Over the last decade, AI has shown its feasibility in classifying heart-related diagnoses from ECGs. Earlier studies have mainly focused on 12 and 2-lead ECGs, but we aim to classify 26 different diagnoses based on 12, 6, 4, 3, and2-lead ECGs in this study.
We trained a supervised model on a dataset containing 88 253 ECGs with 26 different diagnoses used as ground truth. The training and classification steps can be separated into three parts. (1) Pan Tompkins algorithm was used to find peaks and calculate the average heart rate. (2) The average heart rate and the Fourier transformed ECG signal was used to train Convolutional Neural Networks (CNN) system that classified the ECGs with regular or irregular rhythms. 9 out of 26 classes were classified in this step. (3) Finally, CNN models in a classifier chain were trained to classify the remaining 17 diagnoses. The classification results from step 2 and the raw ECG signal were used as input to the classifier chain in step 3.
Our team, CardiOUS, achieved a mean PhysioNet Challenge score of 0.49, 0.44, 0.42, 0.45, and 0.44 using the 12,6, 4, 3, and 2-lead model during 10-fold cross-validation (CV) on the development set. Unfortunately, we were not able to score the model on the hidden validation and test set