The normative modeling framework for computational psychiatry

Rutherford, Saige; Kia, Seyed Mostafa; Wolfers, Thomas; Fraza, Charlotte; Zabihi, Mariam; Dinga, Richard; Berthet, Pierre; Worker, Amanda; Verdi, Serena; Ruhé, Henricus G.; Beckmann, Christian F.; Marquand, André F.

doi:10.1038/s41596-022-00696-5

Cited by 107 publications

(101 citation statements)

References 79 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We estimated the normative models using python version 3.8 ( https://www.python.org/ ), and the pcntoolkit version 0.21 ( Rutherford et al, 2022 ). We used the Bayesian linear regression (BLR) algorithm within the pcntoolkit ( Fraza et al, 2021 , Huertas et al, 2017 ) where we aimed to predict each brain-derived measures using age and sex as covariates and applied common B-spline basis expansion to the age variable with cubic splines with three evenly spaced knot points.…”

Section: Methodsmentioning

confidence: 99%

Deviations from normative brain white and gray matter structure are associated with psychopathology in youth

Kjelkenes

Wolfers

Alnæs

et al. 2022

Developmental Cognitive Neuroscience

Self Cite

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Deviations from normative brain white and gray matter structure are associated with psychopathology in youth

Kjelkenes

Wolfers

Alnæs

et al. 2022

Developmental Cognitive Neuroscience

Self Cite

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

“…Data harmonization is a prerequisite step in neuroimaging studies with data from multiple sites (Shinohara et al, 2017). Several methods have been developed to harmonize data from different sites, including ComBat and its variants, normative modelling, as well as deep learning based algorithms that transfer the data from different sites into a common, comparable space (Fortin et al, 2017; Fortin et al, 2018; Yu et al, 2018; Dewey et al, 2019; Kia et al, 2020; Moyer et al, 2020; Bayer et al, 2021; Liu et al, 2021; Zuo et al, 2021; Rutherford et al, 2022; Sun et al, 2022). Particularly, ComBat and its variants have been successfully applied to a variety of neuroimaging studies to harmonize diffusion tensor imaging measures, cortical thickness, regional volume measures, and functional connectivity measures (Fortin et al, 2017; Fortin et al, 2018; Yu et al, 2018).…”

Section: Discussionmentioning

confidence: 99%

“…Normative modelling uses percentiles or z-scores to chart the variation of one or several targeting variables orthogonal to the variation of other covariates. Instead of removing site effects from data as a data preprocessing step, normative modelling models site variance as part of the normative model (Kia et al, 2020; Bayer et al, 2021; Rutherford et al, 2022). However, the computational cost and complexity of the model limit its current use to low dimensional imaging data.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Multiscale functional connectivity patterns of the aging brain learned from rsfMRI data of 4,259 individuals of the multi-cohort iSTAGING study

Zhou

Srinivasan

et al. 2022

Preprint

View full text Add to dashboard Cite

To learn multiscale functional connectivity patterns of the aging brain, we built a brain age prediction model of functional connectivity measures at seven scales on a large fMRI dataset, consisting of resting-state fMRI scans of 4259 individuals with a wide age range (22 to 97 years, with an average of 63) from five cohorts. We computed multiscale functional connectivity measures of individual subjects using a personalized functional network computational method, harmonized the functional connectivity measures of subjects from multiple datasets in order to build a functional brain age model, and finally evaluated how functional brain age gap correlated with cognitive measures of individual subjects. Our study has revealed that functional connectivity measures at multiple scales were more informative than those at any single scale for the brain age prediction, the data harmonization significantly improved the brain age prediction performance, and harmonization in the tangent space worked better than in the original space. Moreover, brain age gap scores of individual subjects derived from the brain age prediction model were significantly correlated with clinical and cognitive measures. Overall, these results demonstrated that multiscale functional connectivity patterns learned from a large-scale multi-site rsfMRI dataset were informative for characterizing the aging brain and the derived brain age gap was predictive of cognitive and clinical measures.

show abstract

“…Through building a normative model on a large-scale healthy population, brain abnormalities of individual patients can be quantified by examining their statistical differences from the distribution of the norm. Gaussian process (GP) regressionbased normative modeling has been increasingly applied to quantify individual deviations and dissect neurobiological heterogeneity in various psychiatric disorders [124]. With this tool, an association was successfully discovered between transdiagnostic dimensions of psychopathology and individual's unique deviations from normative neurodevelopment in brain structure [75].…”

Section: Supervised and Unsupervised Learningmentioning

confidence: 99%

Modern Views of Machine Learning for Precision Psychiatry

Chen¹,

Kulkarni²,

Galatzer‐Levy³

et al. 2022

Preprint

View full text Add to dashboard Cite

In light of the NIMH’s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of the ML methodologies and applications by combining neuroimaging, neuromodulation and advanced mobile technologies in psychiatry practice. Additionally, we review the role of ML in molecular phenotyping, cross-species biomarker identification in precision psychiatry. We further discuss explainable AI (XAI) and causality testing in a closed-human-in-the-loop manner, and highlight the ML potential in multimedia information extraction and multimodal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.

show abstract

The normative modeling framework for computational psychiatry

Cited by 107 publications

References 79 publications

Deviations from normative brain white and gray matter structure are associated with psychopathology in youth

Deviations from normative brain white and gray matter structure are associated with psychopathology in youth

Multiscale functional connectivity patterns of the aging brain learned from rsfMRI data of 4,259 individuals of the multi-cohort iSTAGING study

Modern Views of Machine Learning for Precision Psychiatry

Contact Info

Product

Resources

About