TabulaTime: A Novel Multimodal Deep Learning Framework for Advancing Acute Coronary Syndrome Prediction through Environmental and Clinical Data Integration

2025-02-24

AI Summary

Early prediction of acute coronary syndrome (ACS) is hindered by conventional clinical risk scores’ neglect of environmental risk factors and their inability to effectively integrate heterogeneous temporal data. To address this, we propose the first clinical–environmental bimodal deep learning framework. Our approach introduces the PatchRWKV module—designed to efficiently model dynamic temporal associations between air pollution exposures (e.g., PM₁₀, NO₂) and clinical indicators (e.g., systolic blood pressure, prior angina)—and incorporates a cross-modal attention mechanism to enable interpretable risk attribution. By aligning and jointly learning representations from both clinical and environmental time-series data, our model achieves over 20% improvement in prediction accuracy over strong baselines (e.g., CatBoost) on real-world data; notably, air pollution features alone contribute >10% performance gain. This work establishes a novel paradigm for environmental–health risk modeling.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Acute Coronary Syndromes (ACS), including ST-segment elevation myocardial infarctions (STEMI) and non-ST-segment elevation myocardial infarctions (NSTEMI), remain a leading cause of mortality worldwide. Traditional cardiovascular risk scores rely primarily on clinical data, often overlooking environmental influences like air pollution that significantly impact heart health. Moreover, integrating complex time-series environmental data with clinical records is challenging. We introduce TabulaTime, a multimodal deep learning framework that enhances ACS risk prediction by combining clinical risk factors with air pollution data. TabulaTime features three key innovations: First, it integrates time-series air pollution data with clinical tabular data to improve prediction accuracy. Second, its PatchRWKV module automatically extracts complex temporal patterns, overcoming limitations of traditional feature engineering while maintaining linear computational complexity. Third, attention mechanisms enhance interpretability by revealing interactions between clinical and environmental factors. Experimental results show that TabulaTime improves prediction accuracy by over 20% compared to conventional models such as CatBoost, Random Forest, and LightGBM, with air pollution data alone contributing over a 10% improvement. Feature importance analysis identifies critical predictors including previous angina, systolic blood pressure, PM10, and NO2. Overall, TabulaTime bridges clinical and environmental insights, supporting personalized prevention strategies and informing public health policies to mitigate ACS risk.

Problem

• Enhances ACS risk prediction
• Integrates environmental and clinical data
• Improves prediction accuracy by 20%

Innovation

• Integrates time-series air pollution data
• Uses PatchRWKV for temporal pattern extraction
• Employs attention mechanisms for interpretability