Improving stroke risk prediction in the general population: Common clinical rules, a new multimorbid index and machine learning based algorithms.

Abstract

We investigated stroke risks in a very large prospective cohort of patients with multimorbidity, using two common clinical rules, a clinical multimorbid index and a machine-learning (ML) approach accounting for the complex relationships among variables, including the dynamic nature of changing risk factors. Methods We studied a prospective US cohort of 3435224 patients from medical databases in a 2-year investigation. Stroke outcomes were examined in relationship to diverse multi-morbid conditions, demographic variables and other inputs, with ML accounting for the dynamic nature of changing multimorbidity risk factors, 2 clinical risk scores and a clinical multimorbid index. Results Common clinical risk scores had moderate and comparable c indices with stroke outcomes in the training and external validation samples (validation - CHADS2: c index 0.812; CHA2DS2-VASc: c index 0.809). A clinical multimorbid index had higher discriminant validity values for both the training/external validation samples (validation: c-index 0.850). The machine learning (ML) based algorithms yielded the highest discriminant validity values for the gradient boosting/neural network logistic regression formulations with no significant differences among the ML approaches (validation for logistic regression: c index 0.866). Calibration of the ML based formulation was satisfactory across a wide range of predicted probabilities. Decision curve analysis demonstrated that clinical utility for the ML based formulation was best. Also, ML models and clinical stroke risk scores were more clinically useful than the treat all strategy. Conclusion Complex relationships of various comorbidities uncovered using a ML approach for diverse(and dynamic) multimorbidity changes have major consequences for stroke risk prediction.