Cost-Sensitive DASS-42 Risk Classification in Young Adults Using Asymmetric Misclassification Costs

Iklima Fatma  Aliena; Riska  Dhenabayu; Rully  Mujiastuti; Tatiana Starostina; Ratih  Amelia

doi:10.59395/ijadis.v7i3.1642

Authors

Iklima Fatma Aliena Department of Digital Business, Universitas Negeri Surabaya, Indonesia
Riska Dhenabayu Department of Digital Business, Universitas Negeri Surabaya, Indonesia https://orcid.org/0000-0002-6530-2099
Rully Mujiastuti Department of Informatics Engineering, Universitas Muhammadiyah Jakarta, Indonesia https://orcid.org/0000-0003-2378-3696
Tatiana Starostina Department of Texts, Languages and Digital Tools, Higher School of Economics University, Russia
Ratih Amelia Department of Digital Business, Universitas Negeri Surabaya, Indonesia

DOI:

https://doi.org/10.59395/ijadis.v7i3.1642

Keywords:

Asymmetric Misclassification , DASS-42, Cost-Sensitive Learning, Mental Health Classification, Young Adults

Abstract

Young adults experience elevated mental health risk, yet most DASS-42 machine learning studies use heterogeneous populations, single-split validation, and accuracy-driven evaluation that treats clinically harmful errors as equal. This study developed a cost-sensitive machine learning framework for three-class mental health risk screening among young adults aged 18–25. A total of 23,039 DASS-42 records were filtered from an international survey and labeled as Low, Moderate, or High risk using the Maximum Severity Rule across depression, anxiety, and stress scores. Six models Naïve Bayes, Decision Tree, Random Forest, XGBoost, LightGBM, and Artificial Neural Network were compared. Class imbalance was handled using class weighting, while Cost-Proportionate Weighting imposed larger penalties on high-risk underclassification through an asymmetric cost matrix. Six models were evaluated using 10-fold stratified cross-validation and held-out testing, with nested hyperparameter tuning for the four tree-based models and fold-wise early stopping for the neural network. Performance was measured using Macro F1-score, ROC-AUC, confusion matrices, and total misclassification cost. The neural network achieved the strongest baseline performance (Macro F1 = 0.9686). Under CPW, its total CSL cost fell to 131, the lowest among all six models. CPW cut cost across all models, from 5.4% to 31.05%, with the neural network showing the largest reduction. Five of six models produced zero Low-High errors; only Decision Tree missed that mark. A rule-based scoring classifier reached 100% accuracy by construction, indicating near-perfect model scores reflect reconstruction of the scoring rule rather than genuine clinical prediction. These findings support cost-aware DASS-42-based screening for early risk identification.

6 2

Downloads

Download data is not yet available.

References

[1] World Health Organization, Mental disorders. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/mental-disorders

[2] G. V. Benito, Machine learning for anxiety and depression profiling and risk assessment in the aftermath of an emergency, Artif Intell Med, vol. 157, p. 102991, 2024, doi: 10.1016/j.artmed.2024.102991.

[3] B. Ahammed, K. Alam, Z. Hoque, and S. A. Keramat, Mental health at risk: Predicting psychological distress in Australian youth through machine learning models, J. Affect. Disord., vol. 395, p. 120679, Feb. 2026, doi: 10.1016/j.jad.2025.120679.

[4] W. Li, Z. Zhao, D. Chen, Y. Peng, and Z. Lu, Prevalence and associated factors of depression and anxiety symptoms among college students: a systematic review and metaanalysis, J. Child Psychol. Psychiatry, vol. 63, no. 11, pp. 12221230, Nov. 2022, doi: 10.1111/jcpp.13606.

[5] A. Daza, N. Saboya, J. I. Necochea-Chamorro, K. Zavaleta Ramos, and Y. D. R. Vsquez Valencia, Systematic review of machine learning techniques to predict anxiety and stress in college students, Inform. Med. Unlocked, vol. 43, p. 101391, 2023, doi: 10.1016/j.imu.2023.101391.

[6] R. Zhao et al., Research Review: Helpseeking intentions, behaviors, and barriers in college students a systematic review and metaanalysis, J. Child Psychol. Psychiatry, vol. 66, no. 10, pp. 15931605, Oct. 2025, doi: 10.1111/jcpp.14145.

[7] A. Wajid, F. Azam, and M. W. Anwar, Applications of artificial intelligence in mental health: a systematic literature review, Discov. Artif. Intell., vol. 5, no. 1, p. 332, Nov. 2025, doi: 10.1007/s44163-025-00569-2.

[8] R. Chahar and A. K. Dubey, Machine Intelligence for Mental Health Diagnosis: A Systematic Review of Methods, Algorithms, and Key Challenges, Comput. Mater. Contin., vol. 86, no. 1, pp. 165, 2026, doi: 10.32604/cmc.2025.066990.

[9] X. Shi, J. Pan, D. Yuan, M. Li, and Y. Pan, Advanced data analysis and prediction model for student mental health risk assessment, Front. Psychol., vol. 16, p. 1682083, Nov. 2025, doi: 10.3389/fpsyg.2025.1682083.

[10] M. Makara-Studziska, E. Tyburski, M. Zauski, K. Adamczyk, J. Mesterhazy, and A. Mesterhazy, Confirmatory Factor Analysis of Three Versions of the Depression Anxiety Stress Scale (DASS-42, DASS-21, and DASS-12) in Polish Adults, Front. Psychiatry, vol. 12, p. 770532, Jan. 2022, doi: 10.3389/fpsyt.2021.770532.

[11] P. Kumar, S. Garg, and A. Garg, Assessment of Anxiety, Depression and Stress using Machine Learning Models, Procedia Comput. Sci., vol. 171, pp. 19891998, 2020, doi: 10.1016/j.procs.2020.04.213.

[12] H. Yang, Y. H. Sun, and K. Lee, Concise multi-class anxiety disorder risk assessment: A novel advanced machine learning approach, J. Anxiety Disord., vol. 112, p. 103018, Jun. 2025, doi: 10.1016/j.janxdis.2025.103018.

[13] E. S. Mohamed, T. A. Naqishbandi, S. A. C. Bukhari, I. Rauf, V. Sawrikar, and A. Hussain, A hybrid mental health prediction model using Support Vector Machine, Multilayer Perceptron, and Random Forest algorithms, Healthc. Anal., vol. 3, p. 100185, 2023, doi: https://doi.org/10.1016/j.health.2023.100185.

[14] J. Biswas, Md. N. Hasan, Md. S. R. Gazi, and Md. M. Rahman, Enhancing mental well-being: An artificial intelligence model for predicting mental disorders, Array, vol. 26, p. 100417, Jul. 2025, doi: 10.1016/j.array.2025.100417.

[15] N. K. Iyortsuun, S.-H. Kim, M. Jhon, H.-J. Yang, and S. Pant, A Review of Machine Learning and Deep Learning Approaches on Mental Health Diagnosis, Healthcare, vol. 11, no. 3, p. 285, Jan. 2023, doi: 10.3390/healthcare11030285.

[16] R. Dehbozorgi et al., The application of artificial intelligence in the field of mental health: a systematic review, BMC Psychiatry, vol. 25, no. 1, p. 132, Feb. 2025, doi: 10.1186/s12888-025-06483-2.

[17] M. Bader, M. Abdelwanis, M. Maalouf, and H. F. Jelinek, Detecting depression severity using weighted random forest and oxidative stress biomarkers, Sci. Rep., vol. 14, no. 1, p. 16328, Jul. 2024, doi: 10.1038/s41598-024-67251-y.

[18] H. I. Dino and M. M. Hassan, Classification of neurological and mental health disorders based on multimodal approaches: A comprehensive review, Neurosci. Biobehav. Rev., vol. 179, p. 106399, Dec. 2025, doi: 10.1016/j.neubiorev.2025.106399.

[19] I. Araf, A. Idri, and I. Chairi, Cost-sensitive learning for imbalanced medical data: a review, Artif. Intell. Rev., vol. 57, no. 4, p. 80, Mar. 2024, doi: 10.1007/s10462-023-10652-8.

[20] S. H. Lovibond and P. F. Lovibond, Manual for the depression anxiety stress scales, 2. ed. in Psychology Foundation monograph. Sydney: Psychology Foundation, 1995.

[21] L. Sasse et al., Overview of leakage scenarios in supervised machine learning, J. Big Data, vol. 12, no. 1, p. 135, May 2025, doi: 10.1186/s40537-025-01193-8.

[22] M. Hagmann and S. Riezler, False perfection in machine prediction: Detecting and assessing circularity problems in machine learning, Dec. 13, 2021, arXiv: arXiv:2106.12417. doi: 10.48550/arXiv.2106.12417.

[23] B. Zadrozny, J. Langford, and N. Abe, Cost-sensitive learning by cost-proportionate example weighting, in Third IEEE International Conference on Data Mining, 2003, pp. 435442. doi: 10.1109/ICDM.2003.1250950.

[24] G. S. Hida and A. C. Alves Do Nascimento, Overview of machine learning in class imbalance scenarios: Trends, challenges, and approaches, Expert Syst. Appl., vol. 298, p. 129592, Mar. 2026, doi: 10.1016/j.eswa.2025.129592.

[25] L. Greenwell, Depression Anxiety Stress Scales Responses. 2019. [Online]. Available: https://www.kaggle.com/datasets/lucasgreenwell/depression-anxiety-stress-scales-responses

[26] Z. Wang et al., Global, regional, and national burden of mental disorders among adolescents and young adults, 19902021: a systematic analysis for the Global Burden of Disease Study 2021, Transl. Psychiatry, vol. 15, no. 1, p. 397, Oct. 2025, doi: 10.1038/s41398-025-03623-w.

[27] I. Rish, An empirical study of the naive Bayes classier, 2001.

[28] L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone, Classification and regression trees. Boca Raton London New York Washington, D.C: Chapman & Hall/CRC, 1984. doi: 10.1201/9781315139470.

[29] L. Breiman, Random Forests, Mach. Learn., vol. 45, no. 1, pp. 532, Oct. 2001, doi: 10.1023/A:1010933404324.

[30] T. Chen and C. Guestrin, XGBoost: A Scalable Tree Boosting System, in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug. 2016, pp. 785794. doi: 10.1145/2939672.2939785.

[31] G. Ke et al., LightGBM: A Highly Efficient Gradient Boosting Decision Tree, 2017.

[32] Y. LeCun, Y. Bengio, and G. Hinton, Deep learning, Nature, vol. 521, no. 7553, pp. 436444, May 2015, doi: 10.1038/nature14539.

[33] B. Davazdahemami, P. Peng, and D. Delen, A deep learning approach for predicting early bounce-backs to the emergency departments, Healthc. Anal., vol. 2, p. 100018, Nov. 2022, doi: 10.1016/j.health.2022.100018.

[34] B. Davazdahemami, H. M. Zolbanin, and D. Delen, An explanatory machine learning framework for studying pandemics: The case of COVID-19 emergency department readmissions, Decis. Support Syst., vol. 161, p. 113730, Oct. 2022, doi: 10.1016/j.dss.2022.113730.

[35] Z. Jiang and W. Zhao, Fusion Algorithm for Imbalanced EEG Data Processing in Seizure Detection, Seizure, vol. 91, pp. 207211, Oct. 2021, doi: 10.1016/j.seizure.2021.06.023.

[36] A. Newaz, M. S. Mohosheu, and Md. A. Al Noman, Predicting complications of myocardial infarction within several hours of hospitalization using data mining techniques, Inform. Med. Unlocked, vol. 42, p. 101361, 2023, doi: 10.1016/j.imu.2023.101361.

[37] L. Rabkin, I. Cohen, and G. Singer, Resource allocation in ordinal classification problems: A prescriptive framework utilizing machine learning and mathematical programming, Eng. Appl. Artif. Intell., vol. 132, p. 107914, Jun. 2024, doi: 10.1016/j.engappai.2024.107914.

[38] T. Fawcett, An introduction to ROC analysis, Pattern Recognit. Lett., vol. 27, no. 8, pp. 861874, Jun. 2006, doi: 10.1016/j.patrec.2005.10.010.

[39] W. L. Ku and H. Min, Evaluating Machine Learning Stability in Predicting Depression and Anxiety Amidst Subjective Response Errors, Healthcare, vol. 12, no. 6, p. 625, Mar. 2024, doi: 10.3390/healthcare12060625.

[40] Md. S. Zulfiker, N. Kabir, A. A. Biswas, T. Nazneen, and M. S. Uddin, An in-depth analysis of machine learning approaches to predict depression, Curr. Res. Behav. Sci., vol. 2, p. 100044, Nov. 2021, doi: 10.1016/j.crbeha.2021.100044.

[41] U. Madububambachu, A. Ukpebor, and U. Ihezue, Machine Learning Techniques to Predict Mental Health Diagnoses: A Systematic Literature Review, Clin. Pract. Epidemiol. Ment. Health, vol. 20, no. 1, p. e17450179315688, Jul. 2024, doi: 10.2174/0117450179315688240607052117.

[42] T. ShamsEldin et al., Artificial intelligence for predicting depression anxiety and stress using psychometric data, Sci. Rep., vol. 15, no. 1, p. 37282, Oct. 2025, doi: 10.1038/s41598-025-21301-1.

[43] N. Park and H. Woo, Change in lifestyle and mental health in young adults: an exploratory study with hybrid machine learning, Front. Public Health, vol. 13, p. 1562280, Jun. 2025, doi: 10.3389/fpubh.2025.1562280.

[44] M. Razavi et al., Machine Learning, Deep Learning, and Data Preprocessing Techniques for Detecting, Predicting, and Monitoring Stress and Stress-Related Mental Disorders: Scoping Review, JMIR Ment. Health, vol. 11, p. e53714, Aug. 2024, doi: 10.2196/53714.