ClinPath: A General-Purpose Knowledge Graph with LLM Reasoning For Understanding Clinical Interactions

Sahithi Ankireddy, Purvi Sehgal, Adam Wierman

Keywords: Healthcare AI, Knowledge Graphs, Large Language Models, MIMIC-IV, Clinical Interactions, Patient Similarity, Multimodal Data Integration

TL;DR: We present ClinPath, a framework for evaluating clinical interactions using knowledge graph modeling and LLM reasoning

Track: Proceedings

Abstract: We present ClinPath, a holistic multimodal framework that combines knowledge graph modeling with large language model (LLM) reasoning to comprehensively represent and and analyze longitudinal patient clinical journeys. Built on the MIMIC-IV database, ClinPath introduces ClinKG, a large-scale clinical knowledge graph that integrates diagnoses, symptoms, medications, procedures, demographics, and provider interactions into a unified representation of patient care. Unlike prior work that constructs narrow, diagnosis-centered graphs, ClinKG captures the full spectrum of patient–provider interactions across time and care settings. The LLM reasoning layer demonstrates ClinPath’s versatility through two key applications: (1) patient similarity analysis, where this pipeline significantly improved performance on our custom benchmark, ClinPath-SimBench, and (2) provider behavior analysis, a novel downstream task. Together, these results illustrate how combining graph-structured representations with LLM-based reasoning yields clinically meaningful, multi-perspective insights.

General Area: Applications and Practice

Specific Subject Areas: Explainability & Interpretability, Foundation Models

Data And Code Availability: Yes

Ethics Board Approval: No

Entered Conflicts: I confirm the above

Anonymity: I confirm the above

Submission Number: 287