TY - JOUR
T1 - Normative modelling of brain morphometry across the lifespan with CentileBrain
T2 - algorithm benchmarking and model optimisation
AU - Ge, Ruiyang
AU - Yu, Yuetong
AU - Qi, Yi Xuan
AU - Fan, Yu nan
AU - Chen, Shiyu
AU - Gao, Chuntong
AU - Haas, Shalaila S.
AU - New, Faye
AU - Boomsma, Dorret I.
AU - Brodaty, Henry
AU - Brouwer, Rachel M.
AU - Buckner, Randy
AU - Caseras, Xavier
AU - Crivello, Fabrice
AU - Crone, Eveline A.
AU - Erk, Susanne
AU - Fisher, Simon E.
AU - Franke, Barbara
AU - Glahn, David C.
AU - Dannlowski, Udo
AU - Grotegerd, Dominik
AU - Gruber, Oliver
AU - Hulshoff Pol, Hilleke E.
AU - Schumann, Gunter
AU - Tamnes, Christian K.
AU - Walter, Henrik
AU - Wierenga, Lara M.
AU - Jahanshad, Neda
AU - Thompson, Paul M.
AU - Frangou, Sophia
AU - Agartz, Ingrid
AU - Asherson, Philip
AU - Ayesa-Arriola, Rosa
AU - Banaj, Nerisa
AU - Banaschewski, Tobias
AU - Baumeister, Sarah
AU - Bertolino, Alessandro
AU - Borgwardt, Stefan
AU - Bourque, Josiane
AU - Brandeis, Daniel
AU - Breier, Alan
AU - Buitelaar, Jan K.
AU - Cannon, Dara M.
AU - Cervenka, Simon
AU - Conrod, Patricia J.
AU - Crespo-Facorro, Benedicto
AU - Davey, Christopher G.
AU - Kahn, René S.
AU - Sommer, Iris E.
AU - van Haren, Neeltje EM
N1 - Publisher Copyright:
© 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license
PY - 2024/3
Y1 - 2024/3
N2 - The value of normative models in research and clinical practice relies on their robustness and a systematic comparison of different modelling algorithms and parameters; however, this has not been done to date. We aimed to identify the optimal approach for normative modelling of brain morphometric data through systematic empirical benchmarking, by quantifying the accuracy of different algorithms and identifying parameters that optimised model performance. We developed this framework with regional morphometric data from 37 407 healthy individuals (53% female and 47% male; aged 3–90 years) from 87 datasets from Europe, Australia, the USA, South Africa, and east Asia following a comparative evaluation of eight algorithms and multiple covariate combinations pertaining to image acquisition and quality, parcellation software versions, global neuroimaging measures, and longitudinal stability. The multivariate fractional polynomial regression (MFPR) emerged as the preferred algorithm, optimised with non-linear polynomials for age and linear effects of global measures as covariates. The MFPR models showed excellent accuracy across the lifespan and within distinct age-bins and longitudinal stability over a 2-year period. The performance of all MFPR models plateaued at sample sizes exceeding 3000 study participants. This model can inform about the biological and behavioural implications of deviations from typical age-related neuroanatomical changes and support future study designs. The model and scripts described here are freely available through CentileBrain.
AB - The value of normative models in research and clinical practice relies on their robustness and a systematic comparison of different modelling algorithms and parameters; however, this has not been done to date. We aimed to identify the optimal approach for normative modelling of brain morphometric data through systematic empirical benchmarking, by quantifying the accuracy of different algorithms and identifying parameters that optimised model performance. We developed this framework with regional morphometric data from 37 407 healthy individuals (53% female and 47% male; aged 3–90 years) from 87 datasets from Europe, Australia, the USA, South Africa, and east Asia following a comparative evaluation of eight algorithms and multiple covariate combinations pertaining to image acquisition and quality, parcellation software versions, global neuroimaging measures, and longitudinal stability. The multivariate fractional polynomial regression (MFPR) emerged as the preferred algorithm, optimised with non-linear polynomials for age and linear effects of global measures as covariates. The MFPR models showed excellent accuracy across the lifespan and within distinct age-bins and longitudinal stability over a 2-year period. The performance of all MFPR models plateaued at sample sizes exceeding 3000 study participants. This model can inform about the biological and behavioural implications of deviations from typical age-related neuroanatomical changes and support future study designs. The model and scripts described here are freely available through CentileBrain.
UR - http://www.scopus.com/inward/record.url?scp=85185553011&partnerID=8YFLogxK
U2 - 10.1016/S2589-7500(23)00250-9
DO - 10.1016/S2589-7500(23)00250-9
M3 - Review article
C2 - 38395541
AN - SCOPUS:85185553011
VL - 6
SP - e211-e221
JO - The Lancet Digital Health
JF - The Lancet Digital Health
IS - 3
ER -