Deep Convolution Neural Network-Based Classification and Diagnosis of Heart Disease using ElectroCardioGram (ECG) Images

A cardiovascular disease, if identified correctly at an early stage, could reduce the critical consequences in patients , including fatality. One of the best diagnostic tool for detecting heart disease is through an ECG test. Models trained using signal data related to ECG is difficult to be implemented in an actual healthcare scenario. A CNN model is proposed which makes use of 12-lead ECG images to diagnose cardiac conditions such as myocardial infarction, abnormal heart beat, history of myocardial infarction and normal heartbeat. The ECG image can be taken by scanning the image using a smart phone. This would be very helpful in small healthcare centers where there are no experts for diagnosis. The proposed model was efficiently trained with an accuracy of 99% and cardiac condition was diagnosed using ECG images scanned using a mobile with a superior performance. The work also compares the performance of model with pretrained models as ResNet and EfficientNet-B0 for the same ECG image dataset.