Medical Signal based Depression Classification Method using Machine Learning: A Review and Future Research Directions

Paper ID: EIJTEM_2025_12_4_14-20

Author's Name: Pratiksha Deshmukh, Harshali Patil

Volume: 12

Issue: 4

Year: 2025

Page No: 14-20

Abstract:

Among mental health disorders, depression is the most harmful, impacting both individuals and society. Currently, this disorder affects 280 million people globally. Therefore, using machine learning algorithms to predict this disorder helps individuals detect depression at an early stage and provides additional support. In this paper, our focus is on reviewing depression classification methods that utilize machine learning algorithms for medical signals. In the medical signals, ECG, EEG, and wearable devices are used for data collection. Followed by preprocessing of this dataset to prepare it for the machine learning algorithm by passing it through filters, extracting features, and splitting it into training and testing ratios. Next, machine learning and its subfield, deep learning algorithms, are utilized for depression classification. In the literature, binary and multi-class depression classification is done by various authors, and evaluation is done using the various performance metrics, including accuracy, recall, precision, and F-score. Based on this review, we have defined the future research directions to enhance the depression classification method by hyper-tuning the parameters of the pre-processing and ML algorithms using the metaheuristic algorithms. Also, SHAP and LIME analysis on the collected data to determine which factor plays an important role in the depression.

Keywords: Deep Learning, Depression, Detection, Disorder, ECG, EEG, Machine Learning, Medical, Prediction.

References:

[1] G. H. A. Masud, R. I. Shanto, I. Sakin, and M. R. Kabir, “Effective depression detection and interpretation: Integrating machine learning, deep learning, language models, and explainable AI,” Array, p. 100375, Feb. 2025, doi: 10.1016/j.array.2025.100375. Available: https://doi.org/10.1016/j.array.2025.100375
[2] Q. Li et al., “Machine Learning-Based Prediction of Depressive Disorders via Various data Modalities: a survey,” IEEE/CAA Journal of Automatica Sinica, vol. 12, no. 7, pp. 1320–1349, Jul. 2025, doi: 10.1109/jas.2025.125393. Available: https://doi.org/10.1109/jas.2025.125393
[3] S. Aleem, N. U. Huda, R. Amin, S. Khalid, S. S. Alshamrani, and A. Alshehri, “Machine Learning Algorithms for Depression: diagnosis, insights, and research Directions,” Electronics, vol. 11, no. 7, p. 1111, Mar. 2022, doi: 10.3390/electronics11071111. Available: https://doi.org/10.3390/electronics11071111
[4] M . Squires et al., “Deep learning and machine learning in psychiatry: a survey of current progress in depression detection, diagnosis and treatment,” Brain Informatics, vol. 10, no. 1, Apr. 2023, doi: 10.1186/s40708-023-00188-6. Available: https://doi.org/10.1186/s40708-023-00188-6
[5] Ahmed, T., Qassem, M. and Kyriacou, P.A., 2022. Physiological monitoring of stress and major depression: A review of the current monitoring techniques and considerations for the future. Biomedical Signal Processing and Control, 75, p.103591.
[6] Elnaggar, K., El-Gayar, M.M. and Elmogy, M., 2025. Depression detection and diagnosis based on electroencephalogram (EEG) analysis: A systematic review. Diagnostics, 15(2), p.210.
[7] A. Goapalakrishnan et al., “Prenatal depression level prediction using ensemble based deep learning model,” International Journal of Cognitive Computing in Engineering, Jan. 2025, doi: 10.1016/j.ijcce.2024.12.002. Available: https://doi.org/10.1016/j.ijcce.2024.12.002
[8] M. Dia, G. Khodabandelou, S. M. Anwar, and A. Othmani, “Multichannel convolutional transformer for detecting mental disorders using electroancephalogrpahy records,” Scientific Reports, vol. 15, no. 1, May 2025, doi: 10.1038/s41598-025-98264-w. Available: https://doi.org/10.1038/s41598-025-98264-w
[9] X. Shui, H. Xu, S. Tan, and D. Zhang, “Depression recognition using daily Wearable-Derived Physiological data,” Sensors, vol. 25, no. 2, p. 567, Jan. 2025, doi: 10.3390/s25020567. Available: https://doi.org/10.3390/s25020567
[10] R. F. Navea et al., “EEG Channel Estimation using CNN-Based Depression Classifier,” Journal of Advanced Research in Applied Sciences and Engineering Technology, pp. 87–95, Oct. 2024, doi: 10.37934/araset.61.2.8795. Available: https://doi.org/10.37934/araset.61.2.8795
[11] A. Habib, S. N. Vaniya, A. Khandoker, and C. Karmakar, “MDDBranchNet: A deep learning model for detecting major depressive disorder using ECG Signal,” IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 7, pp. 3798–3809, Jul. 2024, doi: 10.1109/jbhi.2024.3390847. Available: https://doi.org/10.1109/jbhi.2024.3390847
[12] M. Ying, X. Shao, J. Zhu, Q. Zhao, X. Li, and B. Hu, “EDT: An EEG-based attention model for feature learning and depression recognition,” Biomedical Signal Processing and Control, vol. 93, p. 106182, Mar. 2024, doi: 10.1016/j.bspc.2024.106182. Available: https://doi.org/10.1016/j.bspc.2024.106182
[13] M. Alzate, R. Torres, J. De La Roca, A. Quintero-Zea, and M. Hernandez, “Machine Learning framework for classifying and Predicting depressive Behavior based on PPG and ECG feature extraction,” Applied Sciences, vol. 14, no. 18, p. 8312, Sep. 2024, doi: 10.3390/app14188312. Available: https://doi.org/10.3390/app14188312
[14] S. Ahmed, M. S. Kaiser, M. S. Hossain, and K. Andersson, “A Comparative Analysis of LIME and SHAP Interpreters with Explainable ML-Based Diabetes Predictions,” IEEE Access, p. 1, Jan. 2024, doi: 10.1109/access.2024.3422319. Available: https://doi.org/10.1109/access.2024.3422319
[15] S. Nematzadeh, F. Kiani, M. Torkamanian-Afshar, and N. Aydin, “Tuning hyperparameters of machine learning algorithms and deep neural networks using metaheuristics: A bioinformatics study on biomedical and biological cases,” Computational Biology and Chemistry, vol. 97, p. 107619, Dec. 2021, doi: 10.1016/j.compbiolchem.2021.107619. Available: https://doi.org/10.1016/j.compbiolchem.2021.107619

View PDF