Brain-age prediction: Systematic evaluation of site effects, and sample age range and size

Yuetong Yu¹, Hao-Qi Cui¹, Shalaila S Haas², Faye New², Nicole Sanford¹, Kevin Yu¹, Denghuang Zhan³, Guoyuan Yang⁴, Jia-Hong Gao⁵, Dongtao Wei⁶, Jiang Qiu⁶, Nerisa Banaj⁷, Dorret I Boomsma⁸, Alan Breier⁹, Henry Brodaty¹⁰, Randy L Buckner^{11

12}, Jan K Buitelaar¹³, Dara M Cannon¹⁴, Xavier Caseras¹⁵, Vincent P Clark¹⁶, Patricia J Conrod¹⁷, Fabrice Crivello¹⁸, Eveline A Crone^{19

20}, Udo Dannlowski²¹, Christopher G Davey²², Lieuwe de Haan²³, Greig I de Zubicaray²⁴, Annabella Di Giorgio²⁵, Lukas Fisch²¹, Simon E Fisher^{26

27}, Barbara Franke^{27

28

29}, David C Glahn³⁰, Dominik Grotegerd²¹, Oliver Gruber³¹, Raquel E Gur³², Ruben C Gur³², Tim Hahn²¹, Ben J Harrison²², Sean Hatton³³, Ian B Hickie³³, Hilleke E Hulshoff Pol^{2

34

35}, Alec J Jamieson²², Terry L Jernigan³⁶, Jiyang Jiang¹⁰, Andrew J Kalnin³⁷, Sim Kang³⁸, Nicole A Kochan¹⁰, Anna Kraus²¹, Jim Lagopoulos³³, Luisa Lazaro³⁹, Brenna C McDonald⁴⁰, Colm McDonald¹⁴, Katie L McMahon⁴¹, Benson Mwangi⁴², Fabrizio Piras⁷, Raul Rodriguez-Cruces⁴³, Jessica Royer⁴³, Perminder S Sachdev¹⁰, Theodore D Satterthwaite³², Andrew J Saykin⁴⁰, Gunter Schumann^{44

45}, Pierluigi Sevaggi⁴⁶, Jordan W Smoller^{12

47

48}, Jair C Soares⁴², Gianfranco Spalletta⁷, Christian K Tamnes⁴⁹, Julian N Trollor^{10

50}, Dennis Van't Ent⁸, Daniela Vecchio⁷, Henrik Walter⁵¹, Yang Wang⁵², Bernd Weber⁵³, Wei Wen¹⁰, Lara M Wierenga¹⁹, Steven C R Williams⁵⁴, Mon-Ju Wu⁴², Giovana B Zunta-Soares⁴², Boris Bernhardt⁴³, Paul Thompson⁵⁵, Sophia Frangou^{1

2}, Ruiyang Ge¹; ENIGMA‐Lifespan Working Group

Affiliations

¹ Djavad Mowafaghian Centre for Brain Health, Department of Psychiatry, University of British Columbia, Vancouver, British Columbia, Canada.
² Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
³ School of Population and Public Health, University of British Columbia, Vancouver, British Columbia, Canada.
⁴ Advanced Research Institute of Multidisciplinary Sciences, School of Medical Technology, School of Life Science, Beijing Institute of Technology, Beijing, China.
⁵ Center for MRI Research, Peking University, Beijing, China.
⁶ School of Psychology, Southwest University, Chongqing, China.
⁷ Laboratory of Neuropsychiatry, Department of Clinical and Behavioral Neurology, IRCCS Santa Lucia Foundation, Rome, Italy.
⁸ Department of Biological Psychology, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands.
⁹ Department of Psychiatry, Indiana University School of Medicine, Indianapolis, Indiana, USA.
¹⁰ Centre for Healthy Brain Ageing (CHeBA), Discipline of Psychiatry and Mental Health, School of Clinical Medicine, University of New South Wales, Sydney, New South Wales, Australia.
¹¹ Department of Psychology, Center for Brain Science, Harvard University, Boston, Massachusetts, USA.
¹² Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.
¹³ Department of Cognitive Neuroscience, Donders Institute for Brain, Cognition and Behaviour, Radboud University Medical Center, Nijmegen, The Netherlands.
¹⁴ Centre for Neuroimaging & Cognitive Genomics (NICOG), Clinical Neuroimaging Laboratory, Galway Neuroscience Centre, College of Medicine Nursing and Health Sciences, University of Galway, Galway, Ireland.
¹⁵ Centre for Neuropsychiatric Genetics and Genomics, Division of Psychological Medicine and Clinical Neurosciences, Cardiff University, Cardiff, UK.
¹⁶ Psychology Clinical Neuroscience Center, Department of Psychology, University of New Mexico, Albuquerque, New Mexico, USA.
¹⁷ Department of Psychiatry and Addiction, Université de Montréal, CHU Ste Justine, Montreal, Quebec, Canada.
¹⁸ Institut des Maladies Neurodégénératives, Université de Bordeaux, Bordeaux, France.
¹⁹ Department of Psychology, Faculty of Social Sciences, Leiden University, Leiden, The Netherlands.
²⁰ Erasmus School of Social and Behavioral Sciences, Erasmus University Rotterdam, Rotterdam, The Netherlands.
²¹ Institute for Translational Psychiatry, University of Münster, Münster, Germany.
²² Department of Psychiatry, The University of Melbourne, Melbourne, Victoria, Australia.
²³ Department of Psychiatry, Amsterdam UMC, Amsterdam, The Netherlands.
²⁴ Faculty of Health, School of Psychology & Counselling, Queensland University of Technology, Brisbane, Queensland, Australia.
²⁵ Department of Mental Health and Addictions, ASST Papa Giovanni XXIII, Bergamo, Italy.
²⁶ Language and Genetics Department, Max Planck Institute for Psycholinguistics, Nijmegen, The Netherlands.
²⁷ Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, The Netherlands.
²⁸ Department of Cognitive Neuroscience, Radboud University Medical Center, Nijmegen, The Netherlands.
²⁹ Department of Human Genetics, Radboud University Medical Center, Nijmegen, The Netherlands.
³⁰ Department of Psychiatry, Tommy Fuss Center for Neuropsychiatric Disease Research, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
³¹ Section for Experimental Psychopathology and Neuroimaging, Department of General Psychiatry, Heidelberg University, Heidelberg, Germany.
³² Department of Psychiatry, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
³³ Brain and Mind Centre, The University of Sydney, Sydney, New South Wales, Australia.
³⁴ Department of Psychology, Utrecht University, Utrecht, The Netherlands.
³⁵ Department of Psychiatry, University Medical Center Utrecht, Utrecht, The Netherlands.
³⁶ Center for Human Development, Departments of Cognitive Science, Psychiatry, and Radiology, University of California, San Diego, California, USA.
³⁷ Department of Radiology, The Ohio State University College of Medicine, Columbus, Ohio, USA.
³⁸ West Region, Institute of Mental Health, Singapore, Singapore.
³⁹ Department of Child and Adolescent Psychiatry and Psychology, Hospital Clínic, IDIBAPS, CIBERSAM, University of Barcelona, Barcelona, Spain.
⁴⁰ Department of Radiology and Imaging Sciences, Indiana University School of Medicine, Indianapolis, Indiana, USA.
⁴¹ School of Clinical Sciences, Centre for Biomedical Technologies, Queensland University of Technology, Brisbane, Queensland, Australia.
⁴² Louis A. Faillace, MD, Department of Psychiatry and Behavioral Sciences, The University of Texas Health Science Center at Houston, Houston, Texas, USA.
⁴³ McConnell Brain Imaging Centre, McGill University, Montreal, Quebec, Canada.
⁴⁴ Department of Psychiatry, CCM, Charite Universitaetsmedizin Berlin, Berlin, Germany.
⁴⁵ Centre for Population Neuroscience and Stratified Medicine (PONS), ISTBI, Fudan University, Shanghai, China.
⁴⁶ Department of Translational Biomedicine and Neuroscience, University of Bari Aldo Moro, Bari, Italy.
⁴⁷ Center for Genomic Medicine, Massachusetts General Hospital, Boston, Massachusetts, USA.
⁴⁸ Center for Precision Psychiatry, Massachusetts General Hospital, Boston, Massachusetts, USA.
⁴⁹ PROMENTA Research Center, Department of Psychology, University of Oslo, Oslo, Norway.
⁵⁰ Department of Developmental Disability Neuropsychiatry, School of Clinical Medicine, University of New South Wales, Sydney, New South Wales, Australia.
⁵¹ Department of Psychiatry and Psychotherapy, Charité Universitätsmedizin Berlin, Corporate Member of FU Berlin and Humboldt Universität zu Berlin, Berlin, Germany.
⁵² Department of Radiology, Medical College of Wisconsin, Milwaukee, Wisconsin, USA.
⁵³ Institute for Experimental Epileptology and Cognition Research, University of Bonn and University Hospital Bonn, Bonn, Germany.
⁵⁴ Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK.
⁵⁵ Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, California, USA.

PMID: 38949537
PMCID: PMC11215839
DOI: 10.1002/hbm.26768

Brain-age prediction: Systematic evaluation of site effects, and sample age range and size

Yuetong Yu et al. Hum Brain Mapp. 2024.

. 2024 Jul 15;45(10):e26768.

doi: 10.1002/hbm.26768.

Authors

Affiliations

¹ Djavad Mowafaghian Centre for Brain Health, Department of Psychiatry, University of British Columbia, Vancouver, British Columbia, Canada.
² Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, New York, USA.
³ School of Population and Public Health, University of British Columbia, Vancouver, British Columbia, Canada.
⁴ Advanced Research Institute of Multidisciplinary Sciences, School of Medical Technology, School of Life Science, Beijing Institute of Technology, Beijing, China.
⁵ Center for MRI Research, Peking University, Beijing, China.
⁶ School of Psychology, Southwest University, Chongqing, China.
⁷ Laboratory of Neuropsychiatry, Department of Clinical and Behavioral Neurology, IRCCS Santa Lucia Foundation, Rome, Italy.
⁸ Department of Biological Psychology, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands.
⁹ Department of Psychiatry, Indiana University School of Medicine, Indianapolis, Indiana, USA.
¹⁰ Centre for Healthy Brain Ageing (CHeBA), Discipline of Psychiatry and Mental Health, School of Clinical Medicine, University of New South Wales, Sydney, New South Wales, Australia.
¹¹ Department of Psychology, Center for Brain Science, Harvard University, Boston, Massachusetts, USA.
¹² Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.
¹³ Department of Cognitive Neuroscience, Donders Institute for Brain, Cognition and Behaviour, Radboud University Medical Center, Nijmegen, The Netherlands.
¹⁴ Centre for Neuroimaging & Cognitive Genomics (NICOG), Clinical Neuroimaging Laboratory, Galway Neuroscience Centre, College of Medicine Nursing and Health Sciences, University of Galway, Galway, Ireland.
¹⁵ Centre for Neuropsychiatric Genetics and Genomics, Division of Psychological Medicine and Clinical Neurosciences, Cardiff University, Cardiff, UK.
¹⁶ Psychology Clinical Neuroscience Center, Department of Psychology, University of New Mexico, Albuquerque, New Mexico, USA.
¹⁷ Department of Psychiatry and Addiction, Université de Montréal, CHU Ste Justine, Montreal, Quebec, Canada.
¹⁸ Institut des Maladies Neurodégénératives, Université de Bordeaux, Bordeaux, France.
¹⁹ Department of Psychology, Faculty of Social Sciences, Leiden University, Leiden, The Netherlands.
²⁰ Erasmus School of Social and Behavioral Sciences, Erasmus University Rotterdam, Rotterdam, The Netherlands.
²¹ Institute for Translational Psychiatry, University of Münster, Münster, Germany.
²² Department of Psychiatry, The University of Melbourne, Melbourne, Victoria, Australia.
²³ Department of Psychiatry, Amsterdam UMC, Amsterdam, The Netherlands.
²⁴ Faculty of Health, School of Psychology & Counselling, Queensland University of Technology, Brisbane, Queensland, Australia.
²⁵ Department of Mental Health and Addictions, ASST Papa Giovanni XXIII, Bergamo, Italy.
²⁶ Language and Genetics Department, Max Planck Institute for Psycholinguistics, Nijmegen, The Netherlands.
²⁷ Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, The Netherlands.
²⁸ Department of Cognitive Neuroscience, Radboud University Medical Center, Nijmegen, The Netherlands.
²⁹ Department of Human Genetics, Radboud University Medical Center, Nijmegen, The Netherlands.
³⁰ Department of Psychiatry, Tommy Fuss Center for Neuropsychiatric Disease Research, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
³¹ Section for Experimental Psychopathology and Neuroimaging, Department of General Psychiatry, Heidelberg University, Heidelberg, Germany.
³² Department of Psychiatry, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
³³ Brain and Mind Centre, The University of Sydney, Sydney, New South Wales, Australia.
³⁴ Department of Psychology, Utrecht University, Utrecht, The Netherlands.
³⁵ Department of Psychiatry, University Medical Center Utrecht, Utrecht, The Netherlands.
³⁶ Center for Human Development, Departments of Cognitive Science, Psychiatry, and Radiology, University of California, San Diego, California, USA.
³⁷ Department of Radiology, The Ohio State University College of Medicine, Columbus, Ohio, USA.
³⁸ West Region, Institute of Mental Health, Singapore, Singapore.
³⁹ Department of Child and Adolescent Psychiatry and Psychology, Hospital Clínic, IDIBAPS, CIBERSAM, University of Barcelona, Barcelona, Spain.
⁴⁰ Department of Radiology and Imaging Sciences, Indiana University School of Medicine, Indianapolis, Indiana, USA.
⁴¹ School of Clinical Sciences, Centre for Biomedical Technologies, Queensland University of Technology, Brisbane, Queensland, Australia.
⁴² Louis A. Faillace, MD, Department of Psychiatry and Behavioral Sciences, The University of Texas Health Science Center at Houston, Houston, Texas, USA.
⁴³ McConnell Brain Imaging Centre, McGill University, Montreal, Quebec, Canada.
⁴⁴ Department of Psychiatry, CCM, Charite Universitaetsmedizin Berlin, Berlin, Germany.
⁴⁵ Centre for Population Neuroscience and Stratified Medicine (PONS), ISTBI, Fudan University, Shanghai, China.
⁴⁶ Department of Translational Biomedicine and Neuroscience, University of Bari Aldo Moro, Bari, Italy.
⁴⁷ Center for Genomic Medicine, Massachusetts General Hospital, Boston, Massachusetts, USA.
⁴⁸ Center for Precision Psychiatry, Massachusetts General Hospital, Boston, Massachusetts, USA.
⁴⁹ PROMENTA Research Center, Department of Psychology, University of Oslo, Oslo, Norway.
⁵⁰ Department of Developmental Disability Neuropsychiatry, School of Clinical Medicine, University of New South Wales, Sydney, New South Wales, Australia.
⁵¹ Department of Psychiatry and Psychotherapy, Charité Universitätsmedizin Berlin, Corporate Member of FU Berlin and Humboldt Universität zu Berlin, Berlin, Germany.
⁵² Department of Radiology, Medical College of Wisconsin, Milwaukee, Wisconsin, USA.
⁵³ Institute for Experimental Epileptology and Cognition Research, University of Bonn and University Hospital Bonn, Bonn, Germany.
⁵⁴ Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK.
⁵⁵ Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, California, USA.

PMID: 38949537
PMCID: PMC11215839
DOI: 10.1002/hbm.26768

Abstract

Structural neuroimaging data have been used to compute an estimate of the biological age of the brain (brain-age) which has been associated with other biologically and behaviorally meaningful measures of brain development and aging. The ongoing research interest in brain-age has highlighted the need for robust and publicly available brain-age models pre-trained on data from large samples of healthy individuals. To address this need we have previously released a developmental brain-age model. Here we expand this work to develop, empirically validate, and disseminate a pre-trained brain-age model to cover most of the human lifespan. To achieve this, we selected the best-performing model after systematically examining the impact of seven site harmonization strategies, age range, and sample size on brain-age prediction in a discovery sample of brain morphometric measures from 35,683 healthy individuals (age range: 5-90 years; 53.59% female). The pre-trained models were tested for cross-dataset generalizability in an independent sample comprising 2101 healthy individuals (age range: 8-80 years; 55.35% female) and for longitudinal consistency in a further sample comprising 377 healthy individuals (age range: 9-25 years; 49.87% female). This empirical examination yielded the following findings: (1) the accuracy of age prediction from morphometry data was higher when no site harmonization was applied; (2) dividing the discovery sample into two age-bins (5-40 and 40-90 years) provided a better balance between model accuracy and explained age variance than other alternatives; (3) model accuracy for brain-age prediction plateaued at a sample size exceeding 1600 participants. These findings have been incorporated into CentileBrain (https://centilebrain.org/#/brainAGE2), an open-science, web-based platform for individualized neuroimaging metrics.

Keywords: benchmarking; brain aging; brainAGE.

PubMed Disclaimer

Conflict of interest statement

Jair C. Soares reports the following conflicts of interest: ALKERMES (Advisory Board), BOEHRINGER Ingelheim (Consultant), COMPASS Pathways (Research Grant), JOHNSON & JOHNSON (Consultant), LIVANOVA (Consultant), RELMADA (Research Grant), SUNOVION (Research Grant), and Mind Med (Research Grant).

Figures

**FIGURE 1**
Flowchart of brain age model optimization: after conducting the analysis with FreeSurfer and stratifying the samples by sex, the study proceeded as follows. (1) The discovery sample was utilized to evaluate the impact of site‐harmonization strategies and age range. This analysis yielded the optimal site‐harmonization strategy. (2) The independent replication sample was employed to further investigate the influence of age range. The outcome of this analysis led to the determination of the optimal age bins and final models. (3) The independent longitudinal consistency sample was utilized to assess the longitudinal consistency of the pre‐trained optimal models.

**FIGURE 2**
Effect of site harmonization approach on the performance of models derived from repeated cross‐validation in different age bins of the discovery sample. Each bar represents one of the seven site handling methods. CORR, correlation coefficient between brain‐age and chronological age; MAE, mean absolute error between brain‐age and chronological age. Sex‐specific results in Figures S2 and S3.

**FIGURE 3**
Performance metrics derived from the application of the models pre‐trained on different age bins of the discovery sample to the corresponding age bins of the replication sample. CORR values averaged across sexes were 0.68 for 40‐year interval bins; and 0.86 for the full age range of the sample. MAE values averaged across sexes were 5.28 years for 40‐year interval bins; and 8.52 years for the full age range of the sample. Sex‐specific results are presented in Figure S4. CORR, correlation coefficient between brain‐age and chronological age; MAE, mean absolute error between brain‐age and chronological age.

**FIGURE 4**
Model performance as a function of the sample size in the two age bins (5–40 and 40–90 years) of the discovery sample. Model parameters for each bin were obtained by randomly resampling the discovery sample without replacement generating subsets of 200–6000 participants. The results are shown here as averages across sexes and the sex‐specific findings are presented in Figure S6. CORR, correlation coefficient between brain‐age and chronological age; MAE, mean absolute error between brain‐age and chronological age.

**FIGURE 5**
Model performance in longitudinal data. The left panel presents the CORR and MAE values for the first and second MRI scans, while the right panel exhibits the percentage changes (%) in CORR and MAE for the second scan compared to the first scan. The results were generated by employing models that had been trained on discovery samples from each age range division and then applied to the longitudinal consistency sample. CORR, correlation coefficient between brain‐age and chronological age; MAE, mean absolute error between brain age and chronological age.

See this image and copyright information in PMC

References

1. Baecker, L. , Dafflon, J. , da Costa, P. F. , Garcia‐Dias, R. , Vieira, S. , Scarpazza, C. , Calhoun, V. D. , Sato, J. R. , Mechelli, A. , & Pinaya, W. H. L. (2021). Brain age prediction: A comparison between machine learning models using region‐ and voxel‐based morphometric data. Human Brain Mapping, 42(8), 2332–2346. 10.1002/hbm.25368 - DOI - PMC - PubMed
1. Baecker, L. , Garcia‐Dias, R. , Vieira, S. , Scarpazza, C. , & Mechelli, A. (2021). Machine learning for brain age prediction: Introduction to methods and clinical applications. EbioMed, 72, 103600. 10.1016/j.ebiom.2021.103600 - DOI - PMC - PubMed
1. Ball, G. , Kelly, C. E. , Beare, R. , & Seal, M. L. (2021). Individual variation underlying brain age estimates in typical development. NeuroImage, 235, 118036. 10.1016/j.neuroimage.2021.118036 - DOI - PubMed
1. Beck, D. , de Lange, A. G. , Maximov, I. I. , Richard, G. , Andreassen, O. A. , Nordvik, J. E. , & Westlye, L. T. (2021). White matter microstructure across the adult lifespan: A mixed longitudinal and cross‐sectional study using advanced diffusion models and brain‐age prediction. NeuroImage, 224, 117441. 10.1016/j.neuroimage.2020.117441 - DOI - PubMed
1. Beheshti, I. , Ganaie, M. A. , Paliwal, V. , Rastogi, A. , Razzak, I. , & Tanveer, M. (2022). Predicting brain age using machine learning algorithms: A comprehensive evaluation. IEEE Journal of Biomedical and Health Informatics, 26(4), 1432–1440. 10.1109/JBHI.2021.3083187 - DOI - PubMed

MeSH terms

Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions
Actions

Grants and funding

LinkOut - more resources

Full Text Sources
Medical
- MedlinePlus Health Information

Save citation to file

Email citation

Add to Collections

Add to My Bibliography

Your saved search

Create a file for external citation management software

Your RSS Feed

Brain-age prediction: Systematic evaluation of site effects, and sample age range and size

Affiliations

Brain-age prediction: Systematic evaluation of site effects, and sample age range and size

Authors

Affiliations

Abstract

Conflict of interest statement

Figures

References

MeSH terms

Grants and funding

LinkOut - more resources

Full Text Sources

Medical