CardioRiskNet: Attention-based CVAE-enabled GCN for Risk Prediction in STEMI

Abstract

Cardiovascular diseases (CVDs) are a major cause of death worldwide, taking almost 18 million lives each year. ST Elevation Myocardial Infarction (STEMI) is one of the highest contributors to the same. The immediate 30-day period post-STEMI is critical in judging long-term patient outcomes. Thus, there is a need for an accurate risk predictor to guide clinical interventions immediately after STEMI. In this paper, we propose CardioRiskNet, a post-STEMI 30-day mortality predictor based on Graph Convolutional Networks, designed to adapt to different populations with the relational nature of graph-based models. To address class imbalance, we propose a data synthesis method for CVD data by introducing a self-attention mechanism in a Conditional Variational Autoencoder. To demonstrate robustness, the model has been tested on three datasets including two publicly available datasets. CardioRiskNet shows better performance compared to the state-of-the-art methods. Posthoc interpretability analysis also suggests that CardioRiskNet offers promising advancements in data-driven risk assessment, providing clinicians with a precise tool for patient management.