Learning and inference in knowledge-based probabilistic model for medical diagnosis

TL;DR

This paper introduces a novel medical diagnosis model combining knowledge graphs and probabilistic networks, utilizing Boltzmann machines and multivariate inference to improve diagnostic accuracy based on electronic medical records.

Contribution

It presents a new methodology for creating a medical knowledge network that integrates weighted knowledge graphs with probabilistic models for diagnosis.

Findings

Optimal disease node quality improves diagnosis accuracy.

The proposed model outperforms logistic regression on CEMR data.

Knowledge graph weights learned from annotated medical records enhance performance.

Abstract

Based on a weighted knowledge graph to represent first-order knowledge and combining it with a probabilistic model, we propose a methodology for the creation of a medical knowledge network (MKN) in medical diagnosis. When a set of symptoms is activated for a specific patient, we can generate a ground medical knowledge network composed of symptom nodes and potential disease nodes. By Incorporating a Boltzmann machine into the potential function of a Markov network, we investigated the joint probability distribution of the MKN. In order to deal with numerical symptoms, a multivariate inference model is presented that uses conditional probability. In addition, the weights for the knowledge graph were efficiently learned from manually annotated Chinese Electronic Medical Records (CEMRs). In our experiments, we found numerically that the optimum choice of the quality of disease node and the expression of symptom variable can improve the effectiveness of medical diagnosis. Our experimental results comparing a Markov logic network and the logistic regression algorithm on an actual CEMR database indicate that our method holds promise and that MKN can facilitate studies of intelligent diagnosis.