AUGMENTED MULTI-LABEL CLASSIFICATION FOR THE EARLY DETECTION OF CO-OCCURRING MENTAL HEALTH DISORDERS

Kavita Shelke; Mansi  Kumbhar; Shruti Katkar; Rahul  Chopade; Joshua  Mathew; Smita  Dange

doi:10.4314/njt.2025.5221

Authors

K. Shelke Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India
M. Kumbhar Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India
S. Katkar Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India
R. Chopade Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India
J. Mathew Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India
S. Dange Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India

DOI:

https://doi.org/10.4314/njt.2025.5221

Keywords:

Multi label Classification, Generative Adversarial Network, Mental health disorders, Early detection

Abstract

Mental health disorders such as anxiety, depression, and schizophrenia often go undiagnosed due to limited awareness, social stigma, and reliance on subjective clinical evaluations. Traditional screening methods can be time-consuming, leading to delayed interventions and worsening conditions. This system aims to provide an early screening tool that helps individuals assess their mental health status and assists healthcare professionals in identifying disorders quickly and accurately. The system employs a multi-label classification approach to predict multiple co-existing mental health disorders simultaneously. The dataset is created using psychiatrist-approved questionnaires, and since real-world mental health data is often limited and biased, Generative Adversarial Networks (GANs) are used to generate synthetic data for improved model training. This enhances generalizability and reduces bias in predictions. By providing a user-friendly AI-powered screening tool, the system helps reduce the taboo around mental health conditions and bridges the gap between individuals and mental health professionals. It ensures faster, data-driven diagnosis, allowing for timely interventions and better treatment planning, ultimately improving mental healthcare accessibility and efficiency. The experimental results indicate that the Random Forest model achieved the best overall performance, with an F1-score weighted average of 0.40 and strong label-wise performance, particularly for obsessive-compulsive disorder (OCD) (F1 = 0.69), Post-Traumatic Stress Disorder (PTSD) (F1 = 0.62), and Normal (F1 = 0.38), demonstrating its effectiveness in multi-label mental health disorder detection.

Author Biographies

K. Shelke, Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India

Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India
M. Kumbhar, Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India

Department of Computer Engineering Fr. C. Rodrigues Institute of Technology Navi Mumbai, India
S. Katkar, Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India

Department of Computer Engineering Fr. C. Rodrigues Institute of Technology Navi Mumbai, India
R. Chopade, Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India

Department of Computer Engineering Fr. C. Rodrigues Institute of Technology Navi Mumbai, India
J. Mathew, Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India

Department of Computer Engineering Fr. C. Rodrigues Institute of Technology Navi Mumbai, India
S. Dange, Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India

Department of Computer Engineering, Fr. C. Rodrigues Institute of Technology Navi Mumbai, India

References

[1] Kim, J. Kim, D. Kamphaus, R. “Early Detection of Mental Health Through Universal Screening at Schools”. Georgia Educational Researcher, 2022, doi: 10.20429/ger.2022.190104

[2] Nadeem, M. Rashid, J. Moon, H. Dosset, A. "Machine Learning for Mental Health: A Systematic Study of Seven Approaches for Detecting Mental Disorders", International Technical Conference on Circuits/Systems, Computers, and Communications (ITC-CSCC), Jeju, Korea, Republic of, 2023, pp. 1-6, doi: 10.1109/ITC-CSCC58803.2023.10212609.

[3] Ahuja R. and Alisha B. "Mental Stress Detection in University Students Using Machine Learning Algorithms." Procedia Computer Science, 152, pp. 349-353, 2018, doi: 10.1016/j.procs.2019.05.007

[4] Kim, J. Liu, N. Tan, H. Chu, C. "Unobtrusive monitoring to detect depression for elderly with chronic illnesses", IEEE Sensors Journal. 17, (17), pp 5694-5704, 2017, doi: 10.1109/JSEN.2017.2729594

[5] Osman, A.B., Tabassum, F., Patwary, M.J., Imteaj, A., Alam, T., Bhuiyan, M.A., & Miraz, M.H. "Examining Mental Disorder/Psychological Chaos through Various ML and DL Techniques: A Critical Review", Annals of Emerging Technologies in Computing, 2022, doi: 10.33166/AETiC.2022.02.005

[6] Seal, A. Bajpai, R. Agnihotri, J. Yazidi, A. Herrera-Viedma, E. Krejcar, O. " DeprNet: A Deep Convolution Neural Network Framework for Detecting Depression Using EEG" IEEE Transactions on Instrumentation and Measurement, p 1, 2021, doi: 10.1109/TIM.2021.3053999

[7] Wijayarathna, C. Lakshika, E. “Toward Stress Detection During Gameplay: A Survey,” in IEEE Transactions on Games, 15 (4), pp. 549-565, 2023, doi: 10.1109/TG.2022.3216404

[8] Kumar, R. Pooja, K. Udathu, M. Lakshmi, J. Santhosh, C. “Detection of Depression Using Machine Learning Algorithms”, International Journal of Online and Biomedical Engineering, 18, pp 155-163, 2022.

[9] Bhavani, B. Naveen, N. "An Approach to Determine and Categorize Mental Health Condition using Machine Learning and Deep Learning Models," Engineering, Technology & Applied Science Research, 14, pp 13780-13786, 2024, https://doi.org/10.48084/etasr.7162

[10] Mashrura, T. Ramon, D. Eleni, S. “A Machine learning Model For Detecting Depression, Anxiety, and Stress from Speech,” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Korea Republic, 2024, pp. 7085-7089, 2024, doi: 10.1109/ICASSP48485.2024.10446567

[11] Anu, P., Shruti, G. Neha, T. “Predicting Anxiety, Depression and Stress in Modern Life using Machine Learning Algorithms” Procedia Computer Science, 167, 2019, doi: 10.1016/j.procs.2020.03.442

[12] Mario, A. Adrian, L. Luis, G. Manuel, M. “Detecting Mental Disorders in Social Media Through Emotional Patterns - The Case of Anorexia and Depression” IEEE Transactions on Affective Computing, 14 (1) pp. 211-222, 2023, doi: 10.1109/TAFFC.2021.3075638

[13] Guo, Y. Zhang, Z. Xu, X., “Research on the detection model of mental illness of online forum users based on convolutional network”, BMC Psychology, 11, p 424, 2023, https://doi.org/10.1186/s40359-023-01460-4

[14] Khoo, L.S. Lim, M.K. Chong, C.Y. McNaney, R. "Machine Learning for Multimodal Mental Health Detection: A Systematic Review of Passive Sensing Approaches", Sensors, 24 (2), p 348, 2024, https://doi.org/10.3390/s24020348

[15] Sharma, K., Ahmed, I. A. Ahmad, K. Ghanshyam, G. Tejani, F. A. Seyed J. M. "Early Detection of Mental Health Disorders Using Machine Learning Models Using Behavioral and Voice Data Analysis." Scientific Reports, 15(1), pp. 1-19, 2025, https://doi.org/10.1038/s41598-025-00386-8.

[16] Kiran, V. K. Tiwari, G. "Early Identification and Management of Mental Disorders". International Journal of Indian Psychology, 11(4), pp 697-701, 2023, doi: 10.25215/1104.060

[17] Yadav, G. Bokhari, M. Alzahrani, S. Alam, S. Shuaib, M. "Emotion-Aware Ensemble Learning (EAEL): Revolutionizing Mental Health Diagnosis of Corporate Professionals via Intelligent Integration of Multi-Modal Data Sources and Ensemble Techniques", IEEE Access, p 1, 2025, doi: 10.1109/ACCESS.2025.3529032

[18] Abd Rahman, R. Omar, K. Mohd Noah, S. A. Mohd D. Mohd Shahrul N. Al-Garadi, M. "Application of Machine Learning Methods in Mental Health Detection: A Systematic Review", IEEE Access, 8. pp. 183952-183964, 2020, 10.1109/ACCESS.2020.3029154.

[19] Abdullah, M. & Negied, N. " Detection and Prediction of Future Mental Disorder From Social Media Data Using Machine Learning, Ensemble Learning, and Large Language Models", IEEE Access, p. 1, 2024, 10.1109/ACCESS.2024.3406469.

[20] Kim, J. Liu, N. Tan, H. X. Chu, C. "Unobtrusive monitoring to detect depression for elderly with chronic illnesses", IEEE Sensors Journal, 17, (17), pp. 5694-5704, 2017. doi: 10.1109/JSEN.2017.2729594

[21] Lei X. Maria S. Alfredo C. Kalyan V. "Modeling tabular data using conditional GAN." Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, Article 659, pp. 7335–7345, 2019.

[22] Breiman, L. "Random Forests." Machine Learning. 45, pp. 5-32, 2001, 10.1023/A:1010950718922. .

[23] Jesse, R. Bernhard, P. Geoff, H. Eibe, F. "Classifier chains for multi-label classification", Machine Learning. 85 (3), 333–359, 2011, https://doi.org/10.1007/s10994-011-5256-5.

[24] Zhang, M. Zhou, Z. "A Review On Multi-Label Learning Algorithms. Knowledge and Data Engineering", IEEE Transactions on Knowledge and Data Engineering, 26, pp. 1819-1837, 2014, 10.1109/TKDE.2013.39.