TY - JOUR
T1 - Towards collaborative data science in mental health research
T2 - The ECNP neuroimaging network accessible data repository
AU - Khuntia, Adyasha
AU - Buciuman, Madalina Octavia
AU - Fanning, John
AU - Stolicyn, Aleks
AU - Vetter, Clara
AU - Armio, Reetta Liina
AU - From, Tiina
AU - Goffi, Federica
AU - Hahn, Lisa
AU - Kaufmann, Tobias
AU - Laurikainen, Heikki
AU - Maggioni, Eleonora
AU - Martinez-Zalacain, Ignacio
AU - Ruef, Anne
AU - Dong, Mark Sen
AU - Schwarz, Emanuel
AU - Squarcina, Letizia
AU - Andreassen, Ole
AU - Bellani, Marcella
AU - Brambilla, Paolo
AU - Haren, Neeltje van
AU - Hietala, Jarmo
AU - Lawrie, Stephen M.
AU - Soriano-Mas, Carles
AU - Whalley, Heather
AU - Taquet, Maxime
AU - Meisenzahl, Eva
AU - Falkai, Peter
AU - Wiegand, Ariane
AU - Koutsouleris, Nikolaos
N1 - Publisher Copyright:
© 2024 The Authors
PY - 2025
Y1 - 2025
N2 - The current biologically uninformed psychiatric taxonomy complicates optimal diagnosis and treatment. Neuroimaging-based machine learning methods hold promise for tackling these issues, but large-scale, representative cohorts are required for building robust and generalizable models. The European College of Neuropsychopharmacology Neuroimaging Network Accessible Data Repository (ECNP-NNADR) addresses this need by collating multi-site, multi-modal, multi-diagnosis datasets that enable collaborative research. The newly established ECNP-NNADR includes 4829 participants across 21 cohorts and 11 distinct psychiatric diagnoses, available via the Virtual Pooling and Analysis of Research data (ViPAR) software. The repository includes demographic and clinical information, including diagnosis and questionnaires evaluating psychiatric symptomatology, as well as multi-atlas grey matter volume regions of interest (ROI). To illustrate the opportunities offered by the repository, two proof-of-concept analyses were performed: (1) multivariate classification of 498 patients with schizophrenia (SZ) and 498 matched healthy control (HC) individuals, and (2) normative age prediction using 1170 HC individuals with subsequent application of this model to study abnormal brain maturational processes in patients with SZ. In the SZ classification task, we observed varying balanced accuracies, reaching a maximum of 71.13% across sites and atlases. The normative-age model demonstrated a mean absolute error (MAE) of 6.95 years [coefficient of determination (R2) = 0.77, P < .001] across sites and atlases. The model demonstrated robust generalization on a separate HC left-out sample achieving a MAE of 7.16 years [R2 = 0.74,P < .001]. When applied to the SZ group, the model exhibited a MAE of 7.79 years [R2 = 0.79, P < .001], with patients displaying accelerated brain-aging with a brain age gap (BrainAGE) of 4.49 (8.90) years. Conclusively, this novel multi-site, multi-modal, transdiagnostic data repository offers unique opportunities for systematically tackling existing challenges around the generalizability and validity of imaging-based machine learning applications for psychiatry.
AB - The current biologically uninformed psychiatric taxonomy complicates optimal diagnosis and treatment. Neuroimaging-based machine learning methods hold promise for tackling these issues, but large-scale, representative cohorts are required for building robust and generalizable models. The European College of Neuropsychopharmacology Neuroimaging Network Accessible Data Repository (ECNP-NNADR) addresses this need by collating multi-site, multi-modal, multi-diagnosis datasets that enable collaborative research. The newly established ECNP-NNADR includes 4829 participants across 21 cohorts and 11 distinct psychiatric diagnoses, available via the Virtual Pooling and Analysis of Research data (ViPAR) software. The repository includes demographic and clinical information, including diagnosis and questionnaires evaluating psychiatric symptomatology, as well as multi-atlas grey matter volume regions of interest (ROI). To illustrate the opportunities offered by the repository, two proof-of-concept analyses were performed: (1) multivariate classification of 498 patients with schizophrenia (SZ) and 498 matched healthy control (HC) individuals, and (2) normative age prediction using 1170 HC individuals with subsequent application of this model to study abnormal brain maturational processes in patients with SZ. In the SZ classification task, we observed varying balanced accuracies, reaching a maximum of 71.13% across sites and atlases. The normative-age model demonstrated a mean absolute error (MAE) of 6.95 years [coefficient of determination (R2) = 0.77, P < .001] across sites and atlases. The model demonstrated robust generalization on a separate HC left-out sample achieving a MAE of 7.16 years [R2 = 0.74,P < .001]. When applied to the SZ group, the model exhibited a MAE of 7.79 years [R2 = 0.79, P < .001], with patients displaying accelerated brain-aging with a brain age gap (BrainAGE) of 4.49 (8.90) years. Conclusively, this novel multi-site, multi-modal, transdiagnostic data repository offers unique opportunities for systematically tackling existing challenges around the generalizability and validity of imaging-based machine learning applications for psychiatry.
KW - Data repository
KW - Machine learning
KW - Multi-site data
KW - Neuroimaging
KW - Psychiatry
KW - Structural MRI
KW - Transdiagnostic
UR - http://www.scopus.com/inward/record.url?scp=85212316367&partnerID=8YFLogxK
U2 - 10.1016/j.nsa.2024.105407
DO - 10.1016/j.nsa.2024.105407
M3 - Article
AN - SCOPUS:85212316367
SN - 2772-4085
VL - 4
JO - Neuroscience Applied
JF - Neuroscience Applied
M1 - 105407
ER -