Online Disease Self-diagnosis with Inductive Heterogeneous Graph Convolutional Networks [article]

Zifeng Wang and Rui Wen and Xi Chen and Shilei Cao and Shao-Lun Huang and Buyue Qian and Yefeng Zheng
2020 arXiv   pre-print
We propose a Healthcare Graph Convolutional Network (HealGCN) to offer disease self-diagnosis service for online users, based on the Electronic Healthcare Records (EHRs). Two main challenges are focused in this paper for online disease self-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
more » ... teractions 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, resulting in better reasoning ability of our HealGCN model, when confronting users with scarce descriptions. At last, we validate our model on a large-scale EHR dataset, the superior performance does confirm our model's effectiveness in practice.
arXiv:2009.02625v1 fatcat:hjuajp3je5gpln7xju6vl3g3ui