A Proof-of-Concept for Explainable Disease Diagnosis Using Large Language Models and Answer Set Programming

TL;DR

This paper presents McCoy, a framework combining Large Language Models and Answer Set Programming to create an interpretable, knowledge-based disease diagnosis system that leverages medical literature and patient data.

Contribution

Introduces McCoy, a novel system integrating LLMs with ASP for explainable disease diagnosis, reducing knowledge base construction effort.

Findings

Strong performance on small-scale diagnosis tasks

Effective translation of medical literature into ASP code

Robust, interpretable prediction framework

Abstract

Accurate disease prediction is vital for timely intervention, effective treatment, and reducing medical complications. While symbolic AI has been applied in healthcare, its adoption remains limited due to the effort required for constructing high-quality knowledge bases. This work introduces McCoy, a framework that combines Large Language Models (LLMs) with Answer Set Programming (ASP) to overcome this barrier. McCoy orchestrates an LLM to translate medical literature into ASP code, combines it with patient data, and processes it using an ASP solver to arrive at the final diagnosis. This integration yields a robust, interpretable prediction framework that leverages the strengths of both paradigms. Preliminary results show McCoy has strong performance on small-scale disease diagnosis tasks.