Predicting Stroke and Mortality in Mitral Regurgitation: A Machine Learning Approach

We hypothesized that an interpretable gra-dient boosting machine (GBM) model considering comorbidities, P-wave and echocardiographic meas-urements, can better predict mortality and cerebro-vascular events in mitral regurgitation (MR). Patients from a tertiary center were analyzed. The GBM model was used as an interpretable statistical approach to identify the leading indicators of high-risk patients with either outcome of CVAs and all-cause mortality. A total of 706 patients were included. GBM analysis showed that age, systolic blood pressure, diastolic blood pressure, plasma albumin levels, mean P-wave duration (PWD), MR regurgitant volume, left ventric-ular ejection fraction (LVEF), left atrial dimension at end-systole (LADs), velocity-time integral (VTI) and effective regurgitant orifice were significant predictorsof TIA/stroke. Age, sodium, urea and albumin levels, platelet count, mean PWD, LVEF, LADs, left ventricu-lar dimension at end systole (LVDs) and VTI were sig-nificant predictors of all-cause mortality. The GBM demonstrates the best predictive performance in terms of precision, sensitivity c-statistic and F1-score com-pared to logistic regression, decision tree, random for-est, support vector machine, and artificial neural networks. Gradient boosting model incorporating clin-ical data from different investigative modalities signifi-cantly improves risk prediction performance and identify key indicators for outcome prediction in MR. (Curr Probl Cardiol 2023;48:101464.)

Automated summary

We hypothesized that an interpretable gradient boosting machine (GBM) model considering comorbidities, P-wave and echocardiographic measurements, can better predict mortality and cerebrovascular events in mitral regurgitation (MR).