AI approaches for predicting progression to acute coronary syndrome among stable coronary heart disease patients
Haozhong Ma1,2, Hexiang Bai1,2, Jiahuan Yan2
1State Key Laboratory of Transvascular Implantation Devices and the Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China.
Insights
This study introduces an AI model using electronic health records to predict acute coronary syndrome (ACS) transitions in patients with coronary heart disease (CHD). The AI approach shows high accuracy for early ACS detection, improving patient outcomes.
Area of Science:
- Artificial Intelligence in Medicine
- Cardiovascular Disease Research
- Health Informatics
Background:
- Coronary heart disease (CHD) and acute coronary syndrome (ACS) are major global health concerns.
- Current diagnostic methods for ACS are often invasive, expensive, and time-consuming.
- Early detection of ACS is crucial for reducing mortality and morbidity.
Purpose of the Study:
- To develop and validate an AI-driven approach for early detection of transitions from stable CHD to ACS.
- To utilize electronic health records (EHR) for identifying high-risk patients.
- To enhance clinical decision support for ACS management.
Main Methods:
- Development of a T2G-Former model utilizing a large dataset of 12,336 patient records from 131 medical institutions.
- Application of the model to predict ACS development within a 12-month timeframe.
- Utilizing SHAP values for model interpretability and identification of key clinical predictors.
Main Results:
- The T2G-Former model achieved a high area under the curve (AUC) of 0.953.
- The model demonstrated a sensitivity of 0.814 in predicting ACS on the test set.
- SHAP analysis provided insights into the clinical variables contributing to ACS prediction.
Conclusions:
- AI-enabled analysis of EHR data offers a scalable solution for early ACS detection.
- The developed model shows significant potential for improving clinical decision-making in CHD management.
- This approach can help mitigate the global burden of cardiovascular disease through timely interventions.
Abstract:
Coronary heart disease (CHD), including its acute manifestation, acute coronary syndrome (ACS), remains a leading cause of morbidity and mortality worldwide. Early identification of ACS is critical for reducing the global burden of CHD, yet traditional diagnostic methods are often invasive, costly, and time consuming. In this study, we introduce an AI-driven approach that utilizes electronic health records (EHR) to identify transitions from stable CHD to ACS, using a comprehensive dataset of 12,336 patient records from 131 medical institutions in Jiangsu Province, China. The proposed model, applying the T2G-Former to predict ACS in 12 months, demonstrated superior performance, with an area under the curve of 0.953 and a sensitivity of 0.814 on the test set. Model interpretability was supported by SHAP values, which clarified the contribution of individual clinical variables. Our findings highlight the potential of AI-enabled EHR analysis for scalable early ACS detection and clinical decision support.
More Related Videos
Related Concept Videos
01:27Coronary Artery Disease V: Interprofessional Care
01:30Acute Coronary Syndrome I: Introduction
01:19Acute Coronary Syndrome II: Pathophysiology and Clinical Manifestations
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:28Acute Coronary Syndrome IV: Interprofessional Care
01:26Acute Coronary Syndrome V: Nursing Management