Modern Research in Decision Making

Predicting students’ mental health using an integrated model based on data mining and multi-criteria decision-making-A case study: Kosar University of Bojnord

Document Type : Original Article

Authors

Aylin Pakzad 1
Leyla Fazli 2

1 Assistant professor, Department of Industrial Engineering, Kosar University of Bojnord, Bojnord, Iran

2 Ph.D., Lecturer, Department of Industrial Engineering, Arak University, Arak, Iran.

Abstract
Students, as future professionals and key players in social networks and community development, face various psychological challenges. Early detection and timely intervention can prevent the emergence of more serious issues. Therefore, aiming to provide an innovative framework for predicting students’ mental health, this study proposes an intelligent integration of multi-criteria decision-making (DEMATEL1), improved principal component analysis2, and machine learning techniques. First, based on a comprehensive dataset of student information and using DEMATEL technique, the complex structure of relationships between factors affecting students’ mental health is identified. Then, the target variable (mental health status) was extracted through improved principal component analysis. In the modeling phase, accordingly to comparing five machine learning algorithms, the logistic regression model was selected as the superior model due to its 100% accuracy and high interpretability. Combining the probabilistic output of this model with other algorithms improved all models’ accuracy to 100%. Coefficient analysis revealed that psychological variables-such as academic anxiety, suicidal thoughts, and depression-had the most negative impact, while marital status and interest in the field of study had protective effects on students’ mental health. The results of this study can be used as a powerful tool for early identification of students who need psychological support.

Keywords

Prediction
Multi-criteria decision-making
Data mining
Students’ mental health
Modeling
[1] Dulmus, C.N., & Wodarski, J.S. Prevention of childhood mental disorders: a literature review reflecting hope and a vision for the future. Child and Adolescent Social Work Journal, 14(3), 1997, 181-198. https://doi.org/10.1023/A:1024517619261.
[2] Mansourian, M., Khademi, S., & Marateb, H.R. A comprehensive review of computer-aided diagnosis of major mental and neurological disorders and suicide: a biostatistical perspective on data mining. Diagnostics, 11(3), 2021, 393. DOI:10.3390/diagnostics11030393. 
[3] Jha, S. The Mental healthcare act, 2017: A Ray of Hope. 2020. Available at SSRN: https://ssrn.com/abstract=3564919 or http://dx.doi.org/10.2139/ssrn.3564919.
 [4] Reddy, V.E. Mental health issues and challenges in India: A review. International Journal of Social Sciences Management and Entrepreneurship, 3(2), 2019, 72-78.
[5] König, H., König, H.H., & Konnopka, A. The excess costs of depression: a systematic review and meta-analysis. Epidemiology and Psychiatric Sciences, 29, e30. 2019. 1-16. DOI: 10.1017/S2045796019000180.
[6] Liu, Y.S., Chokka, S., Cao, B., & Chokka, P.R. Screening for bipolar disorder in a tertiary mental health center using EarlyDetect: A machine learning-based pilot study. Journal of Affective Disorders Report, 6, 2021, 100215. 1-6. https://doi.org/10.1016/j.jadr.2021.100215.
[7] Habibi, M., Bagherian Sararoudi, R., & Ghahremani, S. Mental health challenges in students: A futuristic view on depression and suicidal behaviors. Journal of Research in Behavioral Sciences. 16(4). 2019. 573-599. DOI. 10.52547/rbs.16.4.573.
[8] Khadivar, A., & Mojibian, F. Workshops clustering using a combination approach of data mining and MCDM. Modern Research in Decision Making, 3(2), 2018, 107-128. [In Persian]
[9] Karimi, M., & Afshr Kazemi, M.A. Predicting failures and planning ATM maintenance by using data mining technique. Modern Research in Decision Making, 1(3), 2016, 113-130. [In Persian]
[10] Shokohyar, S., Rezaeian, A., & Boroufar, A. Identifying the customer behavior model in life insurance Sector using data mining. Management Research in Iran, 20(4), 2021. 65-94. DOI: 20.1001.1.2322200.1395.20.4.4.5. [In Persian]
[11] Norouzi, A., Teymourpour, B., Chubdar, S., & Sepehri, M. Developing a model for discovering the causes of customer churn from banking services via hybrid approach of data mining and survey. Management Research in Iran, 15(4), 2021. 97-125. DOI: 20.1001.1.2322200.1390.15.4.5.1. [In Persian]
[12] Alonso, S.G., de La Torre-Díez, I., Hamrioui, S., López-Coronado, M., Barreno, D.C., Nozaleda, L.M., & Franco, M. Data mining algorithms and techniques in mental health: a systematic review. Journal of Medical Systems, 42(9), 2018, 161. DOI: 10.1007/s10916-018-1018-2.
[13] El-Rufaie, O.E. Primary care psychiatry: Pertinent Arabian perspectives. Eastern Mediterranean Health Journal, 11(3), 2005, 449-458. DOI: 10.26719/2005.11.3.449.
[14] World health organization (WHO). (2024, October 10). Mental health of adolescents (Fact Sheet). Retrieved from https://www.who.int/news-room/fact-sheets/detail/adolescent-mental-health
[15] Eskin, M., Kujan, O., Voracek, M., Shaheen, A., Carta, M. G., Sun, J. M., Flood, C., Poyrazli, S., Janghorbani, M., Yoshimasu, K., Mechri, A., Khader, Y., Aidoudi, K., Bakhshi, S., Harlak, H., Ahmead, M., Moro, M. F., Nawafleh, H., Phillips, L., & Abuderman, A., Tran, U. S., & Tsuno, K. Cross-national comparisons of attitudes towards suicide and suicidal persons in university students from 12 countries. Scandinavian Journal of Psychology.57(6), 2016, 554-563. DOI: 10.1111/sjop.12318. 
 [16] Mehrabian, F., Kashi, S., & Ganje Markieh, Z. Investigating the mental health status and its related factors among the students of Guilan University of Medical Sciences. Research in Medical Education, 14(1), 2022. 73-78. DOI: 10.52547/rme.14.1.73. [In Persian]
[17] Eslami, N., Lal Alizadeh, F., Mohammadzadeh, S., & Nazari, M.S. Evaluation of mental health of dental students in Mashhad School of Dentistry by SCL-90 questionnaire, 2020-2021. Journal of Mashhad Dental School, 47(4), 2023, 352-370. DOI: 10.22038/jmds.2023.66953.2194. [In Persian]
[18] Faraz, S., Azhar Ali, S.S., & Adil, S.H. Machine learning and stress assessment: A review. In Proceedings of the 2018 3rd International Conference on Emerging Trends in Engineering, Sciences and Technology (ICEEST), Karachi, Pakistan, 21-22 December 2018. DOI: 10.1109/ICEEST.2018.8643313.
[19] Liu, Y.S., Chokka, S., Cao, B., & Chokka, P.R. Screening for bipolar disorder in a tertiary mental health center using EarlyDetect: A machine learning-based pilot study. Journal of Affective Disorders Reports. 6, 2021. 100215. DOI: 10.1016/j.jadr.2021.100215.
[20] Fernandes, B.S., Karmakar, C., Tamouza, R., Tran, T., Yearwood, J., Hamdani, N., Laouamri, H., Richard, J.-R., Yolken, R., Berk, M., et al. Precision psychiatry with immunological and cognitive biomarkers: a multi-domain prediction for the diagnosis of bipolar disorder or schizophrenia using machine learning. Translational Psychiatry. 10, 2020. 162. DOI: 10.1038/s41398-020-0836-4.
[21] Alimardani, F., Cho, J.H., Boostani, R., & Hwang, H.J. Classification of bipolar disorder and schizophrenia using steady-state visual evoked potential based features. IEEE Access. 6, 2018. 40379-40388. DOI:  10.1109/ACCESS.2018.2854555.
[22] Oh, J., Oh, B.L., Lee, K.U., Chae, J.H., & Yun, K. Identifying Schizophrenia Using Structural MRI With a Deep Learning Algorithm. Front. Psychiatry, 11, 16. 2020. https://doi.org/10.3389/fpsyt.2020.00016.
[23] Cai, X.L., Xie, D.J., Madsen, K.H., Wang, Y.M., Bögemann, S.A., Cheung, E.F.C., Møller, A., & Chan, R.C.K. Generalizability of machine learning for classification of schizophrenia based on resting-state functional MRI data. Human Brain Mapping. 41,2020. 172-184. DOI: 10.1002/hbm.24797. 
[24] Ding, Y., Chen, X., Fu, Q., & Zhong, S. A depression recognition method for college students using deep integrated support vector algorithm. IEEE Access, 8, 2020. 75616-75629. DOI: 10.1109/ACCESS.2020.2987523.
[25] Li, X., La, R., Wang, Y., Niu, J., Zeng, S., Sun, S., & Zhu, J. EEG-based mild depression recognition using convolutional neural network. Medical and Biological Engineering and Computing. 57, 2019. 1341-1352. DOI: 10.1007/s11517-019-01959-2.
[26] Liu, Y., Qu, H.Q., Mentch, F.D., Qu, J., Chang, X., Nguyen, K., Tian, L., Glessner, J., Sleiman, P.M.A., & Hakonarson, H. Application of deep learning algorithm on whole genome sequencing data uncovers structural variants associated with multiple mental disorders in African American patients. Molecular Psychiatry, 27(3), 2022. 1469-1478. https://doi.org/10.1038/s41380-021-01418-1.
[27] Fariborzi, M., Zeinalnezhad, M., & Saghaei, A. Accuracy improvement of mood disorders prediction using a combination of data mining and meta-heuristic algorithms. Journal of Health and Biomedical Informatics, 9(3), 2022. 106 -119. DOI: 10.34172 /jhbmi.2022.01. [In Persian]
[28] Naghavi, A., Teismann, T., Asgari, Z., Mohebbian, M.R., Mansourian, M., & Mañanas, M. Á. Accurate diagnosis of suicide ideation/behavior using robust ensemble machine learning: A University Student Population in the Middle East and North Africa (MENA) region. Diagnostics, 10(11): 956. 2020. DOI: 10.3390/diagnostics10110956.
[29] Luo, M. Research on students’ mental health based on data mining algorithms. Journal of Healthcare Engineering. 2021 Oct 25;2021:1382559. DOI: 10.1155/2021/1382559. 
[30] Sahu, B., Kedia, J., Ranjan, V., Mahaptra, B. P., & Dehuri, S. Mental health prediction in students using data mining techniques. The Open Bioinformatics Journal, 16(1), 2023. 230720–2022–19. https://doi.org/10.2174/18750362-v16-230720-2022-19
[31] Koosha, H., Dangkoub, S., & Barzanooni, A.A. Application of data mining techniques to predict students’ mental health status to improve educational performance. Journal of Technology of Education, 13(2), 2018. 157-171. https://doi.org/10.22061/jte.2018.3075.1779. [In Persian]
[32] Trevithick, S., Flabouris, A., Tall, G., & Webber, C.F. International EMS systems: New South Wales, Australia. Resuscitation, 59(2), 2003. 165-170. DOI: 10.1016/s0300-9572(03)00343-5. 
[33] Amini, N., Yadollahi, H., & Inanlou, S.  Ranking of country provinces health. Social welfare, 5(20), 2006. 27-48. http://refahj.uswr.ac.ir/article-1-2000-en.html. [In Persian]
[34] Premachandra, I. M. A note on DEA VS. principal component analysis: An Improvement to Joe Zhu's approach. European Journal of Operational Research, 132(3), 2001. 553-560. https://doi.org/10.1016/S0377-2217(00)00145-4.
[35] Jadhav, S. D., & Channe, H. Comparative study of K-NN, naive bayes and decision tree classification techniques. International Journal of Science and Research, 5(1), 2016, 1842-1845. DOI:10.21275/v5i1.nov153131.
[36] Kutner, M. H., Nachtsheim, C. J., Neter, J., & Li, W. Applied Linear Statistical Models (5th ed.). McGraw-Hill, 2005.
[37] Williams, B., Onsman, A., & Brown, T. Exploratory factor analysis: A five-step guide for notices. Journal of Emergency Primary Helth Care, 8(3), 2010, 1-13. DOI: 10.33151/apj.8.3.93.
[38] Yim, J., & Mitchell, H. A. comparison of corporate failure models in Australia: Hybrid neural networks, logit models and discriminant analysis. Developments in Applied Artificial Intelligence, 2718, 2003, 348-358. https:

Home

Guide for Authors

Submit Manuscript

Reviewers

Contact Us