Optimizing depression diagnosis: fNIRS and machine learning differentiate unipolar, bipolar, and healthy states
Journal of Affective Disorders · 2026
DOI: 10.1016/j.jad.2025.121097 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Affective Disorders, 2026. Verfasst von Jiayun Zhu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Engineering, Huzhou University, Huzhou, China. Hauptthemen laut MEDLINE: Bipolar Disorder, Machine Learning, Prefrontal Cortex, Depressive Disorder. Die Arbeit nennt 42 Literaturangaben.
Abstract (Originalsprache)
BACKGROUND: Differentiating Unipolar Depression (UD) from Bipolar Depression (BD) remains challenging due to overlapping symptoms, which can lead to misdiagnosis and inappropriate treatment. fNIRS provides a portable, objective measure of prefrontal cortical activity, yet its utility for clinically relevant ternary classification (UD, BD, HC) remains underexplored. METHODS: Prefrontal hemodynamics signals were recorded using 22-channel fNIRS during a verbal fluency task in 171 participants (UD = 72, BD = 59, HC = 40). Six classical machine learning models (Support Vector Machine, Random Forest, XGBoost, Logistic Regression, Naive Bayes, Decision Tree) and two deep learning models (1D-CNN, LSTM) were evaluated for ternary classification using whole-brain (FULL) features and eight prefrontal subregions. All models underwent hyperparameter optimization, stratified 5-fold cross-validation with class-weight adjustment, and data augmentation. Performance metrics included accuracy, sensitivity, specificity, and area under the ROC curve (AUC). RESULTS: SVM achieved the highest FULL-region accuracy (80.19 %). FULL integration outperformed single-region models by 14.51 % average accuracy. Among subregions, the orbitofrontal cortex (OFC) contributed most to classification performance (average left OFC accuracy: 67.40 %). UD was most reliably identified, whereas BD frequently overlapped with HC, reflecting intrinsic neurophysiological similarity. Deep learning models achieved moderate performance, consistent with limited sample size and high feature dimensionality. CONCLUSIONS: fNIRS-based machine learning reliably differentiates UD, BD, and HC at the group level. Whole-brain integration yields superior performance, with OFC as a key discriminative region. SVM and Random Forest offer the best balance of accuracy and clinical feasibility. Persistent BD-HC overlap remains a challenge, highlighting the need for larger BD cohorts and complementary multimodal assessments.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Information Engineering, Huzhou University, Huzhou, China.
- Department of Neurosis and Psychosomatic Diseases, Huzhou Third Municipal Hospital, Huzhou, China.
- Affiliated Huzhou Third Municipal Hospital, Wenzhou Medical University, Huzhou, China.
- School of Information Engineering, Huzhou University, Huzhou, China. Electronic address: zefeng.wang@zjhu.edu.cn.
Zitieren
APA
Zhu, J., Wu, B., Mou, L., Shen, Y., Sheng, Z., Wang, Z., & Shen, Z. (2026). Optimizing depression diagnosis: fNIRS and machine learning differentiate unipolar, bipolar, and healthy states. Journal of Affective Disorders. https://doi.org/10.1016/j.jad.2025.121097
Vancouver
Zhu J, Wu B, Mou L, Shen Y, Sheng Z, Wang Z, et al. Optimizing depression diagnosis: fNIRS and machine learning differentiate unipolar, bipolar, and healthy states. Journal of Affective Disorders. 2026. doi:10.1016/j.jad.2025.121097
BibTeX
@article{Zhu2026,
author = {Zhu, Jiayun and Wu, Boyuan and Mou, Lan and Shen, Yuqi and Sheng, Zhenxi and Wang, Zefeng and Shen, Zhongxia},
title = {Optimizing depression diagnosis: fNIRS and machine learning differentiate unipolar, bipolar, and healthy states},
journal = {Journal of Affective Disorders},
year = {2026},
doi = {10.1016/j.jad.2025.121097}
}
EUVIMED