(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. …
(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. …
(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 …
(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 …
Cortical Thickness | Functional Networks | ||||||
---|---|---|---|---|---|---|---|
Study | Benchmark Task | N | Age (m, s.d.) | F, M (%) | N | Age (m, s.d.) | F, M (%) |
HCP | Regression – predicting cognition | 529 | 28.8, 3.6 | 53.4, 46.6 | 499 | 28.9, 3.6 | 54.3, 45.6 |
COBRE | Classification & Group Difference | 124 | 37.0, 12.7 | 24.2, 75.8 | 121 | 35.4, 12.4 | 23.1, 76.9 |
UMich | Classification & Group Difference | 89 | 32.6, 9.6 | 50.6, 49.3 | 87 | 33.0, 10.1 | 50.6, 49.3 |
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 …
Benchmark | Modality | Normative ModelingDeviation Score Data | Raw Data | PerformanceDifference |
---|---|---|---|---|
Group Difference | Cortical thickness | 117/187 | 0/187 | 117* |
Group Difference | Functional Networks | 50/136 | 0/136 | 50* |
Classification | Cortical thickness | 0.87 | 0.43 | 0.44* |
Classification | Functional Networks | 0.69 | 0.68 | 0.01 |
Regression | Cortical thickness | 0.699 | 0.708 | –0.008 |
Regression | Functional Networks | 0.877 | 0.890 | –0.013 |
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.
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.
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).
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).