Self-Explaining Hypergraph Neural Networks for Diagnosis Prediction

TL;DR

This paper introduces SHy, a hypergraph neural network that provides personalized, concise, and faithful explanations for diagnosis prediction from EHR data, capturing complex disease interactions and addressing data incompleteness.

Contribution

The paper presents a novel self-explaining hypergraph neural network model that enhances interpretability and predictive accuracy in healthcare diagnosis prediction tasks.

Findings

SHy outperforms existing models in predictive accuracy.

SHy offers more flexible and succinct explanations.

The model effectively handles incomplete EHR data.

Abstract

The burgeoning volume of electronic health records (EHRs) has enabled deep learning models to excel in predictive healthcare. However, for high-stakes applications such as diagnosis prediction, model interpretability remains paramount. Existing deep learning diagnosis prediction models with intrinsic interpretability often assign attention weights to every past diagnosis or hospital visit, providing explanations lacking flexibility and succinctness. In this paper, we introduce SHy, a self-explaining hypergraph neural network model, designed to offer personalized, concise and faithful explanations that allow for interventions from clinical experts. By modeling each patient as a unique hypergraph and employing a message-passing mechanism, SHy captures higher-order disease interactions and extracts distinct temporal phenotypes as personalized explanations. It also addresses the incompleteness of the EHR data by accounting for essential false negatives in the original diagnosis record. A qualitative case study and extensive quantitative evaluations on two real-world EHR datasets demonstrate the superior predictive performance and interpretability of SHy over existing state-of-the-art models.