Abstract
INTRODUCTION: The clinical utility of dementia prognostic scores has limited validity across diverse populations. This study aimed to enhance the Cardiovascular Risk Factors, Aging and Dementia (CAIDE) model by incorporating resting heart rate (RHR) using a machine learning method across a diverse population. METHODS: We developed CAIDE and CAIDE-RHR models using a random forest algorithm in the National Alzheimer's Coordinating Center (NACC) dataset. Model performances were assessed using area under the receiver-operating characteristic curve (AUC), Matthew's correlation coefficient (MCC), and the Brier score. RESULTS: Incorporating RHR into the CAIDE model significantly improved predictive accuracy across Black African, Asian, White, and Native Hawaiian populations (mean AUC range: 0.80-0.91). However, this improvement was not observed in the American Indian population, where the AUC decreased from 0.87 to 0.84. DISCUSSION: Our findings highlight significant ethnic differences in dementia risk prediction models. These results underscore the need for validating and tailoring dementia risk scores to ensure applicability across diverse races. HIGHLIGHTS: Incorporating resting heart rate (RHR) into the Cardiovascular Risk Factors, Aging, and Dementia (CAIDE) model significantly improves its predictive accuracy for dementia risk across diverse populations, offering a novel addition to dementia risk models. The application of the machine learning technique enhances dementia risk prediction by capturing complex, non-linear relationships among variables. The improved model enables more precise early identification of individuals at risk of cognitive decline, supporting preventive strategies in dementia care. Resting heart rate, a simple and non-invasive cardiovascular measure, is demonstrated to be a valuable predictor for dementia risk, making it practical for clinical application.