Comparative Evaluation of rs-fMRI Representations for Differentiating Schizophrenia and Bipolar Disorder with Psychosis
- 1Faculty of Electrical Engineering and Information Technologies
Abstract
Psychosis as a symptom manifests in schizophenia and bipolar disorder, two highly heterogeneous psychiatric illnesses with overlapping clinical manifestations. Resting-state functional Magnetic Resonance Imaging (rsfMRI), represents a promising tool for identifying objective biomarkers of functional brain alterations to aid differential diagnosis. In this work, we comparatively evaluate multiple rs-fMRI representations for differentiating schizophrenia and bipolar disorder using intrinsic connectivity network (ICN) temporal profiles and several functional network connectivity (FNC) approaches, including static, dynamic, and high-order connectivity analyses. The study was conducted on a cohort of 371 subjects with psychosis, while evaluation was performed using a separate held-out cohort of 315 subjects. We investigated convolutional neural network architectures applied to ICN temporal profiles, spectrograms, and scalograms, alongside classical machine learning models trained on connectivity-derived features. Across the evaluated approaches, ICN temporal profiles provided the most consistent discriminative performance, with a 1D convolutional neural network achieving the strongest overall results under the benchmark protocol. Among connectivity-based methods, static functional connectivity generally outperformed dynamic and high-order representations, suggesting that increased representational complexity did not necessarily translate into improved generalization. Although the obtained classification performance remained modest, the results highlight the challenges of robust psychosis differentiation using rs-fMRI while emphasizing the relative stability of low-order connectivity representations and temporal ICN features. These findings contribute to ongoing efforts toward reproducible and interpretable neuroimaging biomarkers for psychiatric disorders.
Related
- Rapid Resolution of Apophenic Psychosis With Low-Dose Olanzapine in Very Late-Onset Schizophrenia-Like Psychosis
- Frontal–striatal–thalamic circuit dysfunction and inferential processing between internal representations and external events across the psychosis spectrum
- Systems-Level Transcriptomic and Cellular Architecture of the Human Striatum in Schizophrenia and Bipolar Psychosis.
- Galectins and the Interleukin-33/Suppression of Tumorigenicity-2 Pathway in First-episode Psychosis and Schizophrenia: A Cross-sectional Exploratory Study
- Steroidomic Differences Among Clozapine, Olanzapine, and Risperidone in Male Patients with First-Episode Psychosis, Including a Treatment-Resistant Schizophrenia Subgroup
BibTeX
@misc{janeva2026comparative,
title = {{Comparative Evaluation of rs-fMRI Representations for Differentiating Schizophrenia and Bipolar Disorder with Psychosis}},
author = {D. Janeva and M. Breyton and S. Markovska-Simoska and R. Guilhaumou and S. Petkoski and A. Iraji and V. Calhoun and B. Gerazov},
howpublished = {medRxiv},
year = {2026},
month = jun,
doi = {10.64898/2026.06.16.26355608},
url = {https://www.medrxiv.org/content/10.64898/2026.06.16.26355608v2},
note = {Public domain},
}
RIS
TY - UNPB
TI - Comparative Evaluation of rs-fMRI Representations for Differentiating Schizophrenia and Bipolar Disorder with Psychosis
AU - D. Janeva
AU - M. Breyton
AU - S. Markovska-Simoska
AU - R. Guilhaumou
AU - S. Petkoski
AU - A. Iraji
AU - V. Calhoun
AU - B. Gerazov
PY - 2026
DA - 2026/06/16
PB - medRxiv
DO - 10.64898/2026.06.16.26355608
UR - https://www.medrxiv.org/content/10.64898/2026.06.16.26355608v2
AB - Psychosis as a symptom manifests in schizophenia and bipolar disorder, two highly heterogeneous psychiatric illnesses with overlapping clinical manifestations. Resting-state functional Magnetic Resonance Imaging (rsfMRI), represents a promising tool for identifying objective biomarkers of functional brain alterations to aid differential diagnosis. In this work, we comparatively evaluate multiple rs-fMRI representations for differentiating schizophrenia and bipolar disorder using intrinsic connectivity network (ICN) temporal profiles and several functional network connectivity (FNC) approaches, including static, dynamic, and high-order connectivity analyses. The study was conducted on a cohort of 371 subjects with psychosis, while evaluation was performed using a separate held-out cohort of 315 subjects. We investigated convolutional neural network architectures applied to ICN temporal profiles, spectrograms, and scalograms, alongside classical machine learning models trained on connectivity-derived features. Across the evaluated approaches, ICN temporal profiles provided the most consistent discriminative performance, with a 1D convolutional neural network achieving the strongest overall results under the benchmark protocol. Among connectivity-based methods, static functional connectivity generally outperformed dynamic and high-order representations, suggesting that increased representational complexity did not necessarily translate into improved generalization. Although the obtained classification performance remained modest, the results highlight the challenges of robust psychosis differentiation using rs-fMRI while emphasizing the relative stability of low-order connectivity representations and temporal ICN features. These findings contribute to ongoing efforts toward reproducible and interpretable neuroimaging biomarkers for psychiatric disorders.
ER -