Multivariate connectivity deviations reveal task-evoked and clinical network reorganization
Abstract
Understanding how cognitive demands and pathology reshape functional connectivity (FC) requires multivariate, region-specific methods. Here, we introduce one-class SVM-based connectome anomaly recognition (OSCAR), which detects condition-related deviations in regional connectivity profiles. OSCAR learns region-to-whole-brain connectivity patterns from a reference state using one-class support vector machines and quantifies target-condition deviations based on outlier proportions. We validated OSCAR across three diverse cognitive tasks, in which it identified regions within networks associated with conflict processing, object-location memory, and lexical learning. In a clinical cohort that included individuals with early psychosis, OSCAR identified relevant regions, including thalamic and basal ganglia areas. Compared with permutation-based multivariate analysis of variance, OSCAR detected additional established task- and disease-relevant parcels, while its task-related findings were at least as close, and often closer, to independent activation findings. OSCAR thus provides an interpretable, region-centered approach for mapping multivariate FC reconfigurations across experimental and clinical conditions.
Related
- Migraine-related differences in connectivity patterns during emotional audiovisual processing revealed by functional connectivity multivariate pattern analysis.
- Normal aging limits cortical network reorganization and behavioral recovery after experimental stroke
- Multivariate prediction of white matter BOLD activity and its relationship to marginal connectivity
- Cortical Network Reorganization During Balance Control in Chronic Stroke: Premotor-Parietal Behavioral Uncoupling and Directional Prefrontal Compensation.
- Sex-Modulated Coupling Between Genetically-Regulated Gene Expression and Functional Network Connectivity in Schizophrenia
BibTeX
@article{kroll2026multivariate,
title = {{Multivariate connectivity deviations reveal task-evoked and clinical network reorganization}},
author = {Jean-Philippe Kröll and Mohamed Abdelmotaleb and Harun Kocataş and Veronica Müller and Lya Paas and Marcus Meinzer and Agnes Flöel and Simon Eickhoff and Kaustubh R. Patil},
journal = {iScience},
year = {2026},
month = oct,
doi = {10.1016/j.isci.2026.117959},
url = {https://www.cell.com/iscience/fulltext/S2589-0042(26)03342-0},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Multivariate connectivity deviations reveal task-evoked and clinical network reorganization
AU - Jean-Philippe Kröll
AU - Mohamed Abdelmotaleb
AU - Harun Kocataş
AU - Veronica Müller
AU - Lya Paas
AU - Marcus Meinzer
AU - Agnes Flöel
AU - Simon Eickhoff
AU - Kaustubh R. Patil
PY - 2026
DA - 2026/10/21
JO - iScience
DO - 10.1016/j.isci.2026.117959
UR - https://www.cell.com/iscience/fulltext/S2589-0042(26)03342-0
AB - Understanding how cognitive demands and pathology reshape functional connectivity (FC) requires multivariate, region-specific methods. Here, we introduce one-class SVM-based connectome anomaly recognition (OSCAR), which detects condition-related deviations in regional connectivity profiles. OSCAR learns region-to-whole-brain connectivity patterns from a reference state using one-class support vector machines and quantifies target-condition deviations based on outlier proportions. We validated OSCAR across three diverse cognitive tasks, in which it identified regions within networks associated with conflict processing, object-location memory, and lexical learning. In a clinical cohort that included individuals with early psychosis, OSCAR identified relevant regions, including thalamic and basal ganglia areas. Compared with permutation-based multivariate analysis of variance, OSCAR detected additional established task- and disease-relevant parcels, while its task-related findings were at least as close, and often closer, to independent activation findings. OSCAR thus provides an interpretable, region-centered approach for mapping multivariate FC reconfigurations across experimental and clinical conditions.
SN - 2589-0042
ER -