Abstract

Event Abstract Back to Event Precise predictions of intelligence and personality traits from brain structure Ryota Kanai1*, Hiromitsu Mizutani1, Haruto Takagishi2 and Toshio Yamagishi3 1 Araya Brain Imaging, Department of Neuroinformatics, Japan 2 Tamagawa University, Brain Science Institute, Japan 3 Hitotsubashi University, Graduate School of International Corporate Strategy, Japan The recent surge of interest in the relationship between brain structure and cognitive function has revealed numerous correlations between regional morphometric properties of the brain such as grey matter volume and cognitive traits such as cognitive abilities and personality traits (Kanai & Rees, 2011). While consistent results across multiple studies (e.g. Kanai, Dong, Bahrami & Rees, 2011; Sandberg et al., 2014; Kanai, 2015) suggest the presence of personal information in structural MRI data, it remains unknown to what extent such brain-behaviour correlations allow us to make predictions about an individual’s traits. In the present study, we used a machine-learning approach to predict an individual’s age, gender, intelligence, and big five personality traits from high-resolution T1 weighted MRI images (1mm isotropic). One of the challenges to construct a predictive model from MRI data is the dimensionality of features (i.e. the number of voxels), which is typically much higher than sample size (i.e. the number of participants). In our current study, we used a relatively large sample for a study of this sort (n=470), but there is still a 100-folds difference to the number of voxels corresponding to grey matter (i.e. ~450,000). To address this issue, we applied the regularization method called the elastic net, which has been shown to outperform other approach when the number of features is much larger than the number of samples (Zou & Hatie, 2005). Our results indicate that this approach can successfully construct highly accurate prediction models for age, gender, intelligence and all the five components in the Big Five Model of personality traits. This is in stark contrast with the conventional, univariate voxel-based morphometry (VBM) approach which shows only weak correlations between particular brain regions and traits. In summary, our study demonstrates the richness of the information we can extract from an individual’s brain MRI scan, and suggests that possibility that we can create highly precise predictions models for intelligence and personality traits. Acknowledgements This work was supported by JSPS KAKENHI Grant Numbers 23223003, and the ImPACT programme from the Cabinet of Japan. References Kanai, R. (2015). Open questions in conducting confirmatory replication studies: A reply to Boekel et al. Cortex. Kanai, R. & Rees, G. (2011). The structural basis of inter-individual differences in human behaviour and cognition. Nature Reviews Neuroscience, 12, 231-242. Kanai, R., Dong, M., Bahrami, B. & Rees, G. (2011). Distractibility in daily life is reflected in the structure of human parietal cortex. Journal of Neuroscience, 31, 6620-6626. Sandberg, K., Blicher, J.U., Dong, M., Rees, G., Near, J. & Kanai, R. (2014). Occipital GABA concentration predicts cognitive failures in daily life. Neuroimage, 87, 55-60. Zou, H., & Hastie, T. (2005). Regularization and variable selection via the elastic net. Journal of the Royal Statistical Society, Series B, 67, 301–320. Keywords: MRI, individual differences, machine learning, Intelligence, Personality, Voxel-based morphometry (VBM), Neuroprediction Conference: Neuroinformatics 2015, Cairns, Australia, 20 Aug - 22 Aug, 2015. Presentation Type: Poster, to be considered for oral presentation Topic: Neuroimaging Citation: Kanai R, Mizutani H, Takagishi H and Yamagishi T (2015). Precise predictions of intelligence and personality traits from brain structure. Front. Neurosci. Conference Abstract: Neuroinformatics 2015. doi: 10.3389/conf.fnins.2015.91.00037 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 03 May 2015; Published Online: 05 Aug 2015. * Correspondence: Dr. Ryota Kanai, Araya Brain Imaging, Department of Neuroinformatics, Tokyo, Tokyo, Japan, kanair@gmail.com Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Ryota Kanai Hiromitsu Mizutani Haruto Takagishi Toshio Yamagishi Google Ryota Kanai Hiromitsu Mizutani Haruto Takagishi Toshio Yamagishi Google Scholar Ryota Kanai Hiromitsu Mizutani Haruto Takagishi Toshio Yamagishi PubMed Ryota Kanai Hiromitsu Mizutani Haruto Takagishi Toshio Yamagishi Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.