Online Disease Self-diagnosis with Inductive Heterogeneous Graph Convolutional Networks

TL;DR

This paper introduces HealGCN, a graph convolutional network designed for online disease self-diagnosis that effectively handles cold-start users and scarce clinical descriptions by leveraging a heterogeneous EHR graph and a symptom retrieval system.

Contribution

The paper presents a novel inductive heterogeneous graph convolutional network and a symptom retrieval system for improved online disease diagnosis using EHR data.

Findings

HealGCN outperforms existing methods on large-scale EHR data.

The symptom retrieval system enhances diagnosis accuracy for users with limited descriptions.

The approach effectively models complex user-symptom-disease interactions.

Abstract

We propose a Healthcare Graph Convolutional Network (HealGCN) to offer disease self-diagnosis service for online users based on Electronic Healthcare Records (EHRs). Two main challenges are focused in this paper for online disease diagnosis: (1) serving cold-start users via graph convolutional networks and (2) handling scarce clinical description via a symptom retrieval system. To this end, we first organize the EHR data into a heterogeneous graph that is capable of modeling complex interactions among users, symptoms and diseases, and tailor the graph representation learning towards disease diagnosis with an inductive learning paradigm. Then, we build a disease self-diagnosis system with a corresponding EHR Graph-based Symptom Retrieval System (GraphRet) that can search and provide a list of relevant alternative symptoms by tracing the predefined meta-paths. GraphRet helps enrich the seed symptom set through the EHR graph when confronting users with scarce descriptions, hence yield better diagnosis accuracy. At last, we validate the superiority of our model on a large-scale EHR dataset.