1
|
Zhao X, Zhang J, Gong Y, Xu L, Liu H, Wei S, Wu Y, Cha G, Wei H, Mao J, Xia L. Reliable Detection of Myocardial Ischemia Using Machine Learning Based on Temporal-Spatial Characteristics of Electrocardiogram and Vectorcardiogram. Front Physiol 2022; 13:854191. [PMID: 35707012 PMCID: PMC9192098 DOI: 10.3389/fphys.2022.854191] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2022] [Accepted: 04/12/2022] [Indexed: 11/15/2022] Open
Abstract
Background: Myocardial ischemia is a common early symptom of cardiovascular disease (CVD). Reliable detection of myocardial ischemia using computer-aided analysis of electrocardiograms (ECG) provides an 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 in 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 were extracted from 377 patients with myocardial ischemia and 52 healthy controls. Then, sample entropy (SampEn, of 12 ECG leads and of three 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 (S I , THI, and SHI, where S I is the SampEn of lead I) are further selected for the ECG + VCG model. 5-fold cross validation was used to assess the performance of ECG-only, VCG-only, and ECG + VCG models. 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 with three features (S I ,THI, and SHI) yields better classifying results than ECG-only and VCG-only models with the average accuracy of 0.903, sensitivity of 0.903, specificity of 0.905, F1 score of 0.942, and AUC of 0.904, which shows better performance with fewer features compared with existing works. On the third independent dataset, the testing showed an AUC of 0.814. Conclusion: The SVM algorithm based on the ECG + VCG model could reliably detect myocardial ischemia, providing a potential tool to assist cardiologists in the early diagnosis of CVD in routine screening during primary care services.
Collapse
Affiliation(s)
- Xiaoye Zhao
- School of Instrument Science and Opto-Electronic Engineering, Hefei University of Technology, Hefei, China
- School of Electrical and Information Engineering, North Minzu University, Yinchuan, China
- Key Laboratory of Atmospheric Environment Remote Sensing of Ningxia, Yinchuan, China
| | - Jucheng Zhang
- Department of Clinical Engineering, The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China
| | - Yinglan Gong
- Hangzhou Maixin Technology Co., Ltd., Hangzhou, China
- Institute of Wenzhou, Zhejiang University, Wenzhou, China
| | - Lihua Xu
- Hangzhou Linghua Biotech Ltd., Hangzhou, China
| | - Haipeng Liu
- Research Centre for Intelligent Healthcare, Coventry University, Coventry, United Kingdom
| | - Shujun Wei
- Department of Cardiology, Ningxia Hui Autonomous Region People’s Hospital, Yinchuan, China
| | - Yuan Wu
- Department of Cardiology, Ningxia Hui Autonomous Region People’s Hospital, Yinchuan, China
| | - Ganhua Cha
- School of Electrical and Information Engineering, North Minzu University, Yinchuan, China
| | - Haicheng Wei
- School of Electrical and Information Engineering, North Minzu University, Yinchuan, China
| | - Jiandong Mao
- School of Instrument Science and Opto-Electronic Engineering, Hefei University of Technology, Hefei, China
- School of Electrical and Information Engineering, North Minzu University, Yinchuan, China
- Key Laboratory of Atmospheric Environment Remote Sensing of Ningxia, Yinchuan, China
| | - Ling Xia
- Key Laboratory for Biomedical Engineering of Ministry of Education, Institute of Biomedical Engineering, Zhejiang University, Hangzhou, China
| |
Collapse
|
2
|
Chandraratna PAN, Mohar DS, Sidarous PF, Brar P, Miller J, Shah N, Kadis J, Ali A, Mohar P. Evaluation of non-ST segment elevation acute chest pain syndromes with a novel low-profile continuous imaging ultrasound transducer. Echocardiography 2012; 29:895-9. [PMID: 22591210 DOI: 10.1111/j.1540-8175.2012.01709.x] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022] Open
Abstract
BACKGROUND This investigation was designed to test the hypothesis that continuous cardiac imaging using an ultrasound transducer developed in our laboratory (ContiScan) is superior to electrocardiogram (ECG) monitoring in the diagnosis of coronary artery disease (CAD) in patients with acute non-ST segment elevation chest pain syndromes. METHODS Seventy patients with intermediate to high probability of CAD who presented with typical anginal chest pain and no evidence of ST segment elevation on the ECG were studied. The 2.5-MHz transducer is spherical in its distal part mounted in an external housing to permit steering in 360 degrees. The transducer was placed at the left sternal border to image the left ventricular short-axis view and recorded on video tape at baseline, during and after episodes of chest pain. Two ECG leads were continuously monitored. The presence of CAD was confirmed by coronary arteriography or nuclear or echocardiographic stress testing. RESULTS Twenty-four patients had regional wall motion abnormalities (RWMA) on their initial echo which were unchanged during the period of monitoring. All had evidence of CAD. Twenty-eight patients had transient RWMA. All had evidence of CAD. Eighteen patients had normal wall motion throughout the monitoring period, 14 of these had no evidence of CAD, and four had evidence of CAD. These four patients did not have chest pain during monitoring. The sensitivity, specificity, and accuracy of echocardiographic monitoring for diagnosing non-ST elevation myocardial infarction was 88%, 100%, and 91% respectively. The sensitivity, specificity, and accuracy of the ECG for diagnosis of CAD were 31%, 100%, and 52%, respectively. Echocardiography was superior to ECG (P < 0.001). CONCLUSIONS The data indicate that continuous cardiac imaging is superior to ECG monitoring for the diagnosis of CAD in patients presenting with acute non-ST segment elevation chest pain syndromes. This technique could be a useful adjunct to ECG monitoring for myocardial ischemia in the acute care setting.
Collapse
Affiliation(s)
- P Anthony N Chandraratna
- Division of Cardiology, Long Beach VA Medical Center, UC Irvine School of Medicine, Irvine, California, USA.
| | | | | | | | | | | | | | | | | |
Collapse
|
3
|
Ottander P, Nilsson JB, Jensen SM, Näslund U. Ischemic ST-segment episodes during the initial 24 hours of ST elevation myocardial infarction predict prognosis at 1 and 5 years. J Electrocardiol 2010; 43:224-9. [DOI: 10.1016/j.jelectrocard.2009.12.010] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2009] [Indexed: 11/24/2022]
|
4
|
Haney MF, Häggmark S, Johansson G, Näslund U. ST changes and temporal relation to the J point during heart rate increase and myocardial ischemia. J Electrocardiol 2008; 42:6-11. [PMID: 18976774 DOI: 10.1016/j.jelectrocard.2008.08.039] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/20/2008] [Indexed: 10/21/2022]
Abstract
There is no concensus concerning where in the ST segment to measure. We studied the relation between different J point intervals to ST results during tachycardia and ischemia. Symptomatic (anesthetized) patients with coronary artery disease were paced at ascending incremental levels until they became ischemic. ST vector magnitude and ST vector change from baseline (STC-VM) as well as the sum of ST changes from all 12 electrocardiogram (ECG) leads (ECG ST sum) were measured at J point 0 millisecond, J + 20, J + 60, and J + 80 milliseconds for 34 patients. ST segments increased in similar fashion during pacing and ischemia. There was no difference in ST results when measurement was performed at different time intervals for both STC-VM and ECG ST sum. We conclude that ST assessment by ST change from baseline is not affected by different J point intervals during increased heart rate and ischemia in this clinical model of pacing-induced ischemia and vectorcardiographic ST analysis.
Collapse
Affiliation(s)
- Michael F Haney
- Anesthesiology and Intensive Care Medicine, University Hospital, Umeå, Sweden.
| | | | | | | |
Collapse
|
5
|
Bibliography. Current world literature. Diseases of the aorta, pulmonary, and peripheral vessels. Curr Opin Cardiol 2008; 23:646-7. [PMID: 18830082 DOI: 10.1097/hco.0b013e328316c259] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|