Temporally Phenotyping GLP-1RA Case Reports with Large Language Models: A Textual Time Series Corpus and Risk Modeling
This addresses the challenge of reusing clinical timelines from case reports for longitudinal modeling in diabetes research, representing an incremental application of existing LLMs to a specific domain.
The researchers tackled the problem of extracting clinical timelines from diabetes case reports by creating a textual time-series corpus of 136 case reports and evaluating LLMs for automated timeline extraction, with the best-performing LLM achieving high event coverage (0.871) and temporal sequencing accuracy (0.843). They demonstrated downstream utility by finding lower risk of respiratory sequelae among GLP-1 users versus non-users (HR=0.259, p<0.05).
Type 2 diabetes case reports describe complex clinical courses, but their timelines are often expressed in language that is difficult to reuse in longitudinal modeling. To address this gap, we developed a textual time-series corpus of 136 PubMed Open Access single-patient case reports involving glucagon-like peptide 1 receptor agonists, with clinical events associated with their most probable reference times. We evaluated automated LLM timeline extraction against gold-standard timelines annotated by clinical domain experts, assessing how well systems recovered clinical events and their timings. The best-performing LLM produced high event coverage (GPT5; 0.871) and reliable temporal sequencing across symptoms (GPT5; 0.843), diagnoses, treatments, laboratory tests, and outcomes. As a downstream demonstration, time-to-event analyses in diabetes suggested lower risk of respiratory sequelae among GLP-1 users versus non-users (HR=0.259, p<0.05), consistent with prior reports of improved respiratory outcomes. Temporal annotations and code will be released upon acceptance.