Deep Learning based Automatic Heart Disease Detection using ECG Signals

For medical and clinical applications automated electrocardiogram (ECG) diagnosis may bevery useful aid. We had implemented a deep learning approach in building a system for automaticclassification and detection of ECG signals for processing. To detect cardiovascular disease in ECGsignals we acquired expertise in convolutional neural network (CNN) by using a training data set of259,789 ECG signals accumulated from cardiac function rooms in tertiary care hospital with facilities.Database provided availability of more than 4000 ECG signal samples taken from various outpatient ECGexaminations gathered through 47 subjects 22 females and 25 males. For normal class confusion matrixprocessed out from testing dataset showed 99 accuracy. In ―atrial premature beat‖ class, ECG sampleswere accurately grouped 100 of time. Lastly, for ―premature ventricular contraction‖ class, ECGsegments was correctly segregated 96 of time. Totally, we found an average accuracy in classificationof about 98.33. Specificity (SPC) and sensitivity (SNS) was found to be 98.35 and 98.33 respectively.A novel concept dependent on deep learning and, particularly on a CNN network ensures outstandingbehaviour in automated recognition hence helping in prevention of cardiovascular diseases and in somecases pre detection so as to take necessary preventive steps.