Predicting sex, age, general cognition and mental health with machine learning on brain structural connectomes. Issue 5 (21st December 2022)

• Record Type: Journal Article
• Authors: Yeung, Hon Wah; Stolicyn, Aleks; Buchanan, Colin R.; Tucker‐Drob, Elliot M.; Bastin, Mark E.; Luz, Saturnino; McIntosh, Andrew M.; Whalley, Heather C.; Cox, Simon R.; Smith, Keith
• Is Part Of: Human brain mapping. Volume 44:Issue 5(2023)
• Page Start: 1913
• Page End: 1933
• Publication Date: 2022-12-21
• Subjects: cognition -- deep learning -- diffusion tensor imaging -- general psychopathology -- structural connectomes; Brain mapping -- Periodicals; 611.81
• DOI: 10.1002/hbm.26182
• Languages: English
• ISSNs: 1065-9471

Abstract

Abstract: There is an increasing expectation that advanced, computationally expensive machine learning (ML) techniques, when applied to large population‐wide neuroimaging datasets, will help to uncover key differences in the human brain in health and disease. We take a comprehensive approach to explore how multiple aspects of brain structural connectivity can predict sex, age, general cognitive function and general psychopathology, testing different ML algorithms from deep learning (DL) model (BrainNetCNN) to classical ML methods. We modelled N = 8183 structural connectomes from UK Biobank using six different structural network weightings obtained from diffusion MRI. Streamline count generally provided the highest prediction accuracies in all prediction tasks. DL did not improve on prediction accuracies from simpler linear models. Further, high correlations between gradient attribution coefficients from DL and model coefficients from linear models suggested the models ranked the importance of features in similar ways, which indirectly suggested the similarity in models' strategies for making predictive decision to some extent. This highlights that model complexity is unlikely to improve detection of associations between structural connectomes and complex phenotypes with the current sample size. Abstract : We explore how multiple aspects of brain structural connectivity can predict general cognitive function and general psychopathology. To do this, we modelled six different structural network weightings obtained from diffusion MRI and tested different machine learning (ML) algorithms from deep learning (DL) model (BrainNetCNN) to classical ML methods. DL did not improve on prediction accuracies from simpler linear models, indicating that most of the variation between phenotypes in weighted structural connectomes is linear rather than non‐linear in nature. This may have implied that model complexity is unlikely to improve detection of associations between structural connectomes and complex phenotypes with the current sample size.