Risk models based on non-cognitive measures may identify presymptomatic Alzheimer’s disease

Abstract

ABSTRACTBackgroundAlzheimer’s disease is a progressive disorder without a cure. Developing risk prediction models for detecting presymptomatic Alzheimer’s disease using non-cognitive measures is necessary to enable early interventions.ObjectiveExamine if non-cognitive metrics alone can be used to construct risk models to identify adults at risk for Alzheimer’s dementia and cognitive impairment.MethodsClinical data from older adults without dementia from the Memory and Aging Project (MAP, n=1179) and Religious Orders Study (ROS, n=1103) were analyzed using Cox proportional hazard models to develop risk prediction models for Alzheimer’s dementia and cognitive impairment. Models using only non-cognitive covariates were compared to models that added cognitive covariates. All models were trained in MAP, tested in ROS, and evaluated by the AUC of ROC curve.ResultsModels based on non-cognitive covariates alone achieved AUC (0.800,0.785) for predicting Alzheimer’s dementia (3,5) years from baseline. Including additional cognitive covariates improved AUC to (0.916,0.881). A model with a single covariate of composite cognition score achieved AUC (0.905,0.863). Models based on non-cognitive covariates alone achieved AUC (0.717,0.714) for predicting cognitive impairment (3,5) years from baseline. Including additional cognitive covariates improved AUC to (0.783,0.770). A model with a single covariate of composite cognition score achieved AUC (0.754,0.730).ConclusionRisk models based on non-cognitive metrics predict both Alzheimer’s dementia and cognitive impairment. However, non-cognitive covariates do not provide incremental predictivity for models that include cognitive metrics in predicting Alzheimer’s dementia, but do in models predicting cognitive impairment. Further improved risk prediction models for cognitive impairment are needed.