Atherosclerosis through Hierarchical Explainable Neural Network Analysis

2025-07-09

AI Summary

In personalized classification of subclinical atherosclerosis, existing methods struggle to simultaneously achieve molecular fingerprint specificity for individuals and consistency with population-level patterns, while inadequately integrating clinical similarity with pathogenic dependencies. Method: We propose ATHENA—a hierarchical graph neural network that fuses clinical and multi-omics data to enable heterogeneous alignment between individual molecular fingerprints and cohort-level structural patterns; it incorporates interpretable AI–driven subnetwork clustering to identify mechanism-informed patient subtypes and jointly models inter-individual variability and population-level regularities. Results: Validated on a cohort of 391 patients, ATHENA achieves a 13% improvement in AUC and a 20% increase in F1-score over baselines, significantly enhancing predictive accuracy for disease progression and supporting clinically actionable decision-making.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Humans and AI: Other Foundations of Human Computation & AI
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

In this work, we study the problem pertaining to personalized classification of subclinical atherosclerosis by developing a hierarchical graph neural network framework to leverage two characteristic modalities of a patient: clinical features within the context of the cohort, and molecular data unique to individual patients. Current graph-based methods for disease classification detect patient-specific molecular fingerprints, but lack consistency and comprehension regarding cohort-wide features, which are an essential requirement for understanding pathogenic phenotypes across diverse atherosclerotic trajectories. Furthermore, understanding patient subtypes often considers clinical feature similarity in isolation, without integration of shared pathogenic interdependencies among patients. To address these challenges, we introduce ATHENA: Atherosclerosis Through Hierarchical Explainable Neural Network Analysis, which constructs a novel hierarchical network representation through integrated modality learning; subsequently, it optimizes learned patient-specific molecular fingerprints that reflect individual omics data, enforcing consistency with cohort-wide patterns. With a primary clinical dataset of 391 patients, we demonstrate that this heterogeneous alignment of clinical features with molecular interaction patterns has significantly boosted subclinical atherosclerosis classification performance across various baselines by up to 13% in area under the receiver operating curve (AUC) and 20% in F1 score. Taken together, ATHENA enables mechanistically-informed patient subtype discovery through explainable AI (XAI)-driven subnetwork clustering; this novel integration framework strengthens personalized intervention strategies, thereby improving the prediction of atherosclerotic disease progression and management of their clinical actionable outcomes.

Problem

• Classify subclinical atherosclerosis using hierarchical neural networks
• Integrate clinical and molecular data for personalized disease classification
• Improve atherosclerosis prediction via explainable AI-driven patient subtypes

Innovation

• Hierarchical graph neural network for patient data
• Integrated modality learning for clinical and molecular data
• Explainable AI-driven subnetwork clustering for patient subtypes