Key result
A random forest algorithm predicted poor cardiovascular outcomes in hypertensive patients with an AUC of 0.71, identifying longitudinal systolic blood pressure variability as a key predictor.
Why the study?
Does a machine-learning algorithm incorporating systolic blood pressure variability predict poor cardiovascular outcomes in hypertensive patients?
Observational (n=8,799)
Does a machine-learning algorithm incorporating systolic blood pressure variability predict poor cardiovascular outcomes in hypertensive patients?
Effect estimate: AUC 0.71
A random forest algorithm incorporating longitudinal SBP variability and clinical variables achieved an AUC of 0.71 in predicting poor cardiovascular outcomes in hypertensive patients.
No takes yet. Share an insight, caveat, or question.
ML models incorporating SBP variability should not yet guide hypertension care; leaves open prospective validation of predictive utility.
Lacson et al. (2018) conducted an observational in Hypertension (n=8,799). Random forest machine-learning algorithm was evaluated on Poor cardiovascular outcomes (AUC 0.71). A random forest algorithm predicted poor cardiovascular outcomes in hypertensive patients with an AUC of 0.71, identifying longitudinal systolic blood pressure variability as a key predictor.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: