Autonomous Myocardial Infarction Detection from Electrocardiogram with a Multi Label Classification Approach

Vishwa Mohan Singh, Vibhor Saran, Pooja Kadambi
Proceedings of The 14th Asian Conference on Machine Learning, PMLR 189:911-926, 2023.

Abstract

Myocardial Infarctions (MI) or heart attacks are among the most common medical emergencies globally. Such an episode often has mild or varied symptoms, making it hard to diagnose and respond in a timely manner. An electrocardiogram (ECG) is used to analyze the heart’s electrical activity and, through this help, clinicians detect and localize a heart attack. However, interpretation of the ECG is made manually by trained professionals. In order to make this diagnosis more efficient, multiple methods have tried to automate the MI detection and localization process. In this work, we aim to create a more effective method of MI detection by restructuring the localization as a multi-label classification (MLC) problem, in which one set of attributes can belong to one or more classes. For this classification, features like the ST-deviation, T wave amplitude, and R-S ratios have been extracted and fed into the MLC model, which in our case, is a chain classifier of random forest. This proposed model will have five classes as the target, which represent the locations where an MI can occur. Our method achieves the best overall hamming accuracy of 81.49% in a k-fold cross validation test, with the highest accuracy for an individual class being 97.72% for anterior.

Cite this Paper

BibTeX
@InProceedings{pmlr-v189-singh23a, title = {Autonomous Myocardial Infarction Detection from Electrocardiogram with a Multi Label Classification Approach}, author = {Singh, Vishwa Mohan and Saran, Vibhor and Kadambi, Pooja}, booktitle = {Proceedings of The 14th Asian Conference on Machine Learning}, pages = {911--926}, year = {2023}, editor = {Khan, Emtiyaz and Gonen, Mehmet}, volume = {189}, series = {Proceedings of Machine Learning Research}, month = {12--14 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v189/singh23a/singh23a.pdf}, url = {https://proceedings.mlr.press/v189/singh23a.html}, abstract = {Myocardial Infarctions (MI) or heart attacks are among the most common medical emergencies globally. Such an episode often has mild or varied symptoms, making it hard to diagnose and respond in a timely manner. An electrocardiogram (ECG) is used to analyze the heart’s electrical activity and, through this help, clinicians detect and localize a heart attack. However, interpretation of the ECG is made manually by trained professionals. In order to make this diagnosis more efficient, multiple methods have tried to automate the MI detection and localization process. In this work, we aim to create a more effective method of MI detection by restructuring the localization as a multi-label classification (MLC) problem, in which one set of attributes can belong to one or more classes. For this classification, features like the ST-deviation, T wave amplitude, and R-S ratios have been extracted and fed into the MLC model, which in our case, is a chain classifier of random forest. This proposed model will have five classes as the target, which represent the locations where an MI can occur. Our method achieves the best overall hamming accuracy of 81.49% in a k-fold cross validation test, with the highest accuracy for an individual class being 97.72% for anterior.} }
Endnote
%0 Conference Paper %T Autonomous Myocardial Infarction Detection from Electrocardiogram with a Multi Label Classification Approach %A Vishwa Mohan Singh %A Vibhor Saran %A Pooja Kadambi %B Proceedings of The 14th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Emtiyaz Khan %E Mehmet Gonen %F pmlr-v189-singh23a %I PMLR %P 911--926 %U https://proceedings.mlr.press/v189/singh23a.html %V 189 %X Myocardial Infarctions (MI) or heart attacks are among the most common medical emergencies globally. Such an episode often has mild or varied symptoms, making it hard to diagnose and respond in a timely manner. An electrocardiogram (ECG) is used to analyze the heart’s electrical activity and, through this help, clinicians detect and localize a heart attack. However, interpretation of the ECG is made manually by trained professionals. In order to make this diagnosis more efficient, multiple methods have tried to automate the MI detection and localization process. In this work, we aim to create a more effective method of MI detection by restructuring the localization as a multi-label classification (MLC) problem, in which one set of attributes can belong to one or more classes. For this classification, features like the ST-deviation, T wave amplitude, and R-S ratios have been extracted and fed into the MLC model, which in our case, is a chain classifier of random forest. This proposed model will have five classes as the target, which represent the locations where an MI can occur. Our method achieves the best overall hamming accuracy of 81.49% in a k-fold cross validation test, with the highest accuracy for an individual class being 97.72% for anterior.
APA
Singh, V.M., Saran, V. & Kadambi, P.. (2023). Autonomous Myocardial Infarction Detection from Electrocardiogram with a Multi Label Classification Approach. Proceedings of The 14th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 189:911-926 Available from https://proceedings.mlr.press/v189/singh23a.html.

Related Material