Machine learning versus classical electrocardiographic criteria for echocardiographic left ventricular hypertrophy in a pre-participation cohort.

BACKGROUND

Classical electrocardiographic (ECG) criteria for left ventricular hypertrophy (LVH) are well studied in older populations and patients with hypertension. Their utility in young pre-participation cohorts is unclear.

AIMS

We aimed to develop machine learning models for detection of echocardiogram-diagnosed LVH from ECG, and compare these models with classical criteria.

METHODS

Between November 2009 and December 2014, pre-participation screening ECG and subsequent echocardiographic data was collected from 17 310 males aged 16 to 23, who reported for medical screening prior to military conscription. A final diagnosis of LVH was made during echocardiography, defined by a left ventricular mass index >115 g/m2. The continuous and threshold forms of classical ECG criteria (Sokolow-Lyon, Romhilt-Estes, Modified Cornell, Cornell Product, and Cornell) were compared against machine learning models (Logistic Regression, GLMNet, Random Forests, Gradient Boosting Machines) using receiver-operating characteristics curve analysis. We also compared the important variables identified by machine learning models with the input variables of classical criteria.

RESULTS

Prevalence of echocardiographic LVH in this population was 0.82% (143/17310). Classical ECG criteria had poor performance in predicting LVH. Machine learning methods achieved superior performance: Logistic Regression (area under the curve [AUC], 0.811; 95% confidence interval [CI], 0.738-0.884), GLMNet (AUC, 0.873; 95% CI, 0.817-0.929), Random Forest (AUC, 0.824; 95% CI, 0.749-0.898), Gradient Boosting Machines (AUC, 0.800; 95% CI, 0.738-0.862).

CONCLUSIONS

Machine learning methods are superior to classical ECG criteria in diagnosing echocardiographic LVH in the context of pre-participation screening.