Abstract
Background: Formal thought disorder (FThD) is a core feature of psychosis, and its severity and long-term persistence relates to poor clinical outcomes. However, advances in developing early recognition and management tools for FThD are hindered by a lack of insight into the brain-level predictors of FThD states and progression at the individual level.
Methods: 233 individuals with recent-onset psychosis were drawn from the multi-site European Prognostic Tools for Early Psychosis Management study. Support vector machine classifiers were trained within a cross-validation framework to separate two FThD symptom-based subgroups (high vs. low FThD severity), using cross-sectional whole-brain multi-band fractional amplitude of low frequency fluctuations (fALFF), gray-matter volume (GMV) and white-matter volume (WMV) data. Moreover, we trained machine learning models on these neuroimaging readouts to predict the persistence of high FThD subgroup membership from baseline to 1-year follow-up.
Results: Cross-sectionally, multivariate patterns of GMV within the salience, dorsal attention, visual and ventral attention networks separated the FThD severity subgroups (BAC=60.8%). Longitudinally, distributed activations/deactivations within all fALFF sub-bands (BACslow-5=73.2%, BACslow-4=72.9%, BACslow-3=68.0), GMV patterns overlapping with the cross-sectional ones (BAC=62.7%) and smaller frontal WMV (BAC=73.1%) predicted the persistence of high FThD severity from baseline to follow-up, with a combined multi-modal balanced accuracy of BAC=77%.
Conclusions: We report first evidence of brain structural and functional patterns predictive of FThD severity and persistence in early psychosis. These findings open the avenue for the development of neuroimaging-based diagnostic, prognostic and treatment options for the early recognition and management of FThD and associated poor outcomes.
Methods: 233 individuals with recent-onset psychosis were drawn from the multi-site European Prognostic Tools for Early Psychosis Management study. Support vector machine classifiers were trained within a cross-validation framework to separate two FThD symptom-based subgroups (high vs. low FThD severity), using cross-sectional whole-brain multi-band fractional amplitude of low frequency fluctuations (fALFF), gray-matter volume (GMV) and white-matter volume (WMV) data. Moreover, we trained machine learning models on these neuroimaging readouts to predict the persistence of high FThD subgroup membership from baseline to 1-year follow-up.
Results: Cross-sectionally, multivariate patterns of GMV within the salience, dorsal attention, visual and ventral attention networks separated the FThD severity subgroups (BAC=60.8%). Longitudinally, distributed activations/deactivations within all fALFF sub-bands (BACslow-5=73.2%, BACslow-4=72.9%, BACslow-3=68.0), GMV patterns overlapping with the cross-sectional ones (BAC=62.7%) and smaller frontal WMV (BAC=73.1%) predicted the persistence of high FThD severity from baseline to follow-up, with a combined multi-modal balanced accuracy of BAC=77%.
Conclusions: We report first evidence of brain structural and functional patterns predictive of FThD severity and persistence in early psychosis. These findings open the avenue for the development of neuroimaging-based diagnostic, prognostic and treatment options for the early recognition and management of FThD and associated poor outcomes.
| Original language | English |
|---|---|
| Journal | Biological Psychiatry: Cognitive Neuroscience and Neuroimaging |
| Early online date | 19 Jun 2023 |
| DOIs | |
| Publication status | E-pub ahead of print - 19 Jun 2023 |
Keywords
- Formal thought disorder
- recent-onset psychosis
- neuroimaging
- predictive modeling
- subtyping
- early recognition