AUTHOR=Zhao Xiaoye , Zhang Jucheng , Gong Yinglan , Xu Lihua , Liu Haipeng , Wei Shujun , Wu Yuan , Cha Ganhua , Wei Haicheng , Mao Jiandong , Xia Ling 

TITLE=Reliable Detection of Myocardial Ischemia Using Machine Learning Based on Temporal-Spatial Characteristics of Electrocardiogram and Vectorcardiogram

JOURNAL=Frontiers in Physiology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2022.854191

DOI=10.3389/fphys.2022.854191

ISSN=1664-042X

ABSTRACT=Background: Myocardial ischemia is a common early symptom of cardiovascular disease (CVD). Reliable detection of myocardial ischemia using computer-aided analysis of electrocardiogram (ECG) provides important reference for early diagnosis of CVD. The vectorcardiogram (VCG) could improve the performance of ECG-based myocardial ischemia detection by affording temporal-spatial characteristics related to myocardial ischemia and capturing subtle changes of ST-T segment in continuous cardiac cycles. We aim to investigate if the combination of ECG and VCG could improve the performance of machine learning algorithms in automatic myocardial ischemia detection. 
Methods: The ST-T segments of 20-second, 12-lead ECGs and VCGs are extracted from 377 patients with myocardial ischemia and 52 healthy controls. Then, sample entropy (SampEn, of 12 ECG leads, and of 3 VCG leads), spatial heterogeneity index (SHI, of VCG) and temporal heterogeneity index (THI, of VCG) are calculated. Using a grid search, four SampEn and two features are selected as input signal features for ECG-only and VCG-only models based on support vector machine (SVM), respectively. Similarly, three features (SI, THI, and SHI, where SI is the SampEn of lead I) are further selected for the ECG+VCG model. The performances of ECG-only, VCG-only, and ECG+VCG models are evaluated using 5-fold cross validation. To fully evaluate the algorithmic generalization ability, the model with the best performance was selected and tested on a third independent dataset of 148 patients with myocardial ischemia and 52 healthy controls.
Results: The ECG+VCG model employing three features (SI,THI, and SHI) yields better classifying results than ECG-only and VCG-only models with the average accuracy of 0.903, 0.903 sensitivity, 0.905 specificity, 0.942 F1 score, and 0.904 AUC, which shows better performance with fewer features compared with existing works. On the third independent dataset, the testing showed AUC of 0.814.
Conclusion: The SVM algorithm based on ECG+VCG model could reliably detect myocardial ischemia, providing a potential tool to assist cardiologists in early diagnosis of CVD in routine screening during primary care services.