The DOI matches its Crossref record; 136 of the 136 references it cites were found in a registry or an index.
Brain–phenotype models fail for individuals who defy sample stereotypes
Open accessAbstract
Individual differences in brain functional organization track a range of traits, symptoms and behaviours 1–12 . So far, work modelling linear brain–phenotype relationships has assumed that a single such relationship generalizes across all individuals, but models do not work equally well in all participants 13,14 . A better understanding of in whom models fail and why is crucial to revealing robust, useful and unbiased brain–phenotype relationships. To this end, here we related brain activity to phenotype using predictive models—trained and tested on independent data to ensure generalizability 15 —and examined model failure. We applied this data-driven approach to a range of neurocognitive measures in a new, clinically and demographically heterogeneous dataset, with the results replicated in two independent, publicly available datasets 16,17 . Across all three datasets, we find that models reflect not unitary cognitive constructs, but rather neurocognitive scores intertwined with sociodemographic and clinical covariates; that is, models reflect stereotypical profiles, and fail when applied to individuals who defy them. Model failure is reliable, phenotype specific and generalizable across datasets. Together, these results highlight the pitfalls of a one-size-fits-all modelling approach and the effect of biased phenotypic measures 18–20 on the interpretation and utility of resulting brain–phenotype models. We present a framework to address these issues so that such models may reveal the neural circuits that underlie specific phenotypes and ultimately identify individualized neural targets for clinical intervention.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures




![Extended Data Fig. 1 Model performance and misclassification frequency are robust to analysis approach. (a) Classification accuracy for each phenotypic measure using FC calculated from all in-scanner conditions in the Yale dataset, and five different analysis pipelines: an alternative, 368-node parcellation for FC matrix generation, two alternative classification algorithms (ensemble of weak learners and neural network), an alternative phenotypic binarization threshold (mean split), and an alternative (10-fold) cross-validation approach (see Methods for additional description of each analysis). Box plot line and hinges represent median and quartiles, respectively; whiskers extend to most extreme non-outliers; outliers plotted individually (+). Number of classified individuals and size of training sample same as in main analyses (see Supplementary Table 4) for all analyses except mean split (4 measures [see below], number classified = 109-127, training sample size = 72-82) and 10-fold (number classified same as in main analyses, training sample size = 34-110). r1, rest 1; r2, rest 2; grad, gradual-onset continuous performance task; sst, stop signal task; gfc, general FC. (b) Misclassification frequency (MF), averaged across in-scanner conditions and phenotypic measures to derive a single value per participant, compared between each alternative analysis and main-text analyses. rs, two-tailed rank correlation, n = 128-129, P values FDR adjusted. Note that phenotype mean split is equivalent to mean ± 1/3 × s.d. for scaled scores; mean split-based model accuracy is not reported for these measures, nor are they included in the calculation of misclassification frequency. Given the limited mean split-based results, we repeated this analysis in the HCP data, with comparable results (mean misclassification frequency rs = 0.86, P < 0.0001). 10-fold results reflect 1,000 analysis iterations per phenotypic measure and in-scanner condition (50 per cross-validation partition); all other analyses reflect 100 iterations. In this and all subsequent figures: BNT, Boston Naming Test; WRAT, Wide Range Achievement Test; VL, verbal learning; FW, finger windows; LN, letter–number sequencing; Trails, trail making; VF, verbal fluency; CW, colour–word interference; 20Q, 20 questions; Vocab, vocabulary; MR, matrix reasoning.](https://figures.cochat.ai/paper-figures/2266db0068a8453193d98113a2e1bcb6/brainphenotype-models-fail-for-individuals-who-defy-sample-stereotypes-figure-5.jpg)
![Extended Data Fig. 2 Replication of classification and internal validation results in the UCLA CNP dataset. Results as presented in Fig. 1b, Fig. 2, and Fig. 4a. (a) Significance via one-tailed permutation testing (as in Fig. 1b); P values FDR adjusted (3 tests). For sample sizes, see Supplementary Table 5. (b) As in Yale data, mean of permuted distribution did not significantly differ from 0.5 (all P > 0.05, FDR adjusted [3 tests]), mean and median of original data-based distribution significantly differed from 0.5 (all P < 0.0001, FDR adjusted [6 tests] via two-tailed t- and Wilcoxon signed-rank tests), and the misclassification frequency distributions for original and permuted analyses significantly differed for each measure (all P < 0.0001, FDR adjusted [3 tests] via two-tailed, two-sample Kolmogorov–Smirnov test). (c) *P < 0.0001, FDR adjusted (3 tests) via paired, one-tailed Wilcoxon signed-rank test (as in Fig. 2b). (d) Given the small number of included measures, we present these results only for consistency with main analyses. As in Fig. 2c, different participants excluded for intermediate, missing, or outlier scores for each measure; number of correlated participants for each measure pair ranges from misclassification frequency: 103-138, measure: 162-163. (e) Results as presented in Fig. 4a. Covariate relationships presented if they were significantly related to misclassification frequency in low or high scorers (P < 0.05, adjusted), or if they were significantly related to misclassification frequency in Yale analyses (education, race) to demonstrate comparable trends. All P values FDR adjusted (22 tests). For full results and relationship of covariates to mean score, as well as sample sizes, see Supplementary Tables 9 and 10. PAMret, paired associates memory task, retrieval; SST, stop signal task; MF, misclassification frequency.](https://figures.cochat.ai/paper-figures/7686098f3057487e9f79839801c9d90d/brainphenotype-models-fail-for-individuals-who-defy-sample-stereotypes-figure-6.jpg)
![Extended Data Fig. 3 Replication of classification, internal validation and external validation results in the HCP dataset. Results as presented in Fig. 1b, Fig. 2a, b, Fig. 3a, and Fig. 4a. Given the large HCP sample size, 10-fold cross-validation was used (20 partitions, 50 subsampling iterations each), with the requirement that family members be assigned to the same fold. Given that only two measures were classified, we omit measure versus misclassification frequency similarity and hierarchical linkage analyses. (a) Significance via one-tailed permutation testing (as in Fig. 1b); P values FDR adjusted (2 tests). For sample sizes, see Supplementary Table 6. (b) Permuted distribution means significantly differed from 0.5 via two-tailed, one-sample t-test (cIQ mean = 0.491 [P < 0.0001], fIQ mean = 0.498 [P = 0.04], both FDR adjusted [2 tests]). All else as in Yale and UCLA analyses: mean and median of original data-based distribution significantly differed from 0.5 (all P < 0.0001, FDR adjusted [4 tests] via two-tailed t- and Wilcoxon signed-rank tests), and the misclassification frequency distributions for original and permuted analyses significantly differed for each measure (all P < 0.0001, FDR adjusted [2 tests] via two-tailed, two-sample Kolmogorov–Smirnov test). MF, misclassification frequency. (c) **P = 0.001, ****P < 0.0001, FDR adjusted (2 tests) via paired, one-tailed Wilcoxon signed-rank test (as in Fig. 2b). (d) Results presented as in Fig. 3a. Bar height, grand mean; error bars, s.d. *P < 0.0001, FDR adjusted (9 tests) via two-tailed, nested ANOVA. For each classified measure (cIQ/vocabulary and fIQ/MR for HCP/Yale), six models were trained: 1 using all Yale participants, 1 using Yale CCP, 1 using Yale MCP (see Fig. 3 legend for training set sizes), 1 using all HCP participants (number of participants used for training after excluding intermediate and outlier scores and subsampling to balance classes: 230 and 350 for crystallized and fluid measures, respectively), 1 using HCP CCP (168, 216), and 1 using HCP MCP (62, 134). See Supplementary Tables 4 and 6 for test-set sizes. (e) Results as presented in Fig. 4a. Covariate relationships presented if they were significantly related to misclassification frequency in low or high scorers (P < 0.05, adjusted). For full results and relationship of covariates to mean score, as well as sample sizes, see Supplementary Tables 9 and 10. ****P < 0.0001; all P values FDR adjusted (22 tests).](https://figures.cochat.ai/paper-figures/8cfa107bc5f04067a87312118f2c9cd4/brainphenotype-models-fail-for-individuals-who-defy-sample-stereotypes-figure-7.jpg)




Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The FCS alterations in these regions have been proven to be related to the regulation of widespread cognitive, emotional, and executive control functions in patients with MDD [6, 42-50].”
From Mapping neurophysiological subtypes of major depressive disorder using normative models of the functional connectome (2023) · cites this paper as [48]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“A recent Nature paper reported that the confounding covariates, especially age and head motion (FD), were associated with worse model accuracy [11] in functional connectivity based neuroimaging classification.”
From Confound Controlled Multimodal Neuroimaging Data Fusion and Its Application to Developmental Disorders (2025) · cites this paper as [11]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“The two-step process does not guarantee joint optimum and may result in worse performance in either fusion or regression procedures [10, 11].”
From Confound Controlled Multimodal Neuroimaging Data Fusion and Its Application to Developmental Disorders (2025) · cites this paper as [11]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The assessment and analysis of handedness: The Edinburgh inventory
Oldfield, R. C. (1971) · Neuropsychologia · doi:10.1016/0028-3932(71)90067-4 · Cited by 35,900
The Pittsburgh Sleep Quality Index: a new instrument for psychiatric practice and research
Buysse, D. J., Reynolds, C. F., Monk, T. H., Berman, S. R., & Kupfer, D. J. (1989) · Psychiatry Research · doi:10.1016/0165-1781(89)90047-4 · Cited by 35,234
A Global Measure of Perceived Stress
Cohen, S., Kamarck, T., & Mermelstein, R. (1983) · Journal of Health and Social Behavior · doi:10.2307/2136404 · Cited by 32,807
Brainard, D. H. (1997) · Spatial Vision · doi:10.1163/156856897x00357 · Cited by 19,702
Breiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325
Advances in functional and structural MR image analysis and implementation as FSL
Smith, S. M., Jenkinson, M., Woolrich, M. W., Beckmann, C. F., Behrens, T. E. J., Johansen-Berg, H., Bannister, P. R., De Luca, M., Drobnjak, I., Flitney, D. E., et al. (2004) · NeuroImage · doi:10.1016/j.neuroimage.2004.07.051 · Cited by 13,630
The weirdest people in the world?
Henrich, J., Heine, S. J., & Norenzayan, A. (2010) · Behavioral and Brain Sciences · doi:10.1017/s0140525x0999152x · Cited by 12,641
Measuring individual differences in empathy: Evidence for a multidimensional approach.
Davis, M. H. (1983) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.44.1.113 · Cited by 10,272
(1998) · PubMed · Cited by 10,216
The organization of the human cerebral cortex estimated by intrinsic functional connectivity
Thomas Yeo, B. T., Krienen, F. M., Sepulcre, J., Sabuncu, M. R., Lashkari, D., Hollinshead, M., Roffman, J. L., Smoller, J. W., Zöllei, L., Polimeni, J. R., et al. (2011) · Journal of Neurophysiology · doi:10.1152/jn.00338.2011 · Cited by 9,182
Research works printed but not linked: 7
- Wang, L.-I. Race as proxy: situational racism and self-fulfilling stereotypes. DePaul Law Rev. 53, 1013–1110 (2004).
- Wilkinson, G. S. & Robertson, G. J. Wide Range Achievement Test (WRAT5) (Pearson, 2017).
- Derogatis, L. R. Brief Symptom Inventory (Pearson, 1993).
- Watson, D. & Clark, L. The PANAS-X manual for the Positive and Negative Affect Schedule-Expanded Form. Iowa Res. Online 277, 1–27 (1999).
- Sheslow, D. & Adams, W. Wide Range Assessment of Memory and Learning 2nd edn (Pearson, 2003).
- Frackowiak, R. S. J. et al. (eds) Human Brain Function (Academic Press, 2004).
- First, M., Spitzer, R., Gibbon, M. & Williams, J. Structured Clinical Interview for DSM-IV-TR Axis I Disorders, Research Version, Patient Edition (Biometrics Research, New York State Psychiatric Institute, 2002).
Cited by
Confronting racially exclusionary practices in the acquisition and analyses of neuroimaging data
Ricard, J. A., Parker, T., Dhamala, E., Kwasa, J. A. C., Allsop, A. S., & Holmes, A. J. (2022) · Nature Neuroscience · doi:10.1038/s41593-022-01218-y · Cited by 177
Evidence for embracing normative modeling
Rutherford, S., Barkema, P., Tso, I. F., Sripada, C., Beckmann, C. F., Ruhe, H. G., & Marquand, A. F. (2023) · eLife · doi:10.7554/elife.85082 · Cited by 175
A Systematic Evaluation of Machine Learning–Based Biomarkers for Major Depressive Disorder
Winter, N. R., Blanke, J., Leenings, R., Ernsting, J., Fisch, L., Sarink, K., Barkhau, C., Emden, D., Thiel, K., Flinkenflügel, K., et al. (2024) · JAMA Psychiatry · doi:10.1001/jamapsychiatry.2023.5083 · Cited by 157
Factors associated with healthy aging in Latin American populations
Santamaria-Garcia, H., Sainz-Ballesteros, A., Hernandez, H., Moguilner, S., Maito, M., Ochoa-Rosales, C., Corley, M., Valcour, V., Miranda, J. J., Lawlor, B., et al. (2023) · Nature Medicine · doi:10.1038/s41591-023-02495-1 · Cited by 141
Sun, X., Sun, J., Lu, X., Dong, Q., Zhang, L., Wang, W., Liu, J., Ma, Q., Wang, X., Wei, D., et al. (2023) · Biological Psychiatry · doi:10.1016/j.biopsych.2023.05.021 · Cited by 129
Metadata
- Authors
- Greene, A. S., Shen, X., Noble, S., Horien, C., Hahn, C. A., Arora, J., Tokoglu, F., Spann, M. N., Carrión, C. I., Barron, D. S., Sanacora, G., Srihari, V. H., Woods, S. W., Scheinost, D., & Constable, R. T.
- Affiliations
- Yale University (US)
- Columbia University Irving Medical Center (US)
- Brigham and Women's Hospital (US)
- Corresponding author
- Greene, Abigail S.
- Constable, R. Todd
- ORCID
- Venue
- Nature
- Published
- 2022-08-24
- Volume
- 609
- Issue
- 7925
- Pages
- 109-118
- ISSN
- 0028-0836 (ISSN-L)
- 1476-4687
- PMC
- PMC9433326
- OpenAlex
- W4293004881
- Semantic Scholar
- d6715d38bdf3f82b173c06d8008f5e0ff6aa9961
- Cited by
- 167
- References
- 129
- Citations by year
- 2026: 26 · 2025: 38 · 2024: 59 · 2023: 36 · 2022: 8
- FWCI
- 18.17
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Nature (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Funders
- National Institutes of Health (5u54mh091657-05, 1U54‐MH‐091657, UL1TR001863, TL1TR001864)
- McDonnell Center for Systems Neuroscience (1U54MH091657)
- National Institute on Aging (P30AG066508)
- National Institute of Mental Health (R01MH103831, R01MH121095, MH121095, 1U54 MH091657, U54-MH091657, T32 MH 19961, T32MH019961)
- National Institute of General Medical Sciences (T32GM007205)
- NIH Blueprint for Neuroscience Research (1U54-MH-091657)
- National Center for Advancing Translational Sciences
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Functional Brain Connectivity Studies
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Advanced Neuroimaging Techniques and Applications
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neural and Behavioral Psychology Studies
- Keywords
- model failure, individual differences, neurocognitive measures, clinical covariates, predictive modeling, generalizability, neural circuits
- MeSH terms
- Mental Status and Dementia Tests, Brain, Computer Simulation, Humans, Individuality, Models, Biological, Phenotype, Stereotyping, Datasets as Topic
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Brain–phenotype models fail for individuals who defy sample stereotypes. https://app.cochat.ai/papers/10.1038/s41586-022-05118-w
- The paper
- Greene, A. S., Shen, X., Noble, S., Horien, C., Hahn, C. A., Arora, J., Tokoglu, F., Spann, M. N., Carrión, C. I., Barron, D. S., Sanacora, G., Srihari, V. H., Woods, S. W., Scheinost, D., & Constable, R. T. (2022). Brain–phenotype models fail for individuals who defy sample stereotypes. Nature. https://doi.org/10.1038/s41586-022-05118-w
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.