Explainable detection of myocardial infarction using deep learning models with Grad-CAM technique on ECG signals

V Jahmunah; E Y K Ng; Ru-San Tan; Shu Lih Oh; U Rajendra Acharya

doi:10.1016/j.compbiomed.2022.105550

Explainable detection of myocardial infarction using deep learning models with Grad-CAM technique on ECG signals

Comput Biol Med. 2022 Jul:146:105550. doi: 10.1016/j.compbiomed.2022.105550. Epub 2022 Apr 25.

Authors

V Jahmunah¹, E Y K Ng¹, Ru-San Tan², Shu Lih Oh³, U Rajendra Acharya⁴

Affiliations

¹ Department of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore.
² National Heart Centre Singapore, Singapore; Duke-NUS Medical School, Singapore.
³ School of Engineering, Ngee Ann Polytechnic, Singapore.
⁴ School of Engineering, Ngee Ann Polytechnic, Singapore; Biomedical Engineering, School of Social Science and Technology, Singapore University of Social Sciences, Singapore; International Research Organization for Advanced Science and Technology (IROAST), Kumamoto University, Kumamoto, Japan; Department Bioinformatics and Medical Engineering, Asia University, Taiwan; School of Management and Enterprise, University of Southern Queensland, Australia. Electronic address: aru@np.edu.sg.

PMID: 35533457
DOI: 10.1016/j.compbiomed.2022.105550

Abstract

Myocardial infarction (MI) accounts for a high number of deaths globally. In acute MI, accurate electrocardiography (ECG) is important for timely diagnosis and intervention in the emergency setting. Machine learning is increasingly being explored for automated computer-aided ECG diagnosis of cardiovascular diseases. In this study, we have developed DenseNet and CNN models for the classification of healthy subjects and patients with ten classes of MI based on the location of myocardial involvement. ECG signals from the Physikalisch-Technische Bundesanstalt database were pre-processed, and the ECG beats were extracted using an R peak detection algorithm. The beats were then fed to the two models separately. While both models attained high classification accuracies (more than 95%), DenseNet is the preferred model for the classification task due to its low computational complexity and higher classification accuracy than the CNN model due to feature reusability. An enhanced class activation mapping (CAM) technique called Grad-CAM was subsequently applied to the outputs of both models to enable visualization of the specific ECG leads and portions of ECG waves that were most influential for the predictive decisions made by the models for the 11 classes. It was observed that Lead V4 was the most activated lead in both the DenseNet and CNN models. Furthermore, this study has also established the different leads and parts of the signal that get activated for each class. This is the first study to report features that influenced the classification decisions of deep models for multiclass classification of MI and healthy ECGs. Hence this study is crucial and contributes significantly to the medical field as with some level of visible explainability of the inner workings of the models, the developed DenseNet and CNN models may garner needed clinical acceptance and have the potential to be implemented for ECG triage of MI diagnosis in hospitals and remote out-of-hospital settings.

Keywords: Deep learning; DenseNet model; Explainable artificial intelligence; Grad-CAM; Myocardial infarction.

MeSH terms

Algorithms
Deep Learning*
Diagnosis, Computer-Assisted
Electrocardiography / methods
Humans
Myocardial Infarction* / diagnosis