Big Five, self-reported depression, and anxiety are predictive for Alzheimer’s disease

ObjectivesThe main goal of machine learning approaches to classify people into healthy, increased Alzheimer’s disease (AD) risk, and AD is the identification of valuable predictors for valid classification, prediction of conversion, and automatization of the process. While biomarkers from cerebrospinal fluid (CSF) are the best-established predictors for AD, other less invasive, easy-to-assess candidate predictors have been identified. Here, we evaluated the predictive value of such less invasive, predictors separately and in different combinations for classification of healthy controls (HC), subjective cognitive decline (SCD), mild cognitive impairment (MCI), and mild AD.MethodsWe evaluated the predictive value of personality scores, geriatric anxiety and depression scores, a resting-state functional magnetic resonance imaging (fMRI) marker (mPerAF), apoliprotein E (ApoE), and CSF markers (tTau, pTau181, Aβ42/40 ratio) separately and in different combinations in multi-class support vector machine classification. Participants (189 HC, 338 SCD, 132 MCI, 74 mild AD) were recruited from the multi-center DZNE-Longitudinal Cognitive Impairment and Dementia Study (DELCODE).ResultsHC were best predicted by a feature set comprised of personality, anxiety, and depression scores, while participants with AD were best predicted by a feature set containing CSF markers. Both feature sets had equally high overall decoding accuracy. However, all assessed feature sets performed relatively poorly in the classification of SCD and MCI.ConclusionOur results highlight that SCD and MCI are heterogeneous groups, pointing out the importance of optimizing their diagnosis criteria. Moreover, CSF biomarkers, personality, depression, and anxiety indicate complementary value for class prediction, which should be followed up on in future studies.Key PointsUsing multi-class support vector machine, we compared the predictive value of well-established versus non-invasive, easy-to-assess candidate variables for classification of participants with healthy cognition, subjective cognitive decline, mild cognitive impairment, and mild Alzheimer’s disease.Personality traits, geriatric anxiety and depression scores, resting-state mPerAF, ApoE genotype, and CSF markers were comparatively evaluated both separately and in different combinations.Predictive accuracy was similarly high for a combination of personality, anxiety and depression scores as for CSF markers.Both established as well as candidate variables performed poorly in classifying SCD and MCI, highlighting heterogenous causes of those cognitive states.CSF biomarkers and extended personality measures show complementary value for class prediction, which should be followed up on in future studies.