What question did this study set out to answer?

This research aims to enhance the prediction of Acute Coronary Syndromes by integrating environmental and clinical data through a novel framework.

March 13, 2026Open Access

TabulaTime: Novel multimodal deep learning for Acute Coronary Syndrome prediction through environmental and clinical data integration

Key Result

TabulaTime improved Acute Coronary Syndrome prediction accuracy by 20.5% over CatBoost, with environmental data contributing a further 10.1% gain.

Key Points

This research aims to enhance the prediction of Acute Coronary Syndromes by integrating environmental and clinical data through a novel framework.
Developed the TabulaTime framework for multimodal data integration
Utilized PatchRWKV for temporal feature extraction
Compared prediction accuracy against traditional models including CatBoost, MLP, CNN, RNN, and Transformers
Achieved a 20.5% improvement in prediction accuracy over CatBoost
Environmental data integration contributed an additional 10.1% boost in predictive performance
Identified key clinical and pollution-related predictors through feature analysis

Structured PICO

Does the TabulaTime multimodal deep learning framework improve Acute Coronary Syndrome risk prediction accuracy compared to traditional models?

Population

Patients at risk for Acute Coronary Syndromes (STEMI, NSTEMI)

Intervention

TabulaTime multimodal deep learning framework integrating clinical and environmental time-series data

Comparator

CatBoost and other state-of-the-art models (MLP-, CNN-, RNN- and Transformer-based models)

Outcome

ACS prediction accuracy

A novel multimodal deep learning framework integrating clinical and environmental data significantly improves the accuracy of Acute Coronary Syndrome risk prediction.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Acute Coronary Syndromes (ACS), including ST- and non-ST-segment elevation myocardial infarction (STEMI, NSTEMI), remain a leading cause of global mortality. Traditional Cardiovascular Risk Scores (CVRS) provide important insights but mainly rely on clinical data, often neglecting environmental factors (e.g.air pollution, climate) that significantly influence cardiovascular health. Integrating complex time-series environmental and clinical datasets also presents substantial challenges. We propose TabulaTime, a multimodal deep learning framework integrating clinical risk factors with environmental data to enhance ACS risk prediction. TabulaTime delivers three innovations: multimodal integration of time-series environmental and clinical data; PatchRWKV for extracting complex temporal patterns with linear computational complexity; and enhanced interpretability through attention mechanisms. TabulaTime improves prediction accuracy by 20.5% over CatBoost, with environmental data contributing a 10.1% gain. PatchRWKV outperforms state-of-the-art models (MLP-, CNN-, RNN- and Transformer-based models). Feature analysis highlights key clinical and environmental predictors. This approach advances personalised prevention and strengthens public health against cardiovascular risks. • A novel multimodal deep learning framework, TabulaTime, integrates clinical and environmental time-series data to improve Acute Coronary Syndrome (ACS) risk prediction. • We introduce PatchRWKV, an efficient time-series feature extractor with linear complexity that outperforms state-of-the-art models in capturing temporal patterns. • The integration of environmental data improves ACS prediction accuracy by 10.1%, with feature analysis identifying key clinical and pollution-related predictors.