The precision of current models restricts the use of automatic electrocardiogram (ECG) analysis in clinical practice. There is a high hope for how ML+AI technology, might enhance clinical practice. Here, we build a Neural Network-based model that will be developed using MIT Benchmark data and others to study a newly generated data from Pittsburgh hospital on Cardiac Arrhythmias disease. The novely of the model/platform will focus on new feature engineering that can improve the classification to a maximum accuracy. Are we going to outperforms cardiology resident doctors in identifying six different types of abnormalities in 12-lead ECG recordings?