Limited generalizability of multivariate brain-based dimensions of child psychiatric symptoms

Bing Xu; Lorenza Dall'Aglio; John Flournoy; Gerda Bortsova; Brenden Tervo-Clemmens; Paul Collins; Marleen de Bruijne; Monica Luciana; Andre Marquand; Hao Wang; Henning Tiemeier; Ryan L Muetzel

doi:10.1038/s44271-024-00063-y

Limited generalizability of multivariate brain-based dimensions of child psychiatric symptoms

Commun Psychol. 2024 Feb 28;2(1):16. doi: 10.1038/s44271-024-00063-y.

Authors

Bing Xu^{1

2}, Lorenza Dall'Aglio^{1

2}, John Flournoy³, Gerda Bortsova⁴, Brenden Tervo-Clemmens⁵, Paul Collins⁶, Marleen de Bruijne^{4

7}, Monica Luciana⁶, Andre Marquand^{8

9}, Hao Wang¹⁰, Henning Tiemeier^{11

12}, Ryan L Muetzel^{1

13}

Affiliations

¹ Department of Child and Adolescent Psychology and Psychiatry, Erasmus MC University Medical Center Rotterdam-Sophia Children's Hospital, Rotterdam, The Netherlands.
² The Generation R Study Group, Erasmus MC University Medical Center Rotterdam, Rotterdam, The Netherlands.
³ Department of Psychology, Harvard University, Cambridge, MA, USA.
⁴ Department of Radiology and Nuclear Medicine, Biomedical Imaging Group Rotterdam, Erasmus MC University Medical Center Rotterdam, Rotterdam, The Netherlands.
⁵ Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
⁶ Department of Psychology, University of Minnesota, Minneapolis, MN, USA.
⁷ Department of Computer Science, University of Copenhagen, Copenhagen, Denmark.
⁸ Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, The Netherlands.
⁹ Radboud University Medical Center, Nijmegen, The Netherlands.
¹⁰ Leiden Institute of Advanced Computer Science, Leiden University, Leiden, The Netherlands.
¹¹ Department of Child and Adolescent Psychology and Psychiatry, Erasmus MC University Medical Center Rotterdam-Sophia Children's Hospital, Rotterdam, The Netherlands. tiemeier@hsph.harvard.edu.
¹² Department of Social and Behavioral Sciences, Harvard T. Chan School of Public Health, Boston, MA, USA. tiemeier@hsph.harvard.edu.
¹³ Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Center Rotterdam, Rotterdam, The Netherlands.

Abstract

Multivariate machine learning techniques are a promising set of tools for identifying complex brain-behavior associations. However, failure to replicate results from these methods across samples has hampered their clinical relevance. Here we aimed to delineate dimensions of brain functional connectivity that are associated with child psychiatric symptoms in two large and independent cohorts: the Adolescent Brain Cognitive Development (ABCD) Study and the Generation R Study (total n = 6935). Using sparse canonical correlations analysis, we identified two brain-behavior dimensions in ABCD: attention problems and aggression/rule-breaking behaviors. Importantly, out-of-sample generalizability of these dimensions was consistently observed in ABCD, suggesting robust multivariate brain-behavior associations. Despite this, out-of-study generalizability in Generation R was limited. These results highlight that the degrees of generalizability can vary depending on the external validation methods employed as well as the datasets used, emphasizing that biomarkers will remain elusive until models generalize better in true external settings.

Abstract

Grants and funding