Skip to content
Open access

Cross‐Disease Classification of Depression, Bipolar Disorder, and Schizophrenia Using Multiscale Spatiotemporal Network Fusion Features From fNIRS

Jan 2026 · Depression and Anxiety · Vol 2026 · 0 citations · 39 references
Medicine

TL;DR

A novel multiscale spatiotemporal network fusion (MSNF) feature extraction method based on functional near–infrared spectroscopy (fNIRS) combined with the verbal fluency test (VFT) designed to enable objective, efficient, and automated differentiation among multiple psychiatric disorders, as well as between patient groups and healthy controls.

Abstract

Background Major depressive disorder (MDD), bipolar disorder (BD), and schizophrenia (SCZ) are highly prevalent and disabling psychiatric conditions with increasing incidence, significantly affecting individuals’ daily functioning, social relationships, and overall quality of life. Current diagnostic practices largely rely on clinical interviews and symptom‐based rating scales, which are inherently subjective and time‐consuming—posing major obstacles to large‐scale screening. Methods To address this, we propose a novel multiscale spatiotemporal network fusion (MSNF) feature extraction method based on functional near–infrared spectroscopy (fNIRS) combined with the verbal fluency test (VFT). This method is designed to enable objective, efficient, and automated differentiation among multiple psychiatric disorders (MDD, BD, and SCZ), as well as between patient groups and healthy controls (HCs). Leveraging the practical advantages of fNIRS, including its portability, motion tolerance, and balanced spatiotemporal resolution, the proposed MSNF fuses temporal dynamics with graph‐theoretical topology, capturing both local hemodynamic dynamics and hierarchy connectivity patterns. Results In this study, a total of 414 participants were recruited, including individuals diagnosed with MDD, BD, SCZ, and HCs. Classification experiments using machine learning (ML) models demonstrate the proposed method’s robustness and superior diagnostic performance in binary and multiclass settings, outperforming traditional unidimensional feature approaches. Additionally, group‐level functional connectivity (FC) analyses reveal distinct neurobiological signatures among psychiatric groups. Conclusions These findings underscore the translational potential of MSNF‐enhanced fNIRS as a scalable neuroimaging–based biomarker tool for early psychiatric screening and differential diagnosis.

Read PDF

Similar papers

Open access Oct 2026

Spatiotemporal feature-based investigation of major depressive disorder and emotion recognition using functional near infrared spectroscopy

Major Depressive Disorder (MDD) remains one of the most prevalent psychiatric conditions worldwide, with a marked increase in incidence and severity following the COVID-19 pandemic. Despite its rising burden, clinical diagnosis continues to rely on subjective assessments, lacking objective and reproducible neurobiologi...

Jin-Long Chao, Rui Yang, Hong Peng et al. · 0 citations
Sep 2026

Distinct pattern in bipolar depression and major depressive disorder: A multiscale imaging-transcriptomic analysis.

These findings identify distinct cortical morphometric organization in BDD and MDD, and these differences are linked to transcriptomic, cellular, and neurotransmitter-related annotations, providing multiscale insights into the neurobiological divergence between the two disorders.

Guang-Wei Sun, Tai-Peng Sun, Yu-Cheng Yuan et al. · 0 citations
Review Open access Oct 2026

Shared Social Brain Gray Matter Reductions in Depression, Schizophrenia, and Alcohol Use Disorder: A Meta-Analysis

A coordinate-based meta-analysis found common as well as separate GMV abnormalities in schizophrenia, major depressive disorder and alcohol use disorder suggesting a common neurostructural substrate and treatment target for social withdrawal and anhedonia across these disorders.

M. Bore, J. He, M. Han et al. · 0 citations
Sep 2026

Multimodal machine learning model integrating electroencephalography, heart rate variability and clinical measures for distinguishing major psychiatric disorders.

BACKGROUND This study aimed to develop and evaluate multimodal machine learning (ML) approaches for differentiating bipolar disorder (BD), major depressive disorder (MDD), and schizophrenia (SZ), conditions that are clinically difficult to distinguish because of overlapping symptom presentations despite their distinct...

Byeongjae Kang, J. Lee, J. Chang et al. · 0 citations
Open access Oct 2026

Depression’s Shadow in First-Onset Schizophrenia: Mapping the Burden and Clinical Significance in Drug-Naïve Patients

Background: Severe depressive symptoms (SDS) are common in patients with schizophrenia (SZ) and are associated with poor prognosis, reduced quality of life, and an increased risk of suicide. However, the prevalence of SDS and its key associated factors in first-onset drug-naïve patients with SZ remain unclear. Methods:...

Lin Zhang, Jie Zhang, Lu Wen et al. · 0 citations
Oct 2026

Stage-dependent gray matter morphological alterations across the clinical spectrum of depressive disorder.

BACKGROUND Previous studies have reported gray matter volume (GMV) deficits in different illness stages of depression; however, whether patients at different stages show shared or distinct GMV abnormality patterns has not been systematically characterized. METHODS We conducted a quantitative voxel-wise meta-analysis...

Kun Xu, Bao-Lin Wu, Zi-Ru Zhao et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.