In order to proceed the fast detection of depression with EEG (electroencephalogram) signal, this study proposed a so-called AKRCC-KNN model for automatic and accurate diagnosis. Based on the multi-channel EEG signal with pre-processing, there is a novel approach focusing on the feature extraction, in which the PLI (phase lag index) of EEG signals is calculated as the feature; moreover, the feature selection algorithm (so-called AKRCC) is innovatively integrated with AKRC (altered Kendall’s rank correlation coefficient) method for feature re-arrangement and convergence determination for feature selection, in order to improve the selective feature’s accuracy with limited computation expense. Hence the entire process of detection of depression with enhanced performance is listed as follows. Firstly, the PLI of EEG signals is computed to obtain their functional connectivity networks. AKRCC algorithm is then applied to rank PLI matrix elements by their discriminative power and determine optimal feature dimensionality through classification accuracy convergence monitoring. Finally, the selected multidimensional features are input into a KNN classifier for automatic classification. Extensive experiments on the MODMA dataset (24 major depression disorder patients, 29 healthy controls) demonstrate the model’s superior performance. With 1-second full-band EEG features, the AKRCC-KNN model achieves a state-of-the-art identification accuracy of 97.65% (specificity: 96.95%, sensitivity: 98.54%), surpassing existing methods. This indicates that the proposed depression detection model in this paper can achieve intelligent and rapid depression detection, providing an efficient, accurate, and diverse solution for clinical depression detection.

1. [1] S. Evans-Lacko, S. Aguilar-Gaxiola, A. Al-Hamzawi, J. Alonso, C. Benjet, R. Bruffaerts, W. T. Chiu, S. Florescu, G. de Girolamo, O. Gureje, J. M. Haro, Y. He, C. Hu, E. G. Karam, N. Kawakami, S. Lee, C. Lund, V. Kovess-Masfety, D. Levinson, F. Navarro-Mateu, B. E. Pennell, N. A. Sampson, K. M. Scott, H. Tachimori, M. ten Have, M. C. Viana, D. R. Williams, B. J. Wojtyniak, Z. Zarkov, R. C. Kessler, S. Chatterji, and G. Thornicroft, “Socio-economic variations in the mental health treatment gap for people with anxiety, mood, and substance use disorders: Results from the WHO World Mental Health (WMH) surveys,” Psychological Medicine, Vol.48, Issue 9, pp. 1560-1571, 2018. https://doi.org/10.1017/S0033291717003336
2. [2] J. Lundberg, T. Cars, E. Lampa, K. E. Selling, A. Leval, A. Gannedahl, M. Själin, C. Björkholm, and C. Hellner, “Determinants and Outcomes of Suicidal Behavior Among Patients with Major Depressive Disorder,” JAMA Psychiatry, Vol.80, No.12, pp. 1218-1225, 2023. https://doi.org/10.1001/jamapsychiatry.2023.2833
3. [3] T. Tomita, Y. Sato, T. Nakagami, S. Tsuchimine, A. Kaneda, S. Kaneko, K. Nakamura, and N. Yasui-Furukori, “Items of the Montgomery-Åsberg Depression Rating Scale Associated with Response to Paroxetine Treatment in Patients With Major Depressive Disorder,” Clinical Neuropharmacology, Vol.39, No.3, pp. 135-139, 2016. https://doi.org/10.1097/wnf.0000000000000146
4. [4] H. Sawaya, M. Atoui, A. Hamadeh, P. Zeinoun, and Z. Nahas, “Adaptation and initial validation of the Patient Health Questionnaire – 9 (PHQ-9) and the Generalized Anxiety Disorder – 7 Questionnaire (GAD-7) in an Arabic speaking Lebanese psychiatric outpatient sample,” Psychiatry Research, Vol.239, pp. 245-252, 2016. https://doi.org/10.1016/j.psychres.2016.03.030
5. [5] C-H. Lin, C. Park, and R. S. McIntyre, “Early improvement in HAMD-17 and HAMD-7 scores predict response and remission in depressed patients treated with fluoxetine or electroconvulsive therapy,” J. of Affective Disorders, Vol.253, pp. 154-161, 2019. https://doi.org/10.1016/j.jad.2019.04.082
6. [6] K. J. Rohan, J. N. Rough, M. Evans, S. Y. Ho, J. Meyerhoff, L. M. Roberts, and P. M. Vacek, “A protocol for the Hamilton rating scale for depression: Item scoring rules, rater training, and outcome accuracy with data on its application in a clinical trial,” J. of Affective Disorders, Vol.200, pp. 111-118, 2016. https://doi.org/10.1016/j.jad.2016.01.051
7. [7] F. Rosenow, K. M. Klein, and H. M. Hamer, “Non-invasive EEG evaluation in epilepsy diagnosis,” Expert Review of Neurotherapeutics, Vol.15, Issue 4, pp. 425-444, 2015. https://doi.org/10.1586/14737175.2015.1025382
8. [8] B. S. Peterson, J. Trampush, M. Brown, M. Maglione, M. Bolshakova, M. Rozelle, J. Miles, S. Pakdaman, S. Yagyu, A. Motala, and S. Hempel, “Tools for the Diagnosis of ADHD in Children and Adolescents: A Systematic Review,” Pediatrics, Vol.153, No.4, Article No.e2024065854, 2024. https://doi.org/10.1542/peds.2024-065854
9. [9] Y. Liu, K. Dong, and L. Sun, “Divergent spatiotemporal signatures characterize impaired facial emotional recognition in major depressive disorder: An event-related microstate study,” J. of Affective Disorders, Vol.381, pp. 281-290, 2025. https://doi.org/10.1016/j.jad.2025.04.038
10. [10] B. Hosseinifard, M. H. Moradi, and R. Rostami, “Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal,” Comput Methods Programs Biomed., Vol.109, Issue 3, pp. 339-345, 2013. https://doi.org/10.1016/j.cmpb.2012.10.008
11. [11] P. F. Lee, D. P. X. Kana, P. Croarkin, C. K. Phang, and D. Doruk, “Neurophysiological correlates of depressive symptoms in young adults: A quantitative EEG study,” J. Clin. Neurosci., Vol.47, pp. 315-322, 2018. https://doi.org/10.1016/j.jocn.2017.09.030
12. [12] M. A. Özçoban and O. Tan, “Electroencephalographic markers in major depressive disorder: Insights from absolute, relative power, and asymmetry analyses,” Frontiers in Psychiatry, Vol.15, Article No.1480228, 2025. https://doi.org/10.3389/fpsyt.2024.1480228
13. [13] D. Hou, C. Wang, Y. Chen, W. Wang, and J. Du, “Long-range temporal correlations of broadband EEG oscillations for depressed subjects following different hemispheric cerebral infarction,” Cognitive Neurodynamics, Vol.11, No.6, pp. 529-538, 2017. https://doi.org/10.1007/s11571-017-9451-3
14. [14] Z. Guo, X. Wu, J. Liu, L. Yao, and B. Hu, “Altered electroencephalography functional connectivity in depression during the emotional face-word Stroop task,” J. of Neural Engineering, Vol.15, No.5, pp. 056014.1-056014.13, 2018. https://doi.org/10.1088/1741-2552/aacdbb
15. [15] B. Zhang, G. Yan, Z. Yang, Y. Su, J. Wang, and T. Lei, “Brain Functional Networks Based on Resting-State EEG Data for Major Depressive Disorder Analysis and Classification,” IEEE Trans. on Neural Systems and Rehabilitation Engineering, Vol.29, pp. 215-229, 2020. https://doi.org/10.1109/TNSRE.2020.3043426
16. [16] D. Watts, R. F. Pulice, J. Reilly, A. R. Brunoni, F. Kapczinski, and I. C. Passos, “Predicting treatment response using EEG in major depressive disorder: A machine-learning meta-analysis,” Translational Psychiatry, Vol.12, No.1, Article No.332, 2022. https://doi.org/10.1038/s41398-022-02064-z
17. [17] E. Ebrahimzadeh, A. Dehghani, M. Asgarinejad, and H. Soltanian-Zadeh, “Non-linear processing and reinforcement learning to predict rTMS treatment response in depression,” Psychiatry Research: Neuroimaging, Vol.337, Article No.111764, 2024. https://doi.org/10.1016/j.pscychresns.2023.111764
18. [18] M.-P. Hosseini, A. Hosseini, and K. Ahi, “A Review on Machine Learning for EEG Signal Processing in Bioengineering,” IEEE Reviews in Biomedical Engineering, Vol.14, pp. 204-218, 2020. https://doi.org/10.1109/RBME.2020.2969915
19. [19] U. R. Acharya, V. K. Sudarshan, H. Adeli, J. Santhosh, J. E. W. Koh, S. D. Puthankatti, and A. Adeli, “A Novel Depression Diagnosis Index Using Nonlinear Features in EEG Signals,” European Neurology, Vol.74, Issues 1-2, pp. 79-83, 2015. https://doi.org/10.1159/000438457
20. [20] C. Jiang, Y. Li, Y. Tang, and C. Guan, “Enhancing EEG-Based Classification of Depression Patients Using Spatial Information,” IEEE Trans. on Neural Systems and Rehabilitation Engineering, Vol.29, pp. 566-575, 2021. https://doi.org/10.1109/TNSRE.2021.3059429
21. [21] S. Mahato and S. Paul, “Detection of major depressive disorder using linear and non-linear features from EEG signals,” Microsystem Technologies, Vol.25, No.3, pp. 1065-1076, 2019. https://doi.org/10.1007/s00542-018-4075-z
22. [22] H. Cai, J. Han, Y. Chen, X. Sha, Z. Wang, B. Hu, J. Yang, L. Feng, Z. Ding, Y. Chen, and J. Gutknecht, “A Pervasive Approach to EEG-Based Depression Detection,” Complexity, Vol.1, Article No.5238028, 2018. https://doi.org/10.1155/2018/5238028
23. [23] Y. Mohammadi and M. H. Moradi, “Prediction of Depression Severity Scores Based on Functional Connectivity and Complexity of the EEG Signal,” Clinical EEG and Neuroscience, Vol.52, Issue 1, pp. 52-60, 2021. https://doi.org/10.1177/1550059420965431
24. [24] H. Akbari, M. T. Sadiq, A. U. Rehman, M. Ghazvini, R. A. Naqvi, M. Payan, H. Bagheri, and H. Bagheri, “Depression recognition based on the reconstruction of phase space of eeg signals and geometrical features,” Applied Acoustics, Vol.179, Article No.108078, 2021. https://doi.org/10.1016/j.apacoust.2021.108078
25. [25] H. Lin, C. Jian, Y. Cao, X. Ma, H. Wang, F. Miao, X. Fan, J. Yang, G. Zhao, and H. Zhou, “MDD-TSVM: A novel semisupervised-based method for major depressive disorder detection using electroencephalogram signals,” Computers in Biology and Medicine, Vol.140, Article No.105039, 2022. https://doi.org/10.1016/j.compbiomed.2021.105039
26. [26] Y. Wang, L. Xu, H. Qian, H. Lin, and X. Zhang, “Improved empirical wavelet transform combined with particle swarm optimization-support vector machine for EEG-based depression recognition,” EURASIP J. on Advances in Signal Processing, Vol.2024, Article No.101, 2024. https://doi.org/10.1186/s13634-024-01199-z
27. [27] H. Peng, C. Xia, Z. Wang, J. Zhu, X. Zhang, and S. Sun, “Multivariate Pattern Analysis of EEG-Based Functional Connectivity: A Study on the Identification of Depression,” IEEE Access, Vol.7, pp. 92630-92641, 2019. https://doi.org/10.1109/ACCESS.2019.2927121
28. [28] Z. Wang, P. Xu, T. Liu, Y. Tian, X. Lei, and D. Yao, “Robust removal of ocular artifacts by combining independent component analysis and system identification,” Biomedical Signal Processing and Control, Vol.10, pp. 250-259, 2014. https://doi.org/10.1016/j.bspc.2013.10.006
29. [29] S. Tsuchimoto, S. Shibusawa, S. Iwama, M. Hayashi, K. Okuyama, N. Mizuguchi, K. Kato, and J. Ushiba, “Use of common average reference and large-Laplacian spatial-filters enhances EEG signal-to-noise ratios in intrinsic sensorimotor activity,” J. of Neuroscience Methods, Vol.353, Article No.109089, 2021. https://doi.org/10.1016/j.jneumeth.2021.109089
30. [30] C. J. Stam, G. Nolte, and A. Daffertshofer, “Phase lag index: Assessment of functional connectivity from multi channel EEG and MEG with diminished bias from common sources,” Human Brain Mapping, Vol.28, Issue 11, pp. 1178-1193, 2007. https://doi.org/10.1002/hbm.20346
31. [31] O. Kramer, “K-Nearest Neighbors,” O. Kramer (Ed.), “Dimensionality Reduction with Unsupervised Nearest Neighbors,” pp. 13-23, Springer, 2013. https://doi.org/10.1007/978-3-642-38652-7_2
32. [32] MODMA Dataset. https://modma.lzu.edu.cn/data/index/ [Accessed May 21, 2024]
33. [33] Z. Wang, C. Hu, W. Liu, X. Zhou, and X. Zhao, “EEG-based high-performance depression state recognition,” Frontiers in Neuroscience, Vol.17, Article No.1301214, 2024. https://doi.org/10.3389/fnins.2023.1301214
34. [34] Z. Zhang, Q. Meng, L. Jin, H. Wang, and H. Hou, “A novel EEG-based graph convolution network for depression detection: Incorporating secondary subject partitioning and attention mechanism,” Expert Systems with Applications, Vol.239, Article No.122356, 2024. https://doi.org/10.1016/j.eswa.2023.122356