Differential predictability of cognitive profiles from brain structure in older males and females

• DOI: 10.1007/s11357-023-00934-y
• Publication Date: 2023-09-20T23:04:20Z
• Authors: Christiane Jockwitz; Camilla Krämer; Paulo Dellani; Svenja Caspers
• Keywords: Predictability; Verbal fluency test; Elementary cognitive task

Structural brain imaging parameters may successfully predict cognitive performance in neurodegenerative diseases but mostly fail to abilities healthy older adults. One important aspect contributing this might be sex differences. Behaviorally, males and females have been found differ terms of profiles, which cannot captured by examining them as one homogenous group. In the current study, we examined whether prediction from structure, i.e. region-wise grey matter volume (GMV), would benefit investigation sex-specific profiles a large sample adults (1000BRAINS; N = 634; age range 55-85 years). Prediction was assessed using machine learning (ML) approach. Targets represented a) whole-sample component solution extracted females, b) components. Results revealed generally low predictability GMV. males, observed across both, whole well however, differences components were observed, visual working memory (WM) executive functions showed higher than fluency verbal WM. Hence, results accentuated that addressing allowed more fine-grained differences, not observable solution. The findings only emphasize need further investigate predictive power each component, they also importance analyses