Inferring Alzheimer’s disease pathologic traits from clinical measures in living adults

BACKGROUND AND OBJECTIVES: Develop imputation models using clinical measures to infer Alzheimer’s disease neuropathologic changes (AD-NC) in living adults to identify adults at risk for Alzheimer’s disease (AD). METHODS: We used clinical and postmortem data of two prospective cohort studies –– Memory and Aging Project (MAP) and Religious Orders Study (ROS). We used generalized linear regression models with Elastic-Net penalty to train imputation models of AD-NC traits (β-Amyloid, tau tangles, global AD pathology, and NIA-Reagan), in MAP decedents using clinical measures collected at last visit as predictors. ROS cohort was used as an independent validation and test data. We validated these models in ROS decedents and applied the models to baseline clinical data of ROS participants to infer baseline AD-NC traits. Baseline clinical data were collected an average of 8 years before last follow-up. We used Cox proportional hazard models to test if inferred baseline AD-NC traits predicted incident AD dementia (ADD). In addition, two-sample t-tests were used to examine if inferred baseline AD-NC traits predicted adults with high risk of pathologic AD profiled at death. RESULTS: By applying imputation models to clinical measures collected at last visit in ROS to validate the imputation models, we obtained predicted R(2) as 0.188 for β-Amyloid, 0.316 for tau tangles, and 0.262 for global AD pathology. Prediction area under the receiver operating characteristic curve (AUC) for the dichotomous NIA-Reagan was 0.765. All four inferred AD-NC traits at last visit strongly discriminated postmortem NIA-Reagan status (p-values < 10(−28)). The inferred baseline levels of all four AD-NC traits predicted ADD, with higher accuracies for predicting ADD in Year 3 (AUC ranging in 0.861 – 0.919) versus Year 5 (AUC 0.842 – 0.896), and the highest accuracy was obtained using inferred NIA-Reagan status. The inferred baseline levels of all four AD-NC traits significantly discriminate individuals with postmortem pathologic AD (all p-values < 1.5 × 10(−7)). CONCLUSIONS: Inferred baseline levels of AD-NC traits derived from clinical measures discriminate adults at risk for ADD and pathologic AD profiled at death. Further studies are needed to determine if repeated measures of inferred AD-NC traits can be used to monitor the accumulation of AD-NC traits during the prolonged course of AD.