Knowledge Graph Augmented Large Language Models for Next-Visit Disease Prediction
By: Ruiyu Wang , Tuan Vinh , Ran Xu and more
Potential Business Impact:
Helps doctors understand patient health risks better.
Electronic health records (EHRs) support powerful clinical prediction models, but existing methods typically provide coarse, post hoc explanations that offer limited value for patient-level decision making. We introduce a knowledge graph (KG)-guided chain-of-thought (CoT) framework that generates clinically grounded and temporally consistent reasoning for visit-level disease prediction in MIMIC-III. ICD-9 codes are mapped to PrimeKG, from which disease-relevant nodes and multi-hop reasoning paths are extracted and used as scaffolds for CoT generation; only explanations whose conclusions match observed outcomes are retained. Lightweight LLaMA-3.1-Instruct-8B and Gemma-7B models are then fine-tuned on this supervision corpus. Across ten PrimeKG-mapped diseases and limited training cohorts (400 and 1000 cases), KG-guided models outperform strong classical baselines, achieving AUROC values of 0.66 to 0.70 and macro-AUPR values of 0.40 to 0.47. The models also transfer zero-shot to the CRADLE cohort, improving accuracy from approximately 0.40 to 0.51 up to 0.72 to 0.77. A blinded clinician evaluation shows consistent preference for KG-guided CoT explanations in clarity, relevance, and clinical correctness.
Similar Papers
Enhancing Clinical Note Generation with ICD-10, Clinical Ontology Knowledge Graphs, and Chain-of-Thought Prompting Using GPT-4
Computation and Language
Helps doctors write patient notes faster.
Automated Construction of Medical Indicator Knowledge Graphs Using Retrieval Augmented Large Language Models
Artificial Intelligence
Builds smart doctor tools from medical texts.
DKG-LLM : A Framework for Medical Diagnosis and Personalized Treatment Recommendations via Dynamic Knowledge Graph and Large Language Model Integration
Computation and Language
Helps doctors diagnose sickness and pick treatments.