Machine learning model for detecting masked hypertension in young adults

Introduction Cardiovascular disease (CVD) remains the leading global cause of mortality, with hypertension (HT) being a significant contributor, responsible for 56% of CVD-related deaths. Masked hypertension (MHT), a condition where patients exhibit normotensive blood pressure (BP) in clinical settings but elevated BP in out-of-clinic measurements, poses an elevated risk for cardiovascular complications and often goes undiagnosed. Current diagnostic methods, such as ambulatory BP monitoring (ABPM) and home BP monitoring (HBPM), have limitations in feasibility and accessibility. Methods This study aimed to address these challenges by leveraging machine learning (ML) models to predict MHT based on clinical data from a single outpatient visit. Utilizing a dataset from the African-PREDICT study, which included comprehensive clinical, biomarker, body composition, and physical activity data from a young, healthy cohort (aged 20–30 years) in South Africa, we developed a predictive framework for MHT detection. Results The ML models demonstrated the potential to enhance early identification and treatment of MHT, reducing reliance on resource-intensive methods like ABPM. Specifically, we found that utilizing a Least Absolute Shrinkage and Selection Operator (LASSO) feature selection method with an extreme gradient boosting model had an accuracy of 0.83 and a ROC AUC score of 0.86 while relying predominantly on four features: systolic blood pressure, body weight, left ventricular mass at systole, and circulating levels of dehydroepiandrosterone sulfate. Discussion This approach could enable targeted interventions, particularly in resource-limited settings, thereby mitigating the progression of MHT and its associated risks. These findings underscore the importance of integrating advanced computational techniques into clinical practice to address global health challenges.