Introduction: Sex differences in neuropsychological (NP) test performance might have important implications for the diagnosis of Alzheimer's disease (AD). This study investigates sex differences in neuropsychological performance among individuals without dementia at baseline.
Methods: Neuropsychological assessment data, both standard test scores and process coded responses, from Framingham Heart Study participants were analyzed for sex differences using regression model and Cox proportional hazards model. Optimal NP profiles were identified by machine learning methods for men and women.
Results: Sex differences were observed in both summary scores and composite process scores of NP tests in terms of adjusted means and their associations with AD incidence. The optimal NP profiles for men and women have 10 and 8 measures, respectively, and achieve 0.76 mean area under the curve for AD prediction.
Discussion: These results suggest that NP tests can be leveraged for developing more sensitive, sex-specific indices for the diagnosis of AD.
Keywords: Alzheimer's disease; machine learning; neuropsychological measures; process making; sex differences.
© 2023 The Authors. Alzheimer's & Dementia published by Wiley Periodicals LLC on behalf of Alzheimer's Association.