Construct Left Ventricular Hypertrophy Prediction Model Based on Random Forest

Heart disease ranks second in Taiwan’s top ten cause of death in 2016 and the number of deaths in heart disease increases by about 700 people each year. Left ventricular hypertrophy (LVH) has a significant impact on increasing the morbidity of coronary disease and stroke. Therefore, how to improve the accuracy of heart disease diagnosis is urgent. This study suggests a better method that used K-Nearest Neighbor (KNN) to impute missing values of ECG data and Z-score to standardize ECG data for the requirement of the random forest. This study combined the random forest and ECG data to develop an ECG left ventricular hypertrophy classifier. The experimental results show that the accuracy of the prediction model is 66.1%, the sensitivity is 58%, and the specificity is 70.9%.