Predicting Progression to Clinical Alzheimer's Disease Dementia Using the Random Survival Forest

Background: Assessing the risk of developing clinical Alzheimer's disease (AD) dementia, by machine learning survival analysis approaches, among participants registered in Alzheimer's Disease Centers is important for AD dementia management. Objective: To construct a prediction model for the onset time of clinical AD dementia using the National Alzheimer Coordinating Center (NACC) and the Alzheimer's Disease Neuroimaging Initiative (ADNI) registered cohorts. Methods: A model was constructed using the Random Survival Forest (RSF) approach and internally and externally validated on the NACC cohort and the ADNI cohort. An R package and a Shiny app were provided for accessing the model. Results: We built a predictive model having the six predictors: delayed logical memory score (story recall), CDR (R) Dementia Staging Instrument - Sum of Boxes, general orientation in CDR (R), ability to remember dates and ability to pay bills in the Functional Activities Questionnaire, and patient age. The C indices of the model were 90.82% (SE = 0.71%) and 86.51% (SE = 0.75%) in NACC and ADNI respectively. The time-dependent AUC and accuracy at 48 months were 92.48% (SE = 1.12%) and 88.66% (SE = 1.00%) respectively in NACC, and 90.16% (SE = 1.12%) and 85.00% (SE = 1.14%) respectively in ADNI. Conclusion: The model showed good prediction performance and the six predictors were easy to obtain, cost-effective, and non-invasive. The model could be used to inform clinicians and patients on the probability of developing clinical AD dementia in 4 years with high accuracy.