Integrating Automated Knowledge Extraction with Large Language Models for Explainable Medical Decision-Making
Haodi Zhang, Jiahong Li, Yi‐Chi Wang, Yuanfeng Song
Abstract
Large language models (LLMs) have demonstrated strong reasoning ability and inspired many previously unimaginable applications. In this paper, we aim to harness the strong reasoning capability of LLMs toward explainable medical diagnosis. As we know, deep learning has been widely adopted and shown improvement in medical diagnostics. However, it is often criticized for its lack of interpretability. To address this drawback, we propose the first method that innovatively combines Markov logic networks (MLNs) with external knowledge extracted using LLMs, aiming for improved both interpretability and accuracy. Specifically, our approach involves a new process, powered by LLMs and a search engine, to automatically collect and organize external medical knowledge. The outcome is a set of first-order logic (FOL) rules, which then become a key component for the following MLN-based diagnostic algorithm. The resulting MLN-based model can maintain the accuracy of deep networks while providing understandable reasoning for its decisions. By aiming to blend specific knowledge from the medical domain with LLM techniques, our work contributes towards the development of improved automatic diagnosis systems, with the potential for enhancing transparency and trust in medical diagnostics.