Abstract
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.
| Original language | English |
|---|---|
| Pages (from-to) | e211-e221 |
| Journal | The Lancet Digital Health |
| Volume | 6 |
| Issue number | 3 |
| DOIs | |
| Publication status | Published - Mar 2024 |
Bibliographical note
Publisher Copyright:© 2024 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license
Funding
| Funders | Funder number |
|---|---|
| Biobanking and Biomolecular Resources Research Infrastructure | 84.021.00, 184–033–111 |
| Dutch Health Research Council | 10–000–1001 |
| Organization for Health Research and Development | 400–07–080, 481–08–011, 451–04–034, 463–06–001, 912–10–020, 31160008, 400–05–717, 904–61–193, 480–15–001/674, 911–09–032, 016–115–035, 056–32–010, 480–04–004, 024–001–003, 904–61–090, 985–10–002 |
| National Institutes of Health | |
| National Center for Advancing Translational Sciences | UL1 TR000153, R01CA101318, R01MH090553, R01MH116147, P30AG10133, U54EB020403, R01MH117014, R01AG19771, T32MH122394, U24RR025736-01, R01MH104284, U24RR021992, RC2DA029475, U24RR025761, R01HD050735, R01MH113619, R01MH042191, U24RR025736, 1009064, 496682 |
| Icahn School of Medicine at Mount Sinai | UL1TR004419 |
| Icahn School of Medicine at Mount Sinai | |
| Horizon 2020 Framework Programme | 667302, 643051 |
| European Research Council | ERC–230374, ED1615 |
| National Health and Medical Research Council | 496682, 1009064 |
| Russian Foundation for Basic Research | 20–013–00748 |
| Bundesministerium für Bildung und Forschung | 01ZZ0403, 01ZZ0103, 01ZZ9603 |
| Nederlandse Organisatie voor Wetenschappelijk Onderzoek | 51–02–061, MagW 480–04–004, 51–02–062, NWO 433–09–220, 433–09–229, NW0-SP 56–464–14192, 91619115, 016–130–669 |
| Knut och Alice Wallenbergs Stiftelse | |
| Vetenskapsrådet | K2008–62P–20597–01–3, 521–2014–3487, K2012–61X–15078–09–3, 2017–00949, 523–2014–3467, K2010–62X–15078–07–2, K2007–62X–15077–04–1 |
| Instituto de Salud Carlos III | PI060507, PI050427, PI14/00639, PI020499, PI14/00918 |
| Seventh Framework Programme | 602805, 602450, 278948, 603016 |
| University of British Columbia | |
| Norges Forskningsråd | 223273 |
| Helse Sør-Øst RHF | 2013–054, 2017–112, 2019–107, 2014–097 |
| UK Medical Research Council | G0500092 |
| Instituto de Investigación Marqués de Valdecilla | NCT0235832, API07/011, NCT02534363 |