This research presents a novel framework that converts unstructured medical case reports into structured time series of clinical events.

• Extracts temporal relationships between medical events from PubMed case reports
• Compares manual extraction with LLM-powered approaches
• Creates structured datasets that enable process tracing, forecasting, and causal reasoning
• Addresses the critical gap between narrative clinical reports and structured temporal data

This innovation matters because it unlocks valuable temporal information hidden in medical narratives, enabling better patient trajectory analysis and potentially improving clinical decision-making without requiring changes to existing documentation practices.

A Large-Language Model Framework for Relative Timeline Extraction from PubMed Case Reports