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

By sjmartinez • June 13, 2025

Low YS, Jackson ML, Hyde RJ, Brown RE, Sanghavi NM, Baldwin JD, Pike CW, Muralidharan J, Hui G, Alexander N, Hassan H, Nene RV, Pike M, Pokrzywa CJ, Vedak S, Yan AP, Yao DH, Zipursky AR, Dinh C, Ballentine P, Derieg DC, Polony V, Chawdry RN, Davies J, Hyde BB, Shah NH, Gombar S. Answering real-world clinical questions using large language model, retrieval-augmented generation, and agentic systems. Digit Health. 2025 Jun 9;11:20552076251348850. doi: 10.1177/20552076251348850. PMID: 40510193; PMCID: PMC12159471.

Tags: Artificial intelligence, Cohort study, evidence-based medicine, Fellow, Hematology/Oncology, Large language models, Publications, retrieval-augmented generation

irAE-GPT: leveraging large language models to identify immune-related adverse events in electronic health records and clinical trial datasets

Bejan CA, Wang M, Venkateswaran S, Bergmann EA, Hiles L, Xu Y, Chandler GS, Brondfield S, Silverstein J, Wright F, de Dios K, Kim DM,[...]

Toward the simultaneous detection of multiple diseases with a highly cost-effective cell-free DNA methylome test

Zeng W, Liu CC, Li S, Zhou Y, Stackpole ML, Xiao Y, Hu R, Tang C, Liu Q, Zeng W, Yeh A, Melehy A, Tran[...]

Utilizing natural language processing (NLP) to identify breast cancer-associated lung metastases from pathology reports to delineate characteristics of this site of recurrence

López JCV, Ho A, Hughes KS, Bardia A, Vidula N. Utilizing natural language processing (NLP) to identify breast cancer-associated lung metastases from pathology reports to[...]