PREDICTION OF ABNORMAL LEFT VENTRICULAR GEOMETRY ON THE ECG THROUGH MACHINE LEARNING WITH A FOCUS ON OBESITY

Abstract

Objective: Although electrocardiogram (ECG) is of paramount importance in the initial evaluation of cardiac emodelling, it is not a sensitive method of detecting left ventricular hypertrophy (LVH), and it cannot detect changes in left ventricular geometry (LVG) at early stages. Its sensitivity is particularly low for obese patients. We used a machine learning (ML) classifier to detect abnormal LVG from ECG parameters/markers, even before it becomes LVH and looked at the results of our model for obese patients. Design and method: We enrolled 594 consecutive subjects, aged 30 years or older (mean age: 61.6 ± 12 years old) with and without essential hypertension and no indications of cardiovascular disease. All patients underwent a full echocardiographic evaluation and were classified into 2 groups; those with normal geometry (NG) vs. those with concentric emodelling (CR) or LVH defined as concentric hypertrophy (CH) and eccentric hypertrophy (EH). Abnormal LVG was identified as increased relative wall thickness (RWT) and/or left ventricular mass index (LVMi). We trained a Random Forest machine learning model to classify subjects with abnormal LVG and calculated SHAP values to perform feature importance and interaction. Results: 71.3% of all patients were hypertensive. Hypertension, age, body mass index divided by the Sokolow-Lyon voltage (BMI/S-L), QRS-T angle, and QTc duration were among the most important parameters (Figure 1) identified by the model as being predictive of abnormal LVG (AUC/ROC = 0.84, sensitivity = 0.94, specificity 0.61). Specifically for obese patients, whose prevalence in our population was 60.3%, our model performed well (sensitivity = 0.71, specificity = 0.92. When we tried our model without the the BMI/S-L parameter, the specificity dropped to 0.88. We also found that a cut-off point of 18 kgr/ m2mV for the BMI/S-L marker predicted the patients who were more probable to have developed abnormal LVG. Conclusions: Specific clinical and ECG parameters can predict early pathological changes of LVG in patients without established CVD and detect the population who will benefit from a detailed echocardiographic evaluation. We also proved the hypothesis that ECG parameters can be useful in detecting abnormal LVG in obese patients.