IJMSRT foster a global community of researchers and provide them with a platform to publish and access high-quality scientific content. We strive to be at the forefront of scientific communication, enabling the rapid dissemination of cutting-edge research and driving advancements in various fields.
Read moreAbstract Students’ and professionals’ mental stress has become one of the most serious public health issues; however, predictive models continue to be black boxes that do not get trusted by clinicians or teachers. In this research paper, we propose a comparison-based machine learning approach to solve the problem of classification of mental stress into three classes (Low, Moderate, High). Six machine learning algorithms such as Logistic Regression, K-Nearest Neighbors, Support Vector Machine, Random Forest, XGBoost, and LightGBM will be compared based on two feature spaces – all 20 features and the subset of 12 selected with the Mutual Information method. Evaluation was done based on the 1,100 samples survey dataset on psychological, physiological, social, environmental, and academic stressors. The best-performing single split was LightGBM, trained on features selected by the Mutual Information selection process, which resulted in an accuracy of 90.00%, Macro F1 score of 0.900, and Macro ROC-AUC of 0.987. It also showed the best mean cross-validation accuracy of 89.36% ± 0.84%. While tests show that the margin over Random Forest and Logistic Regression is directionally consistent but not statistically significant (as the number of samples is n = 5, therefore p > 0.05), it is statistically significant compared to XGBoost model (paired t-test, p = 0.011). To solve the problem of interpretability, SHapley Additive exPlanations (SHAP) were used in order to analyze the topperforming model. It showed that the key factors affecting students’ stress level are blood pressure, self esteem, and anxiety level, followed by strong contributions from academic performance and depression. The results show that compact and interpretable ensembles can compete with and even surpass the performance of complex black-box models and provide a good basis for practical applications.
REFERENCES
[1]. A.-F.A. Mentis, D. Lee, and P. Roussos, “Applications of artificial intelligence-machine learning for detection of stress: a critical overview,” Molecular Psychiatry, vol. 29, no. 6, pp. 1882–1894, 2024.
[2]. G. Taskasaplidis, D.A. Fotiadis, and P.D. Bamidis, “Review of stress detection methods using wearable sensors,” IEEE Access, vol. 12, pp. 38219–38246, 2024.
[3]. S. Gedam and S. Paul, “A review on mental stress detection using wearable sensors and machine learning techniques,” IEEE Access, vol. 9, pp. 84045–84066, 2021.
[4]. M. Bolpagni, S. Pardini, M. Dianti, and S. Gabrielli, “Personalized stress detection using biosignals from wearables: a scoping review,” Sensors, vol. 24, no. 10, p. 3221, 2024.
[5]. C. Chatzaki and M. Tsiknakis, “An overview of stress analysis based on physiological signals: systematic review of open datasets and current trends,” Sensors, vol. 25, p. 7108, 2025.
[6]. “Use of machine learning for predicting stress episodes based on wearable sensor data: a systematic review,” Computers in Biology and Medicine, vol. 198, Part A, 2025.
[7]. “An explainable machine learning framework for academic stress classification among university students: a compar-ative multi-dataset study with ablation analysis and statistical significance testing,” Frontiers in Computer Science, vol. 8, 2026.
[8]. “Explainable artificial intelligence for predictive modeling of student stress in higher education,” PMC, National Library of Medicine, 2026.
[9]. “Students’ stress prediction and explainable analysis based on improved decision trees,” PMC, National Library of Medicine, 2026.
[10]. “Enhancing diagnostic decision-making: ensemble learning techniques for reliable stress level classification,” Diagnostics, vol. 13, no. 22, p. 3455, 2023.
[11]. “Predictive modeling of students’ stress levels using machine learning algorithm,” ResearchGate preprint, 2025.
[12]. “Leveraging machine learning algorithms and explainable AI for predicting mental health disorder treatment at the workplace,” ScienceDirect, 2026.
[13]. “Explainable machine learning for mental health prediction from social media behavior: a nested crossvalidation study with SHAP and LIME interpretability,” Discover Mental Health, Springer Nature, 2026.
[14]. “Development of an explainable machine learning model for predicting depression in adults with type 2 diabetes mellitus: a cross-sectional SHAP-based analysis of NHANES 2009–2023,” Medicine, vol. 105, 2026.
[15]. S.M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 30, pp. 4765–4774, 2017.
[16]. T. Chen and C. Guestrin, “XGBoost: a scalable tree boosting system,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, pp. 785–794, 2016.
[17]. G. Ke, Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T.-Y. Liu, “LightGBM: a highly efficient gradient boosting decision tree,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 30, pp. 3146–3154, 2017.
[18]. L. Breiman, “Random forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.
Predicting Mental Stress Levels, Explainable AI (SHAP), LightGBM, Features Selection, Machine Learning for Healthcare.
Note : A published paper may take 4-5 working days from the publication date to appear in Rode, Semantic Scholar, and open alex.
