Classification of myocardial infarction with multi-lead ECG signals and deep CNN

• Published in: Pattern recognition letters Vol. 122; pp. 23 - 30
• Main Authors: Baloglu, Ulas Baran, Talo, Muhammed, Yildirim, Ozal, Tan, Ru San, Acharya, U Rajendra
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.05.2019; Elsevier Science Ltd
• Subjects: Artificial neural networks; Biomedical signal; Blood; Cardiac muscle; Deep learning; Diagnosis; Echocardiography; EKG; Electrocardiography; Heart; Heart attacks; Intensive care units; Machine learning; Multi-lead ECG; Muscles; Myocardial infarction; Neural networks; Response time; Time lag; Myocardial infarction; Deep learning; Biomedical signal; Multi-lead ECG
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2019.02.016

•An efficient deep learning model for the diagnosis of MI from the standard 12 lead ECG.•The proposed model can successfully distinguish between 10 different MI types.•Experiments with the public physiobank (PTB) ECG database.•Accuracy and sensitivity performance over 99.00% on all lead ECG signals. Myocardial infarction (MI), commonly known as heart attack, causes irreversible damage to heart muscles and even leads to death. Rapid and accurate diagnosis of MI is critical to avoid death. Blood tests and electrocardiogram (ECG) signals are used to diagnose acute MI. However, for an increase in blood enzyme values, a certain time must pass after the attack. This time lag may delay MI diagnosis. Hence, ECG diagnosis is still very important. Manual ECG interpretation requires expertise and is prone to inter-observer variability. Therefore, computer aided diagnosis may be useful in automatic detection of MI on ECG. In this study, a deep learning model with an end-to-end structure on the standard 12-lead ECG signal for the diagnosis of MI is proposed. For this purpose, the most commonly used technique, convolutional neural network (CNN) is used. Our trained CNN model with the proposed architecture yielded impressive accuracy and sensitivity performance over 99.00% for MI diagnosis on all ECG lead signals. Thus, the proposed model has the potential to provide high performance on MI detection which can be used in wearable technologies and intensive care units. [Display omitted]