Empirical validation of race-neutral normative brain morphometry models across ethnoracially diverse populations

Normative models of brain morphometry quantify individual deviations from typical anatomical patterns and hold promise for enhancing clinical decision-making. However, their clinical utility depends critically on demonstrating generalizability across diverse ethnoracial populations. We previously developed sex-specific, race-neutral normative models for cortical thickness, surface area, and subcortical volumes using brain scans from a large international sample of healthy individuals, as part of the CentileBrain Project, a global initiative to provide open-access, neuroimaging reference models. The primary aim of the present study was to empirically evaluate the generalizability and accuracy of these pretrained models across multiple ethnoracial groups. To this end, we tested model performance in independent samples of healthy individuals from Africa, Asia, Europe, and the Americas, with ethnoracial classification defined either by self-identification or genetic ancestry (N = 4,862). We further compared performance against normative models developed exclusively from a single-population Chinese cohort. Across all groups, as well as in the pooled sample, the pretrained CentileBrain models demonstrated consistently high accuracy, with relative mean absolute error values below 10% for subcortical volume and surface area and below 5% for cortical thickness. Model performance was highly concordant across self-identified and ancestry-defined groups. In a separate analysis, the CentileBrain models performed comparably to a population-specific model when applied to an independent ancestry-matched sample. These findings provide empirical support for the generalizability of race-neutral normative models developed on large and diverse samples and underscore their potential utility for individualized neuroimaging assessment across ethnoracially diverse populations.

Authors

Institutions

Publication Details

Journal
Proceedings of the National Academy of Sciences
Published
2026-05-12
DOI
https://doi.org/10.1073/pnas.2521055123
Primary Topic
Functional Brain Connectivity Studies
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Empirical validation of race-neutral normative brain morphometry models across ethnoracially diverse populations

Neelabja Roy, Faye New, Seda Arslan, Camilo de la Fuente‐Sandoval et al.
Proceedings of the National Academy of Sciences
Functional Brain Connectivity Studies
article

Empirical validation of race-neutral normative brain morphometry models across ethnoracially diverse populations

Neelabja Roy, Faye New, Seda Arslan, Camilo de la Fuente‐Sandoval, Guoyuan Yang, T. Toulopoulou, Tuba Sahin-Ilikoglu, Kevin Yu, Urvaksh Mehta, Alfonso Gonzalez- Valderrama, Kader Kubat, Shalaila S. Haas, Nicolas A. Crossley, Mihai Avram, Felice Iasevoli, Ryota Hashimoto, Mariana Zurita, Kiyotaka Nemoto, Ruiyang Ge, Veena Kumari, Didenur Şahin-Çevik, Masaki Fukunaga, Giuseppe Pontillo, Francisco Reyes-Madrigal, Elias Wagner, Daniel Keeser, Paul Allen, Sophia Frangou, Stefan Borgwardt, Jia-Hong Gao, Nicole Sanford, Yuetong Yu, Florian J. Raabe, Junya Matsumoto, Paul M. Thompson
article en

Abstract

Normative models of brain morphometry quantify individual deviations from typical anatomical patterns and hold promise for enhancing clinical decision-making. However, their clinical utility depends critically on demonstrating generalizability across diverse ethnoracial populations. We previously developed sex-specific, race-neutral normative models for cortical thickness, surface area, and subcortical volumes using brain scans from a large international sample of healthy individuals, as part of the CentileBrain Project, a global initiative to provide open-access, neuroimaging reference models. The primary aim of the present study was to empirically evaluate the generalizability and accuracy of these pretrained models across multiple ethnoracial groups. To this end, we tested model performance in independent samples of healthy individuals from Africa, Asia, Europe, and the Americas, with ethnoracial classification defined either by self-identification or genetic ancestry (N = 4,862). We further compared performance against normative models developed exclusively from a single-population Chinese cohort. Across all groups, as well as in the pooled sample, the pretrained CentileBrain models demonstrated consistently high accuracy, with relative mean absolute error values below 10% for subcortical volume and surface area and below 5% for cortical thickness. Model performance was highly concordant across self-identified and ancestry-defined groups. In a separate analysis, the CentileBrain models performed comparably to a population-specific model when applied to an independent ancestry-matched sample. These findings provide empirical support for the generalizability of race-neutral normative models developed on large and diverse samples and underscore their potential utility for individualized neuroimaging assessment across ethnoracially diverse populations.

Proceedings of the National Academy of SciencesVol. 123(20)
University of Southern California (US), Beijing Institute of Technology (CN), Allen Institute for Brain Science (US), University of British Columbia (CA), McGovern Institute for Brain Research (US), University of Tsukuba (JP), Pontificia Universidad Católica de Chile (CL), Bilkent University (TR), University of Augsburg (DE), National and Kapodistrian University of Athens (GR), LMU Klinikum (DE), National Center of Neurology and Psychiatry (JP), Finis Terrae University (CL), Federico II University Hospital (IT), Institut des Sciences Cognitives Marc Jeannerod (FR), Social Neuroscience Lab (DE), Advanced Research Institute (US), Bernstein Center for Computational Neuroscience Munich (DE), National Institute for Physiological Sciences (JP), Max Planck Institute of Psychiatry (DE), Instituto Nacional de Neurología y Neurocirugía (MX), Resonance Research (United States) (US), Psychiatric Medical Center (AM), Bezirkskrankenhaus Augsburg (DE), Brunel University of London (GB), National Institute of Mental Health and Neurosciences (IN), University of Naples Federico II (IT), Ludwig-Maximilians-Universität München (DE), University of Lübeck (DE)
University of Southern California, Università degli Studi di Napoli Federico II, Japan Agency for Medical Research and Development, Wellcome Trust, Universität zu Lübeck, Beijing Institute of Technology, National and Kapodistrian University of Athens, Ludwig-Maximilians-Universität München, Bilkent Üniversitesi, University of Tsukuba, Peking University, The Wellcome Trust DBT India Alliance, National Center of Neurology and Psychiatry, Pontificia Universidad Católica de Chile, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, McGovern Institute for Brain Research, Massachusetts Institute of Technology, Dipartimento di Scienze Biomediche Avanzate, Università degli Studi di Napoli Federico II, Medical Research Council, Japan Society for the Promotion of Science, National Institute of Mental Health, National Institute for Physiological Sciences
Peace, Justice and strong institutions
Openalex Percentile: Top 5%
Functional Brain Connectivity Studies
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.