Explainable XGBoost Early-Warning Framework  for Academic Stress-Based Student Mental Health Risk Mapping

Supriyono; Heru Noviyanto Firmansyah; Soni Adiyono

doi:10.29207/resti.v10i4.7812

Authors

Supriyono Universitas Muria Kudus
Heru Noviyanto Firmansyah Universitas Muria Kudus
Soni Adiyono Universitas Muria Kudus

DOI:

https://doi.org/10.29207/resti.v10i4.7812

Keywords:

academic stress, DASS-21, explainable AI, K-Means clustering, mental health risk, XGBoost

Abstract

Existing university mental health monitoring often depends on voluntary help-seeking or manual questionnaire interpretation, which may delay early support for students experiencing academic stress. This study proposes an explainable XGBoost-based early-warning framework for non-clinical mapping of student mental health risk from academic stress indicators. The single-site dataset comprised 1,002 anonymized student records from Universitas Muria Kudus. K-Means clustering was used to transform DASS-21 depression, anxiety, and stress scores into low, moderate-, and high-risk categories, while XGBoost predicted the cluster-derived labels using seven single-item academic stress indicators and engineered aggregate and interaction features. On a stratified hold-out testing set of 201 records, the model achieved weighted precision, recall, and F1-score values of 0.8907, 0.8905, and 0.8906, respectively, with class-level F1-scores of 0.9109 for low risk, 0.8900 for moderate risk, and 0.8713 for high risk. Additional ablation, clustering sensitivity, subgroup, threshold, and SHAP stability analyses were conducted to strengthen robustness and interpretability. The findings show that cumulative academic stress and interaction features involving parental expectations, exam anxiety, and learning-method adaptation were consistently influential predictors. The framework is intended to support early institutional prioritization and counseling referral, not clinical diagnosis. Generalization remains limited by the single-institution sample and the use of single-item academic stress indicators; therefore, local retraining and recalibration are required before institutional deployment, including implementation of the Streamlit prototype.

Downloads

Download data is not yet available.

References

S. K. Lipson et al., “Trends in college student mental health and help-seeking by race/ethnicity: Findings from the national healthy minds study, 2013–2021,” J. Affect. Disord., vol. 306, pp. 138–147, 2022, doi: https://doi.org/10.1016/j.jad.2022.03.038.

Y. Deng, J. Cherian, N. Un, N. Khan, and K. Kumari, “Family and Academic Stress and Their Impact on Students ’ Depression Level and Academic Performance,” Front. Psychiatry, vol. 13, no. June, pp. 1–13, 2022, doi: 10.3389/fpsyt.2022.869337.

G. Barbayannis, M. Bandari, X. Zheng, H. Baquerizo, K. W. Pecor, and X. Ming, “Academic Stress and Mental Well-Being in College Students: Correlations, Affected Groups, and COVID-19,” Front. Psychol., vol. 13, no. May, pp. 1–10, 2022, doi: 10.3389/fpsyg.2022.886344.

D. T. H. Le, R. C. K. Chan, J. Hao, and R. B. Wilkinson, “The Mental Health of Australian, Chinese and Vietnamese University Students: A Cross-Cultural Comparison of the DASS-21,” Int. J. Psychol., vol. 60, no. 4, 2025, doi: 10.1002/ijop.70057.

M. A. Castillo-Díaz and C. A. H. Periañez, “Dimensionality, reliability, invariance, and item analysis of the depression, anxiety, and stress scale-21 (DASS-21) in Honduran and Colombian university students,” BMC Psychol., vol. 13, no. 1, 2025, doi: 10.1186/s40359-025-03742-5.

M. E. Hasan et al., “Prevalence, associated factors, and machine learning-based prediction of depression, anxiety, and stress among university students: a cross-sectional study from Bangladesh,” J. Heal. Popul. Nutr., vol. 44, no. 1, 2025, doi: 10.1186/s41043-025-01095-8.

J. Chen, “Student Mental Health Risk Prediction Based on Apriori Algorithm in the Context of Big Data,” in 2024 International Conference on Electrical Drives, Power Electronics & Engineering (EDPEE), 2024, pp. 615–618. doi: 10.1109/EDPEE61724.2024.00120.

M. F. Chan, A. Al Harrasi, H. Al Sinawi, and M. Al Alawi, “Sociodemographics and clinical profiling of students seeking mental health services : a cluster analysis in a public university in Oman,” Learn. Teach. High. Educ. Gulf Perspect., 2026, doi: 10.1108/LTHE-07-2025-0048.

F. N. Al-Wesabi, H. Alsolai, A. M. Hilal, M. A. Hamza, M. Al Duhayyim, and N. Negm, “Machine learning based depression, anxiety, and stress predictive model during COVID-19 crisis,” Comput. Mater. Contin., vol. 70, no. 3, pp. 5803–5820, 2022, doi: 10.32604/cmc.2022.021195.

D. Duan, “Using a predictive model based on fuzzy logic methods to test the mental health of students,” Discov. Comput., vol. 29, no. 1, 2026, doi: 10.1007/s10791-026-09962-6.

K. Lamba, S. Rani, and M. Shabaz, “Explainable machine learning for mental health prediction from social media behavior: a nested cross-validation study with {SHAP} and {LIME} interpretability,” Discov. Ment. Heal., vol. 6, no. 1, 2026, doi: 10.1007/s44192-026-00373-z.

Y. Wang and Y. Tong, “A Machine Learning Approach to Explore Perceived Stress in College Students Post {COVID-19} Pandemic,” Int. J. Inf. Syst. Model. Des., vol. 16, no. 1, pp. 1–21, 2025, doi: 10.4018/IJISMD.391327.

A. Marika, “Identifying Profiles Of Psychological Distress , Psychological Flexibility , And Mindfulness Among Finnish University Students Participating In A Blended Intervention,” Univ. JYVÄSKYLÄ Dep. Psychol., no. May, 2025.

K. N. Singh, H. P. Singh, M. Panjwani, and S. Dahima, “Mental Health Detection and Prediction through Machine Learning Technology,” in Brain Informatics Technology, John Wiley & Sons, Ltd, 2025, ch. 16, pp. 403–423. doi: https://doi.org/10.1002/9781394345625.ch16.

S. Risal, F. Apriyadi, A. Sumardin, A. D. Achmad, and A. N. Puteri, “Enhancing Stroke Prediction with Logistic Regression and Support Vector Machine Using Oversampling Techniques,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 9, no. 3, pp. 646–658, 2025, doi: 10.29207/resti.v9i3.6431.

H. D. Putra, L. Khairani, and D. Hastari, “Comparison of Naive Bayes Classifier and Support Vector Machine Algorithms for Classifying Student Mental Health Data,” in SENTIMAS: Seminar Nasional Penelitian dan Pengabdian Masyarakat, 2023, pp. 120–125. [Online]. Available: https://journal.irpi.or.id/index.php/sentimas/article/view/586/347

S. Kapoor and A. Narayanan, “Leakage and the reproducibility crisis in machine-learning-based science,” Patterns, vol. 4, no. 9, p. 100804, 2023, doi: 10.1016/j.patter.2023.100804.

H. Guo, H. Zhang, and T. Erdenebold, “An interpretable cross-regional prediction study of university students’ mental health based on XGBoost and SHAP,” IEEE Access, vol. 14, no. April, pp. 48025–48039, 2026, doi: 10.1109/ACCESS.2026.3676575.

R. Shwartz-Ziv and A. Armon, “Tabular data: Deep learning is not all you need,” Inf. Fusion, vol. 81, pp. 84–90, 2022, doi: https://doi.org/10.1016/j.inffus.2021.11.011.

S. Ali et al., “Explainable Artificial Intelligence (XAI): What we know and what is left to attain Trustworthy Artificial Intelligence,” Inf. Fusion, vol. 99, p. 101805, 2023, doi: https://doi.org/10.1016/j.inffus.2023.101805.

P. Rajpurkar, E. Chen, O. Banerjee, and E. J. Topol, “AI in health and medicine,” Nat. Med., vol. 28, no. 1, pp. 31–38, 2022, doi: 10.1038/s41591-021-01614-0.

B. Vasey et al., “Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI,” Nat. Med., vol. 28, no. 5, pp. 924–933, 2022, doi: 10.1038/s41591-022-01772-9.

N. Naik et al., “Legal and Ethical Consideration in Artificial Intelligence in Healthcare: Who Takes Responsibility?,” Front. Surg., vol. 9, no. March, pp. 1–6, 2022, doi: 10.3389/fsurg.2022.862322.

P. Córdova Olivera, P. Gasser Gordillo, H. Naranjo Mejía, I. La Fuente Taborga, A. Grajeda Chacón, and A. Sanjinés Unzueta, “Academic stress as a predictor of mental health in university students,” Cogent Educ., vol. 10, no. 2, 2023, doi: 10.1080/2331186X.2023.2232686.

R. R. Bojja, “A Comparative Study of Supervised and Unsupervised Learning Approaches,” Imrjr, vol. 2, no. 4, pp. 80–88, 2025, doi: 10.17148/imrjr.2025.020411.

I. H. Sarker, “Machine Learning: Algorithms, Real-World Applications and Research Directions,” SN Comput. Sci., vol. 2, no. 3, p. 160, 2021, doi: 10.1007/s42979-021-00592-x.

C. Schröer, F. Kruse, and J. M. Gómez, “A Systematic Literature Review on Applying CRISP-DM Process Model,” Procedia Comput. Sci., vol. 181, pp. 526–534, 2021, doi: 10.1016/j.procs.2021.01.199.

A. M. Ikotun, A. E. Ezugwu, L. Abualigah, B. Abuhaija, and J. Heming, “K-means clustering algorithms: A comprehensive review, variants analysis, and advances in the era of big data,” Inf. Sci. (Ny)., vol. 622, pp. 178–210, 2023, doi: https://doi.org/10.1016/j.ins.2022.11.139.

W. Chen, K. Yang, Z. Yu, Y. Shi, and C. L. P. Chen, A survey on imbalanced learning: latest research, applications and future directions, vol. 57, no. 6. 2024. doi: 10.1007/s10462-024-10759-6.

S. Rahmawati, A. Wibowo, and A. F. N. Masruriyah, “Improving Diabetes Prediction Accuracy in Indonesia: A Comparative Analysis of {SVM}, Logistic Regression, and Naive Bayes with {SMOTE} and {ADASYN},” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 8, no. 5, pp. 607–614, 2024, doi: 10.29207/resti.v8i5.5980.

L. Longo et al., “Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions,” Inf. Fusion, vol. 106, no. February, p. 102301, 2024, doi: 10.1016/j.inffus.2024.102301.

N. L. Wibowo, M. A. Soeleman, and A. Z. Fanani, “Antlion Optimizer Algorithm Modification for Initial Centroid Determination in K-means Algorithm,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 7, no. 4, pp. 870–883, 2023, doi: 10.29207/resti.v7i4.4997.

A. E. Ezugwu et al., “A comprehensive survey of clustering algorithms: State-of-the-art machine learning applications, taxonomy, challenges, and future research prospects,” Eng. Appl. Artif. Intell., vol. 110, p. 104743, 2022, doi: https://doi.org/10.1016/j.engappai.2022.104743.

K. K. Pandey and D. Shukla, “Min–max kurtosis mean distance based k-means initial centroid initialization method for big genomic data clustering,” Evol. Intell., vol. 16, no. 3, pp. 1055–1076, 2023, doi: 10.1007/s12065-022-00720-3.

R. Wardhani, N. Nafiiyah, and M. Kemal Farouq, “K-Means Clustering of the Mental Health of Engineering Students at the Universitas Islam Lamongan,” in 2023 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT), 2023, pp. 181–186. doi: 10.1109/COMNETSAT59769.2023.10420590.

G. T. Reddy et al., “Analysis of Dimensionality Reduction Techniques on Big Data,” IEEE Access, vol. 8, pp. 54776–54788, 2020, doi: 10.1109/ACCESS.2020.2980942.

S. Liang, “Comparative Analysis of SVM, XGBoost and Neural Network on Hate Speech Classification,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 5, no. 5, pp. 896–903, 2021, doi: 10.29207/resti.v5i5.3506.

A. M. Carrington et al., “Deep ROC Analysis and AUC as Balanced Average Accuracy, for Improved Classifier Selection, Audit and Explanation,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 1, pp. 329–341, 2023, doi: 10.1109/TPAMI.2022.3145392.