Evidence for embracing normative modeling

  1. Saige Rutherford  Is a corresponding author
  2. Pieter Barkema
  3. Ivy F Tso
  4. Chandra Sripada
  5. Christian F Beckmann
  6. Henricus G Ruhe
  7. Andre F Marquand
  1. Department of Cognitive Neuroscience, Radboud University Nijmegen Medical Centre, Netherlands
  2. Donders Institute, Radboud University Nijmegen, Netherlands
  3. Department of Psychiatry, University of Michigan-Ann Arbor, United States
  4. Department of Psychology, University of Michigan-Ann Arbor, United States
  5. Department of Philosophy, University of Michigan-Ann Arbor, United States
  6. Center for Functional MRI of the Brain (FMRIB), Nuffield Department for Clinical Neuroscience, Welcome Centre for Integrative Neuroimaging, Oxford University, United Kingdom
  7. Department of Psychiatry, Radboud University Nijmegen Medical Centre, Netherlands
5 figures, 2 tables and 5 additional files

Figures

Overview of workflow.

(A) Datasets included the Human Connectome Project (young adult) study, the University of Michigan schizophrenia study, and the Center for Biomedical Research Excellence (COBRE) schizophrenia study. …

Functional brain network normative modeling.

(A) Age distribution per scanning site in the train, test, and transfer data partitions and across the full sample (train +test). (B) The Yeo-17 brain network atlas is used to generate connectomes. …

Functional normative model evaluation metrics.

(A) Explained variance per network pair across the test set (top), and both transfer sets (patients – middle, controls – bottom). Networks were clustered for visualization to show similar variance …

Group difference testing evaluation.

(A) Significant group differences in the deviation score models, (top left) functional brain network deviation, and (top right) cortical thickness deviation scores. The raw data, either cortical …

Benchmark task two multivariate prediction Classification evaluation.

(A) Support vector classification (SVC) using cortical thickness deviation scores as input features (most accurate model). (B) SVC using cortical thickness (residualized of sex and linear/quadratic …

Tables

Table 1
Dataset inclusion and sample overview.
Cortical ThicknessFunctional Networks
StudyBenchmark TaskNAge
(m, s.d.)
F, M (%)NAge
(m, s.d.)
F, M (%)
HCPRegression – predicting cognition52928.8, 3.653.4, 46.649928.9, 3.654.3, 45.6
COBREClassification & Group Difference12437.0, 12.724.2, 75.812135.4, 12.423.1, 76.9
UMichClassification & Group Difference8932.6, 9.650.6, 49.38733.0, 10.150.6, 49.3
Table 2
Benchmarking results.

Deviation (Z) score column shows the performance using deviation scores (AUC for classification, the total number of regions with significant group differences FDR-corrected p<0.05 for case versus …

BenchmarkModalityNormative ModelingDeviation Score DataRaw DataPerformanceDifference
Group DifferenceCortical thickness117/1870/187117*
Group DifferenceFunctional Networks50/1360/13650*
ClassificationCortical thickness0.870.430.44*
ClassificationFunctional Networks0.690.680.01
RegressionCortical thickness0.6990.708–0.008
RegressionFunctional Networks0.8770.890–0.013

Additional files

Supplementary file 1

Functional Normative Model Demographics.

Description: For each included site, we show the sample size (N), age (mean, standard deviation), and sex distribution (Female/Male percent) in the training set (shown in blue) and testing set (shown in green) of the normative models of functional connectivity between large scale resting-state brain networks from the Yeo 17 network atlas.

https://cdn.elifesciences.org/articles/85082/elife-85082-supp1-v2.xlsx
Supplementary file 2

Surface Area Normative Model Demographics.

Description: For each included site, we show the sample size (N), age (mean, standard deviation), and sex distribution (Female/Male percent) of the normative models of surface area extracted for all regions of interest in the Destrieux Freesurfer atlas.

https://cdn.elifesciences.org/articles/85082/elife-85082-supp2-v2.xlsx
Supplementary file 3

Structural Group Difference Testing Statistics.

Description: We show for all cortical thickness and subcortical volume from the Destrieux and aseg Freesurfer atlases regions of interest (ROIs from a two-sample t-test between Schizophrenia versus Healthy Controls) the t-statistic (T-stat), False Discovery Rate corrected p-value (FDRcorr_pvalue), and uncorrected p-value (uncorr_pvalue) for both the raw data (shown in green) and the deviation scores (shown in blue).

https://cdn.elifesciences.org/articles/85082/elife-85082-supp3-v2.xlsx
Supplementary file 4

Functional Connectivity Group Difference Testing Statistics.

Description: We show for all Yeo-17 between network connectivity regions of interest (ROIs) from a two-sample t-test between Schizophrenia versus Healthy Controls the t-statistic (T-stat), False Discovery Rate corrected p-value (FDRcorr_pvalue), and uncorrected p-value (uncorr_pvalue) for both the raw data (shown in green) and the deviation scores (shown in blue).

https://cdn.elifesciences.org/articles/85082/elife-85082-supp4-v2.xlsx
MDAR checklist
https://cdn.elifesciences.org/articles/85082/elife-85082-mdarchecklist1-v2.pdf

Download links