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

Sahithi Ankireddy, Purvi Sehgal, Adam Wierman
Proceedings of the Fifth Machine Learning for Health Symposium, PMLR 297:1609-1618, 2026.

Abstract

We present ClinPath, a holistic multimodal framework that combines knowledge graph modeling with large language model ({LLM}) reasoning to comprehensively represent 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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v297-ankireddy26a, title = {{ClinPath}: A General-Purpose Knowledge Graph with {LLM} Reasoning For Understanding Clinical Interactions}, author = {Ankireddy, Sahithi and Sehgal, Purvi and Wierman, Adam}, booktitle = {Proceedings of the Fifth Machine Learning for Health Symposium}, pages = {1609--1618}, year = {2026}, editor = {Argaw, Peniel and Zhang, Haoran and Jabbour, Sarah and Chandak, Payal and Ji, Jerry and Mukherjee, Sumit and Salaudeen, Olawale and Chang, Trenton and Healey, Elizabeth and Gröger, Fabian and Adibi, Amin and Hegselmann, Stefan and Wild, Benjamin and Noori, Ayush}, volume = {297}, series = {Proceedings of Machine Learning Research}, month = {13--14 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v297/main/assets/ankireddy26a/ankireddy26a.pdf}, url = {https://proceedings.mlr.press/v297/ankireddy26a.html}, abstract = {We present ClinPath, a holistic multimodal framework that combines knowledge graph modeling with large language model ({LLM}) reasoning to comprehensively represent 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.} }
Endnote
%0 Conference Paper %T ClinPath: A General-Purpose Knowledge Graph with LLM Reasoning For Understanding Clinical Interactions %A Sahithi Ankireddy %A Purvi Sehgal %A Adam Wierman %B Proceedings of the Fifth Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2026 %E Peniel Argaw %E Haoran Zhang %E Sarah Jabbour %E Payal Chandak %E Jerry Ji %E Sumit Mukherjee %E Olawale Salaudeen %E Trenton Chang %E Elizabeth Healey %E Fabian Gröger %E Amin Adibi %E Stefan Hegselmann %E Benjamin Wild %E Ayush Noori %F pmlr-v297-ankireddy26a %I PMLR %P 1609--1618 %U https://proceedings.mlr.press/v297/ankireddy26a.html %V 297 %X We present ClinPath, a holistic multimodal framework that combines knowledge graph modeling with large language model ({LLM}) reasoning to comprehensively represent 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.
APA
Ankireddy, S., Sehgal, P. & Wierman, A.. (2026). ClinPath: A General-Purpose Knowledge Graph with LLM Reasoning For Understanding Clinical Interactions. Proceedings of the Fifth Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 297:1609-1618 Available from https://proceedings.mlr.press/v297/ankireddy26a.html.

Related Material