Using normative models pre-trained on cross-sectional data to evaluate intra-individual longitudinal changes in neuroimaging data
- Department of Complex Systems, Institute of Computer Science of the Czech Academy of Sciences, Czech Republic
- Department of Cybernetics, Czech Technical University in Prague, Czech Republic
- National Institute of Mental Health, Czech Republic
- Donders Institute for Brain, Cognition and Behaviour, Netherlands
- Max Planck Institute for Research on Collective Goods, Germany
- University of Cologne, Germany
- Third faculty of medicine, Charles University, Czech Republic
Figures
Figure 1
Visualisations of the core assumptions of normative modelling.
(A) The parameters of the fitted normative model are independent of the time of sampling. (B) People of the same age are comparable irrespective of their year of birth (datasets sampled at different times can be combined).
Figure 2
Simulated detection rate of a true disruption for various values of autocorrelation (individual subplots) comparing the performance of our z-diff method against the naïve subtraction of -scores.
The right column highlights the false-positive rate across various degrees of autocorrelation for the two approaches. We use and θ = 0.05.
Figure 3
The overview of the analytical pipeline for our schizophrenia patients: First, data are preprocessed using FreeSurfer’s longitudinal pipeline.
Subsequently, the pre-trained models are adjusted to a local sample of healthy controls. The site-specific measurement noise variance in healthy subjects is estimated using held-out controls, and finally, the z-diff score is computed.
Figure 4
The effect of preprocessing across all subjects and image-derived phenotypes (IDPs).
(A) Cross-sectional preprocessing: Heatmap of the difference of the original -scores () on held-out controls. (B) Longitudinal preprocessing: Heatmap of the difference of the original -scores () on held-out controls. (C) Histogram of the average () across all IDPs stratified by health status and preprocessing. (D) Histogram of the average () of each subject stratified by health status and preprocessing.
Figure 5
Cross-sectional results for each visit separately: p-Values of Mann-Whitney U test between patients and held-out controls surviving Benjamini-Hochberg correction.
The sign indicates the direction of change (negative means lower thickness in patients).
Figure 6
Regions significantly changed between the visits: Map of regions significantly changed between the two visits (centre).
Each region is described using a scatter plot of -scores across all patients for both visits (the x-axis describes age and the y-axis depicts the -score. Blue dots represent the first and pink dots represent the second visit). The grey dashed line highlights = 0. Histograms in the golden circles depict the distribution of the z-diff score.
Figure 7
Results of the PCA.
(A) Scree plot of the explained variance of PCA components. (B) Scatter plot of change in the Global Assessment of Functioning (GAF) scale vs. the change in the Positive and Negative Syndrome Scale (PANSS) scale. (C, left) Scatter plot of the first PCA component and difference in the GAF scale. (C, right) Heatmap of PCA loadings for the first component. (D, left) Scatter plot of the second PCA component and difference in the PANSS scale. (D, right) A heatmap of PCA loadings for the second component. (E) Average z-diff score.
Appendix 2—figure 1
estimates derived from the data.
Appendix 3—figure 1
Probability of detecting a true disruption for various values of autocorrelation (rows) and variances (columns) comparing the performance of our z-diff method against the naïve subtraction of -scores.
We use θ = 0.05.
Appendix 4—figure 1
Quality of fit as measured by Rho for the first and the second visit.
Appendix 5—figure 1
Regions significantly changed between the visits (longitudinal preprocessing): Map of regions significantly changed between the two visits (centre).
Each region is described using a scatter plot of z-diff across all patients for both visits (the x-axis describes age and the y-axis depicts the z-diff. Blue dots represent individual patients and the pink line shows a trend of z-diff change). The grey dashed line highlights z=0. Histograms in the golden circles depict the distribution of the z-diff score.
Appendix 5—figure 2
Regions significantly changed between the visits (cross-sectional preprocessing): Map of regions significantly changed between the two visits (centre).
Each region is described using a scatter plot of z-diff scores across all patients for both visits (the x-axis describes age and the y-axis depicts the z-diff score). The grey dashed line highlights =0. Histograms in the golden circles depict the distribution of the z-diff score.
Appendix 5—figure 3
Raw changes in grey matter thickness: Each significantly changed region is presented twice, once as a scatter plot containing the original grey matter thickness for both visits (left); females are plotted in pink, males in blue.
The figure on the right depicts visit 2 minus visit 1 in raw thicknesses (separately for females—pink, and males—blue).
Tables
Table 1
Clinical description of the dataset after quality control.
| Patients | Controls | |
|---|---|---|
| N (% females) | 98 (39%) | 67 (63%) |
| Age, median (min, max), years | 27 (18, 46) | 29 (18, 54) |
| Interval between visits, median (min, max), years | 1.1 (0.9,2.7) | 1.2 (0.9, 3) |
| Diagnosis (only for patients) | ||
| Schizophrenia | 53 | |
| Brief psychotic disorder | 45 | |
| Length of disease, median (min, max), months | 4 (1,21) | |
| Clinical scales (only for patients) | Visit 1 | Visit 2 |
| PANSS sum, median (min, max) | 53 (30, 94) | 44 (30, 84) |
| PANSS positive symptoms, median (min, max) | 11 (7, 21) | 8 (7, 26) |
| PANSS negative symptoms, median (min, max) | 14.5 (7, 30) | 11.5 (7, 24) |
| GAF, median (min, max) | 70 (25, 100) | 80.5 (40, 98) |
Additional files
Download links
A two-part list of links to download the article, or parts of the article, in various formats.
Downloads (link to download the article as PDF)
Open citations (links to open the citations from this article in various online reference manager services)
Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)
Using normative models pre-trained on cross-sectional data to evaluate intra-individual longitudinal changes in neuroimaging data
eLife 13:RP95823.
https://doi.org/10.7554/eLife.95823.4
