RESUMO
Introduction: Personality traits and neuropsychiatric symptoms such as neuroticism and depression share genetic overlap and have both been identified as risks factors for development of aging-related neurocognitive decline and Alzheimer's disease (AD). This study aimed to examine revised personality factors derived from the Temperament and Character Inventory, previously shown to be associated with psychiatric disorders, as predictors of neuropsychiatric, cognitive, and brain trajectories of participants from a population-based aging study. Methods: Mixed-effect linear regression analyses were conducted on data for the full sample (Nmax = 1,286), and a healthy subsample not converting to AD-dementia during 25-year follow-up (Nmax = 1,145), complemented with Cox proportional regression models to determine risk factors for conversion to clinical AD. Results: Two personality factors, Closeness to Experience (CE: avoidance of new stimuli, high anxiety, pessimistic anticipation, low reward seeking) and Tendence to Liabilities (TL: inability to change, low autonomy, unaware of the value of their existence) were associated with higher levels of depressive symptoms, stress (CE), sleep disturbance (TL), as well as greater decline in memory, vocabulary and verbal fluency in the full sample. Higher CE was additionally associated with greater memory decline across 25 years in the healthy subsample, and faster right hippocampal volume reduction across 8 years in a neuroimaging subsample (N = 216). Most, but not all, personality-cognition associations persisted after controlling for diabetes, hypertension and cardiovascular disease. Concerning risks for conversion to AD, higher age, and APOE-ε4, but none of the personality measures, were significant predictors. Conclusion: The results indicate that personality traits associated with psychiatric symptoms predict accelerated age-related neurocognitive declines even in the absence of neurodegenerative disease. The attenuation of some personality effects on cognition after adjustment for health indicators suggests that those effects may be partly mediated by somatic health. Taken together, the results further emphasize the importance of personality traits in neurocognitive aging and underscore the need for an integrative (biopsychosocial) perspective of normal and pathological age-related cognitive decline.
RESUMO
Introduction: Graph-based representations are becoming more common in the medical domain, where each node defines a patient, and the edges signify associations between patients, relating individuals with disease and symptoms in a node classification task. In this study, a Graph Convolutional Networks (GCN) model was utilized to capture differences in neurocognitive, genetic, and brain atrophy patterns that can predict cognitive status, ranging from Normal Cognition (NC) to Mild Cognitive Impairment (MCI) and Alzheimer's Disease (AD), on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. Elucidating model predictions is vital in medical applications to promote clinical adoption and establish physician trust. Therefore, we introduce a decomposition-based explanation method for individual patient classification. Methods: Our method involves analyzing the output variations resulting from decomposing input values, which allows us to determine the degree of impact on the prediction. Through this process, we gain insight into how each feature from various modalities, both at the individual and group levels, contributes to the diagnostic result. Given that graph data contains critical information in edges, we studied relational data by silencing all the edges of a particular class, thereby obtaining explanations at the neighborhood level. Results: Our functional evaluation showed that the explanations remain stable with minor changes in input values, specifically for edge weights exceeding 0.80. Additionally, our comparative analysis against SHAP values yielded comparable results with significantly reduced computational time. To further validate the model's explanations, we conducted a survey study with 11 domain experts. The majority (71%) of the responses confirmed the correctness of the explanations, with a rating of above six on a 10-point scale for the understandability of the explanations. Discussion: Strategies to overcome perceived limitations, such as the GCN's overreliance on demographic information, were discussed to facilitate future adoption into clinical practice and gain clinicians' trust as a diagnostic decision support system.