Background/Objectives: Depressive disorder (DD) is a prevalent psychiatric condition often diagnosed through subjective self-reports, which can be time-consuming and lead to inaccurate assessments. To enhance diagnostic precision, integrating Electroencephalography (EEG) with machine learning (ML) has gained attention as an objective approach for DD diagnosis and severity assessment. Methods: We propose an interpretable EEG-based ML framework that integrates optimized functional connectivity features, including Coherence, Phase Lag Index (PLI), and Granger causality, to explore EEG-based functional connectivity patterns in individuals clinically diagnosed with depressive DD and to model symptom severity and cognitive vulnerability. The identified biomarkers provide a promising foundation for developing objective, clinically actionable decision-support tools in psychiatric care. Feature selection was performed using the Neighborhood Component Analysis (NCA) method, and biomarkers were identified through statistical tests. Results: The highest classification performance (97.66% ± 2.05%accuracy, 99.20% ± 1.10% sensitivity, 95.91% ± 4.66% specificity, 98.00% ± 1.02% f1-score, and 0.95 ± 0.48 MCC) was achieved using 21 NCA-selected features with a KNN (K = 9) classifier. The best severity assessment (r2 = 0.89 ± 0.10, MSE = 3.96 ± 17.05) and cognitive impairment prediction (r2 = 0.89 ± 0.06, MSE = 0.23 ± 0.45) were obtained using an ANN regressor with 20 and 17 NCA-selected features, respectively. Conclusions: Our approach outperforms previous EEG-based ML models in DD classification and severity prediction using fewer features. Notably, this is the first study to use EEG connectivity features to predict patients’ severity and cognitive impairment in DD. Coherence and PLI values from frontal and temporal pathways across the alpha, beta, and gamma sub-bands may serve as critical biomarkers for DD diagnosis, severity assessment, and prediction of cognitive impairment.
Objective There is a growing interest in functional near-infrared spectroscopy (fNIRS) among researchers due to its remarkable advantages such as ease of use, being inexpensive and less tolerance to motion artifacts compared to other neuroimaging modalities. Also, its interaction with machine learning (ML) approaches was inevitable like other neuroimaging modalities for different purposes such as diagnostic classification of diseases or prediction of disease severity due to the lack of robust and objective biomarkers. A review of literature is carried out to understand the evolution of biomarker research on clinical populations and clinical states by combining fNIRS and ML. Approach In this review, article search was carried out in accordance with the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) standard and 62 studies were evaluated and we provided a general overview by using fNIRS, particularly in clinical populations and some clinically relevant conditions on healthy populations. Also, potential biomarkers that were found in these studies and some popular ML algorithms that had been used for the prediction or classification of fNIRS data were discussed. Main Results There is an increasing trend to perform ML applications on fNIRS data on biomarker research related to different clinical fields. Among these studies, few were able to have a notable number of participants for classification and clinical state prediction. Oxy-hemoglobin was used more than deoxy-hemoglobin in ML-based studies as a potential feature source. Significance Using ML on fNIRS data might be a promising approach to revealing specific biomarkers for either diagnostic classification of diseases or prediction of clinical conditions.