Diagnosis of Left Ventricular Hypertrophy from ECG Signals Based on CCS Methodology using SVM

An electrocardiogram (ECG) is the easiest and most reliable way to understand Left Ventricular Hypertrophy (LVH), which leads to many other cardiovascular diseases at the initial stage. However, LVH can develop silently over several years without any symptoms, and it is not easy to diagnose LVH even with renowned methods and many other proposed theoretical approaches because of its interrelated nature. Utilizing ECG/EKG data availability, the authors have proposed a classifier using Support Vector Machine (SVM). Here the SVM classifier is a re-fabrication of the Combine Cornell-Sokolow (CCS) methodology, and the classifier has the effectiveness of over 90% detecting LVH in complex cases. Training variation constructs different models with various accuracies, but balance training can achieve quite admissible results. The paper will delineate the training procedure and discuss the findings in it. The study will also have concerned about EGC signal pre-processing, data processing, and feature detection in its path. Any electronic diagnosis system can utilize this research’s classifier to distinguish LVH among complex cases. The classifier can identify LVH cases continuously because of its computation manner, even where an expert physician is unavailable.