Ensemble machine learning approach for screening of coronary heart disease based on echocardiography and risk factors

• Published in: BMC medical informatics and decision making Vol. 21; no. 1; pp. 187 - 13
• Main Authors: Zhang, Jingyi, Zhu, Huolan, Chen, Yongkai, Yang, Chenguang, Cheng, Huimin, Li, Yi, Zhong, Wenxuan, Wang, Fang
• Format: Journal Article
• Language: English
• Published: London BioMed Central 11.06.2021; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Blood pressure; Cardiovascular disease; Cardiovascular diseases; Classification; Clinical medicine; Computer-aided medical diagnosis; Coronary artery disease; Coronary Disease - diagnostic imaging; Coronary heart disease; Coronary vessels; Diabetes; Diagnosis; Echocardiography; Electrocardiography; Ensemble learning; Family medical history; Health and safety screening; Health Informatics; Heart; Heart diseases; Humans; Hypertension; Information Systems and Communication Service; Ischemia; Learning algorithms; Machine Learning; Management of Computing and Information Systems; Mass Screening; Medical imaging; Medicine; Medicine & Public Health; Methods; modeling; Obesity; Reproducibility of Results; Research Article; Risk analysis; Risk Factors; Sensitivity analysis; Speckle tracking echocardiography; Stacking; technology; Tracking; Ultrasonic imaging; China; Norway; Speckle tracking echocardiography; Ensemble learning; Coronary heart disease; Machine learning; Classification
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/s12911-021-01535-5

Background Extensive clinical evidence suggests that a preventive screening of coronary heart disease (CHD) at an earlier stage can greatly reduce the mortality rate. We use 64 two-dimensional speckle tracking echocardiography (2D-STE) features and seven clinical features to predict whether one has CHD. Methods We develop a machine learning approach that integrates a number of popular classification methods together by model stacking, and generalize the traditional stacking method to a two-step stacking method to improve the diagnostic performance. Results By borrowing strengths from multiple classification models through the proposed method, we improve the CHD classification accuracy from around 70–87.7% on the testing set. The sensitivity of the proposed method is 0.903 and the specificity is 0.843, with an AUC of 0.904, which is significantly higher than those of the individual classification models. Conclusion Our work lays a foundation for the deployment of speckle tracking echocardiography-based screening tools for coronary heart disease.