{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Vandewouw MM"],"funding":["NIDA NIH HHS","New Frontiers in Research Fund","NIMH NIH HHS","Gouvernement du Canada | Canadian Institutes of Health Research"],"pagination":["326"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12397277"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["15(1)"],"pubmed_abstract":["Internalizing problems (e.g., anxiety and depression) are associated with a wide range of adverse outcomes. While some predictors of internalizing problems are known (e.g., their frequent co-occurrence with neurodevelopmental (ND) conditions), the biological markers of internalizing problems are not well understood. Here, we used deep learning, a powerful tool for identifying complex and multi-dimensional brain-behaviour relationships, to predict cross-sectional and worsening longitudinal trajectories of internalizing problems. Data were extracted from four large-scale datasets: the Adolescent Brain Cognitive Development study, the Healthy Brain Network, the Human Connectome Project Development study, and the Province of Ontario Neurodevelopmental network. We developed deep learning models"],"journal":["Translational psychiatry"],"pubmed_title":["Using deep learning to predict internalizing problems from brain structure in youth."],"pmcid":["PMC12397277"],"funding_grant_id":["U01 DA051037","U01 DA041106","U01 DA041117","U24 DA041123","U01 DA041028","U24 DA041147","U01 MH109589","U01 DA041089","U01 DA041022","U01 DA041120","U01 DA041174","U01 DA041148","U01 DA041048","U01 DA041025","U01 DA041156","U01 DA041134","U01 DA051039","U01 DA051038","U01 DA051016","U01 DA051018","U01 DA050988","U01 DA050987","U01 DA050989","U01 DA041093"],"pubmed_authors":["Crosbie J","Kushki A","Anagnostou E","Kelley E","Vandewouw MM","Schachar RJ","Taylor MJ","Barnett N","Lerch JP","Jones J","Arnold PD","Ayub M","Arias A","Syed B","Iaboni A"],"additional_accession":[]},"is_claimable":false,"name":"Using deep learning to predict internalizing problems from brain structure in youth.","description":"Internalizing problems (e.g., anxiety and depression) are associated with a wide range of adverse outcomes. While some predictors of internalizing problems are known (e.g., their frequent co-occurrence with neurodevelopmental (ND) conditions), the biological markers of internalizing problems are not well understood. Here, we used deep learning, a powerful tool for identifying complex and multi-dimensional brain-behaviour relationships, to predict cross-sectional and worsening longitudinal trajectories of internalizing problems. Data were extracted from four large-scale datasets: the Adolescent Brain Cognitive Development study, the Healthy Brain Network, the Human Connectome Project Development study, and the Province of Ontario Neurodevelopmental network. We developed deep learning models","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Aug","modification":"2026-06-02T20:34:13.624Z","creation":"2026-05-27T03:08:03.077Z"},"accession":"S-EPMC12397277","cross_references":{"pubmed":["40883286"],"doi":["10.1038/s41398-025-03565-3"]}}