Autonomous Analysis of Curated Patient Data Using a Large Language Model–Based Multiagent Framework
JCO Clinical Cancer Informatics · 2025
DOI: 10.1200/cci-25-00176 ↗Kurz gefasst
Fachartikel in der Zeitschrift JCO Clinical Cancer Informatics, 2025. Verfasst von Jiasheng Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: Division of Hematology, Department of Medicine, The Ohio State University Comprehensive Cancer Center, Columbus, OH. Hauptthemen laut MEDLINE: Artificial Intelligence, Data Curation. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 14 Literaturangaben.
Abstract (Originalsprache)
PURPOSE Analyzing complex medical data sets is specialized and time-consuming. This study aimed to develop and evaluate a novel multiagent artificial intelligence (AI) framework for automating medical data analysis workflows and to compare its performance against nonagent-based approaches using large language models (LLMs). METHODS A six-party AI agent system was developed using the AutoGen platform, with specialized agents for planning, data retrieval, cleaning, statistical analysis, and review, powered by OpenAI gpt-4o. This framework was applied to deidentified single patient-level data sets from 20 recent studies in the field of bone marrow transplantation (2021-2023). The primary objective was to evaluate its accuracy in replicating published primary outcomes, benchmarked against direct use of the Web site–based ChatGPT 4o. RESULTS The multiagent framework successfully replicated 53.3% (95% CI, 40.7 to 66.0) of primary outcomes, significantly outperforming ChatGPT 4o (35.0% [95% CI, 22.9 to 47.1]; P = .04). The agent framework's failures were predominantly due to data transformation issues (46.4%) and analysis code errors (21.4%). In contrast, ChatGPT 4o failures largely stemmed from incorrect statistical method application (38.4%) and data transformation (45.6%), often attempting to resolve code errors by switching to alternative, incorrect statistical methods. Hallucinations of variables or results were not observed in the multiagent approach. CONCLUSION Our multiagent AI framework demonstrated superior accuracy and robustness in automating biomedical data analysis compared with a generalized LLM.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Division of Hematology, Department of Medicine, The Ohio State University Comprehensive Cancer Center, Columbus, OH.
- Tampa General Hospital Cancer Institute, Tampa, FL.
- Department of Medical Oncology, Sidney Kimmel Cancer Center, Thomas Jefferson University, Philadelphia, PA.
ORCID-Profile: Jiasheng Wang, David M Swoboda, Aziz Nazha
Zitieren
APA
Wang, J., Swoboda, D. M., & Nazha, A. (2025). Autonomous Analysis of Curated Patient Data Using a Large Language Model–Based Multiagent Framework. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-25-00176
Vancouver
Wang J, Swoboda DM, Nazha A. Autonomous Analysis of Curated Patient Data Using a Large Language Model–Based Multiagent Framework. JCO Clinical Cancer Informatics. 2025. doi:10.1200/cci-25-00176
BibTeX
@article{Wang2025,
author = {Wang, Jiasheng and Swoboda, David M and Nazha, Aziz},
title = {Autonomous Analysis of Curated Patient Data Using a Large Language Model–Based Multiagent Framework},
journal = {JCO Clinical Cancer Informatics},
year = {2025},
doi = {10.1200/cci-25-00176}
}
EUVIMED