Online Disease Self-diagnosis with Inductive Heterogeneous Graph Convolutional Networks
This work addresses disease self-diagnosis for online users, offering a practical solution with incremental improvements in handling data scarcity and cold-start scenarios.
The paper tackled the problem of online disease self-diagnosis by proposing HealGCN, a model that uses inductive heterogeneous graph convolutional networks on EHR data to handle cold-start users and scarce symptom descriptions, achieving improved diagnosis accuracy as validated on a large-scale dataset.
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.