edsair.doi.dedup.....8686bcd51a9a499d7a4b763945ca835c
Βάση Δεδομένων: OpenAIRE
Περιγραφή
ISSN:20552076
DOI:10.1177/20552076251348850