Personalized Knowledge-based Graph Neural Networks and Regression Analysis for Computational Diagnosis of High-Risk Cardiovascular Disease Patients
Abstract
Acute myocardial infarction (MI) is a major precursor to heart failure (HF), yet few biomarkers are routinely used to predict post-MI HF, and limited therapeutic options exist to prevent its development. Furthermore, identifying patients at extremely high risk of recurrent MI remains challenging. These gaps highlight the need for improved biomarkers, therapeutic targets, and computational approaches for risk assessment and treatment-response prediction. To address risk assessment, we developed a systems bioinformatics (SB), graph-based framework representing patient information as personalized networks and integrating omics, clinical, and molecular prior-knowledge data. Graph neural network (GNN) machine learning (ML) models were compared with conventional ML approaches. Two large-scale public plasma proteomic datasets were used to predict post-MI HF. To investigate treatment response, regression models were applied to longitudinal clinical data from >400 hospitalized patients enrolled in the EMMY trial evaluating empagliflozin. ML-driven feature selection identified proteins and clinical parameters with the greatest predictive value. The graph-based framework demonstrated strong and consistent performance across independent post-MI cohorts. GNN models outperformed conventional approaches, including generalized linear models and XGBoost, particularly when attention mechanisms were incorporated. Using biomarker panels alone, the best GNN achieved an external test AUC of 0.82,…
Read the paper
Related studies
- Strategy for Mitigating DKA Risk in Patients with Type 1 Diabetes on Adjunctive Treatment with SGLT Inhibitors: A STICH Protocol
- Glucoraphanin: a broccoli sprout extract that ameliorates obesity-induced inflammation and insulin resistance
- SGLT2 Inhibitors in Heart Failure: Targeted Metabolomics and Energetic Metabolism
- Mechanisms of blood pressure reduction with sodium-glucose co-transporter 2 (SGLT2) inhibitors
- Sodium-glucose cotransporter inhibitors: beyond glycaemic control
- Decoding the effects of SGLT2 inhibitors on cardiac arrhythmias in heart failure
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.