Predicting Cognitive Impairment and Dementia: A Machine Learning Approach

Background: Efforts to identify important risk factors for cognitive impairment and dementia have to date mostly relied on meta-analytic strategies. A comprehensive empirical evaluation of these risk factors within a single study is currently lacking. Objective: We used a combined methodology of machine learning and semi-parametric survival analysis to estimate the relative importance of 52 predictors in forecasting cognitive impairment and dementia in a large, population-representative sample of older adults. Methods: Participants from the Health and Retirement Study (N = 9,979; aged 50-98 years) were followed for up to 10 years (M = 6.85 for cognitive impairment; M = 7.67 for dementia). Using a split-sample methodology, we first estimated the relative importance of predictors using machine learning (random forest survival analysis), and we then used semi-parametric survival analysis (Cox proportional hazards) to estimate effect sizes for the most important variables. Results: African Americans and individuals who scored high on emotional distress were at relatively highest risk for developing cognitive impairment and dementia. Sociodemographic (lower education, Hispanic ethnicity) and health variables (worse subjective health, increasing BMI) were comparatively strong predictors for cognitive impairment. Cardiovascular factors (e.g., smoking, physical inactivity) and polygenic scores (with and without APOE epsilon 4) appeared less important than expected. Post-hoc sensitivity analyses underscored the robustness of these results. Conclusions: Higher-order factors (e.g., emotional distress, subjective health), which reflect complex interactions between various aspects of an individual, were more important than narrowly defined factors (e.g., clinical and behavioral indicators) when evaluated concurrently to predict cognitive impairment and dementia.