Diagnostic and prognostic value of ECG-predicted hypertension-mediated left ventricular hypertrophy using machine learning

Abstract

Objective: Four hypertension-mediated left ventricular hypertrophy (LVH) phenotypes have been reported using cardiac magnetic resonance (CMR): normal LV, LV remodelling, eccentric and concentric LVH, with varying prognostic implications. The electrocardiogram (ECG) is routinely used to detect LVH; however, its capacity to differentiate between LVH phenotypes is unknown. This study aimed to classify hypertension-mediated LVH from the ECG using machine learning and test for associations of ECG-predicted phenotypes with incident cardiovascular outcomes.

Methods: ECG biomarkers were extracted from the 12-lead ECG of 20 439 hypertensive patients in UK Biobank (UKB). Classification models integrating ECG and clinical variables were built using logistic regression, support vector machine (SVM), and random forest. The models were trained in 80% of the participants, and the remaining 20% formed the test set. External validation was sought in 877 hypertensive participants from the Study of Health in Pomerania (SHIP). In the UKB test set, we tested for associations between ECG-predicted LVH phenotypes and incident major adverse cardiovascular events (MACE) and heart failure.

Results: Among UKB participants 19 408 had normal LV, 758 LV remodelling, 181 eccentric and 92 concentric LVH. Classification performance of the three models was comparable in UKB. SVM (accuracy 0.79, sensitivity 0.59, specificity 0.87, AUC 0.69) was taken forward for external validation with similar results in SHIP. There was superior prediction of eccentric LVH in both cohorts. In the UKB test set, ECG-predicted eccentric LVH was associated with heart failure (hazard ratio 3.42, 95% CI 1.06-9.86).

Conclusion: ECG-based ML classifiers represent a potentially accessible screening strategy for the early detection of hypertension-mediated LVH phenotypes.

Keywords: electrocardiogram; hypertension; left ventricular hypertrophy; machine learning.

FIGURE 1

Flow diagram illustrating the steps involved in UK Biobank participant selection. CMR, cardiac magnetic resonance imaging; HCM, hypertrophic cardiomyopathy; LV, left ventricle; LVH, left ventricular hypertrophy.

FIGURE 2

Ranking of the top 40 features using chi-squared feature selection.

FIGURE 3

(a) Classification of hypertension mediated left ventricular hypertrophy phenotypes in UK Biobank and Study of Health in Pomerania using support vector machine. (b) Classification of hypertension mediated LVH phenotypes using ECG and clinical vs. clinical data alone in UK Biobank and Study of Health in Pomerania with support vector machine. ECG, electrocardiogram; LV, left ventricle; LVH, left ventricular hypertrophy.

FIGURE 4

Associations of ECG-predicted hypertension-mediated left ventricular hypertrophy phenotypes and clinical outcomes. Results are hazard ratios from Cox hazards proportional regression models. The diseases listed are set as the model outcome (response variable) and hypertension-mediated LV phenotype in the exposure of interest with normal LV as the reference group. The model was adjusted for age, sex and BMI. CI, confidence interval; HR, hazard ratio; LVH, left ventricular hypertrophy; MACE, major adverse cardiovascular events.