Interpretable AI Pipeline for Ranking Influential Depression Factors from the Burns Depression Checklist

Authors

Tumpa Rani Shaha
Dept. of Computer Science and Engineering, Dhaka University of Engineering & Technology, Gazipur
Momotaz Begum
Dept. of Computer Science and Engineering, Dhaka University of Engineering & Technology, Gazipur
DOI: https://doi.org/10.52549/ijeei.v14i3.7447
Download PDF
Published: 13-09-2026 • Issue: Vol. 14 No. 3: September 2026 • Section: Regular paper

Abstract

The Burns Depression Checklist (BDC) measures depression severity by adding the scores of 25 symptom items. However, the total score does not show which items contribute most to the severity category. This study presents an interpretable machine learning pipeline to rank predictive BDC items. We analyzed responses from 654 university students in Bangladesh. We first examined the reliability and relationships of the BDC items. We then tested seven machine learning classifiers. We also applied four feature selection methods—RFE, SKB, UFS, and MIFS—and two explanation methods, SHAP and LIME. The BDC showed strong internal consistency, with a Cronbach’s alpha of 0.91. The full-item stacking model achieved 90.84% test accuracy, 86.03% balanced accuracy, and 82.60% macro-F1. We combined the six item rankings on one common scale. Loss of motivation received the highest rank. Loss of interest in work, loneliness, discouragement, hopelessness, and reduced social interest also ranked highly. These items represent reduced motivation, social withdrawal, negative mood, and negative self-view. The main contribution of this study is an item-level ranking that combines evidence from several analytical methods. However, the target categories come directly from the same 25 BDC items. Therefore, the results show how well the models reconstruct BDC severity categories, not how well they diagnose clinical depression. The rankings also do not show clinical urgency. Any positive response to a suicide related item requires separate professional assessment.
Keywords: Depression Screening Tool; Burns Depression Checklist; Machine Learning; Explainable Artificial-Intelligence; Feature Selection

References

[1] G. Dunn, P. Sham, and D. Hand, “Statistics and the nature of depression,” Psychol. Med., vol. 23, no. 4, pp. 871–889, Nov. 1993, doi: 10.1017/S0033291700026350.

[2] M. Mohit, M. Maruf, H. Ahmed, and M. Alam, “Depression and Physical Illnesses: an Update,” Bangladesh Med. J., vol. 40, no. 1, pp. 53–58, Jan. 1970, doi: 10.3329/bmj.v40i1.9966.

[3] X. Li, J. Zhou, M. Wang, C. Yang, and G. Sun, “Cardiovascular disease and depression: a narrative review,” Front. Cardiovasc. Med., vol. 10, p. 1274595, Nov. 2023, doi: 10.3389/fcvm.2023.1274595.

[4] N. Sakib et al., “Depression and suicidality among Bangladeshi students: Subject selection reasons and learning environment as potential risk factors,” Perspect. Psychiatr. Care, vol. 57, no. 3, pp. 1150–1162, Jul. 2021, doi: 10.1111/ppc.12670.

[5] M. A. Mamun et al., “Prevalence and Psychiatric Risk Factors of Excessive Internet Use among Northern Bangladeshi Job-Seeking Graduate Students: A Pilot Study,” Int. J. Ment. Health Addict., vol. 19, no. 4, pp. 908–918, Aug. 2021, doi: 10.1007/s11469-019-00066-5.

[6] S. C. Campisi, A. Ataullahjan, J.-A. B. Baxter, P. Szatmari, and Z. A. Bhutta, “Mental health interventions in adolescence,” Curr. Opin. Psychol., vol. 48, p. 101492, Dec. 2022, doi: 10.1016/j.copsyc.2022.101492.

[7] Md. M. A. Shah, S. Ahmed, and S. M. Y. Arafat, “Demography and Risk Factors of Suicide in Bangladesh: A Six-Month Paper Content Analysis,” Psychiatry J., vol. 2017, pp. 1–5, 2017, doi: 10.1155/2017/3047025.

[8] V. Ajdacic-Gross, “The Prevention of Mental Disorders has a Bright Future,” Front. Public Health, vol. 2, Jun. 2014, doi: 10.3389/fpubh.2014.00060.

[9] G. Serafini et al., “Differential clinical characteristics and possible predictors of bipolarity in a sample of unipolar and bipolar inpatients,” Psychiatry Res., vol. 270, pp. 1099–1104, Dec. 2018, doi: 10.1016/j.psychres.2018.06.041.

[10] D. Burns, H. Westra, M. Trockel, and A. Fisher, “Motivation and Changes in Depression,” Cogn. Ther. Res., vol. 37, no. 2, pp. 368–379, Apr. 2013, doi: 10.1007/s10608-012-9458-3.

[11] J. Upton, “Beck Depression Inventory (BDI),” in Encyclopedia of Behavioral Medicine, M. D. Gellman, Ed., Cham: Springer International Publishing, 2020, pp. 202–203. doi: 10.1007/978-3-030-39903-0_441.

[12] R. Sharp, “The Hamilton Rating Scale for Depression,” Occup. Med., vol. 65, no. 4, pp. 340–340, Jun. 2015, doi: 10.1093/occmed/kqv043.

[13] W. W. K. Zung, “Zung Self-Rating Depression Scale and Depression Status Inventory,” in Assessment of Depression, N. Sartorius and T. A. Ban, Eds., Berlin, Heidelberg: Springer Berlin Heidelberg, 1986, pp. 221–231. doi: 10.1007/978-3-642-70486-4_21.

[14] J. A. Yesavage et al., “Development and validation of a geriatric depression screening scale: A preliminary report,” J. Psychiatr. Res., vol. 17, no. 1, pp. 37–49, Jan. 1982, doi: 10.1016/0022-3956(82)90033-4.

[15] S. J. Brooks, S. P. Krulewicz, and S. Kutcher, “The Kutcher Adolescent Depression Scale: Assessment of Its Evaluative Properties over the Course of an 8-Week Pediatric Pharmacotherapy Trial,” J. Child Adolesc. Psychopharmacol., vol. 13, no. 3, pp. 337–349, Sep. 2003, doi: 10.1089/104454603322572679.

[16] S. A. Montgomery and M. Åsberg, “A New Depression Scale Designed to be Sensitive to Change,” Br. J. Psychiatry, vol. 134, no. 4, pp. 382–389, Apr. 1979, doi: 10.1192/bjp.134.4.382.

[17] J. L. Cox, J. M. Holden, and R. Sagovsky, “Detection of Postnatal Depression: Development of the 10-item Edinburgh Postnatal Depression Scale,” Br. J. Psychiatry, vol. 150, no. 6, pp. 782–786, Jun. 1987, doi: 10.1192/bjp.150.6.782.

[18] P. Bech, N.-A. Rasmussen, L. R. Olsen, V. Noerholm, and W. Abildgaard, “The sensitivity and specificity of the Major Depression Inventory, using the Present State Examination as the index of diagnostic validity,” J. Affect. Disord., vol. 66, no. 2–3, pp. 159–164, Oct. 2001, doi: 10.1016/S0165-0327(00)00309-8.

[19] S. Gilbody, T. Sheldon, and A. House, “Screening and case-finding instruments for depression: a meta-analysis,” Can. Med. Assoc. J., vol. 178, no. 8, pp. 997–1003, Apr. 2008, doi: 10.1503/cmaj.070281.

[20] L. Costantini et al., “A breakthrough in research on depression screening: from validation to efficacy studies,” Acta Biomed. Atenei Parm., vol. 92, no. 3, p. e2021215, Jul. 2021, doi: 10.23750/abm.v92i3.11574.

[21] S. D’Alfonso, “AI in mental health,” Curr. Opin. Psychol., vol. 36, pp. 112–117, Dec. 2020, doi: 10.1016/j.copsyc.2020.04.005.

[22] S. Aleem, N. U. Huda, R. Amin, S. Khalid, S. S. Alshamrani, and A. Alshehri, “Machine Learning Algorithms for Depression: Diagnosis, Insights, and Research Directions,” Electronics, vol. 11, no. 7, p. 1111, Mar. 2022, doi: 10.3390/electronics11071111.

[23] C. Chu, A.-L. Hsu, K.-H. Chou, P. Bandettini, and C. Lin, “Does feature selection improve classification accuracy? Impact of sample size and feature selection on classification using anatomical magnetic resonance images,” NeuroImage, vol. 60, no. 1, pp. 59–70, Mar. 2012, doi: 10.1016/j.neuroimage.2011.11.066.

[24] M. T. Ribeiro, S. Singh, and C. Guestrin, “‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco California USA: ACM, Aug. 2016, pp. 1135–1144. doi: 10.1145/2939672.2939778.

[25] V. Conceição, I. Rothes, and R. Gusmão, “The association between stigmatizing attitudes towards depression and help seeking attitudes in college students,” PLOS ONE, vol. 17, no. 2, p. e0263622, Feb. 2022, doi: 10.1371/journal.pone.0263622.

[26] 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.

[27] J. Cvetković, “Breast Cancer Patients’ Depression Prediction by Machine Learning Approach,” Cancer Invest., vol. 35, no. 8, pp. 569–572, Sep. 2017, doi: 10.1080/07357907.2017.1363892.

[28] C. Lee and H. Kim, “Machine learning-based predictive modeling of depression in hypertensive populations,” PLOS ONE, vol. 17, no. 7, p. e0272330, Jul. 2022, doi: 10.1371/journal.pone.0272330.

[29] A. A. Choudhury, Md. R. H. Khan, N. Z. Nahim, S. R. Tulon, S. Islam, and A. Chakrabarty, “Predicting Depression in Bangladeshi Undergraduates using Machine Learning,” in 2019 IEEE Region 10 Symposium (TENSYMP), Kolkata, India: IEEE, Jun. 2019, pp. 789–794. doi: 10.1109/TENSYMP46218.2019.8971369.

[30] R. Siddiqua, N. Islam, J. F. Bolaka, R. Khan, and S. Momen, “AIDA: Artificial intelligence based depression assessment applied to Bangladeshi students,” Array, vol. 18, p. 100291, Jul. 2023, doi: 10.1016/j.array.2023.100291.

[31] C. M. Hatton, L. W. Paton, D. McMillan, J. Cussens, S. Gilbody, and P. A. Tiffin, “Predicting persistent depressive symptoms in older adults: A machine learning approach to personalised mental healthcare,” J. Affect. Disord., vol. 246, pp. 857–860, Mar. 2019, doi: 10.1016/j.jad.2018.12.095.

[32] S. Jiménez-Serrano, S. Tortajada, and J. M. García-Gómez, “A Mobile Health Application to Predict Postpartum Depression Based on Machine Learning,” Telemed. E-Health, vol. 21, no. 7, pp. 567–574, Jul. 2015, doi: 10.1089/tmj.2014.0113.

[33] A. Sau and I. Bhakta, “Screening of anxiety and depression among seafarers using machine learning technology,” Inform. Med. Unlocked, vol. 16, p. 100228, 2019, doi: 10.1016/j.imu.2019.100228.

[34] T. R. Shaha and M. Begum, “Prediction of Depression Severity via Feature Grouping and Machine Learning with Burn Depression Checklist,” in Applied Intelligence for Healthcare Informatics, 1st ed., Boca Raton: CRC Press, 2025, pp. 85–99. doi: 10.1201/9781003583363-7.

[35] K. A. Adamson and S. Prion, “Reliability: Measuring Internal Consistency Using Cronbach’s α,” Clin. Simul. Nurs., vol. 9, no. 5, pp. e179–e180, May 2013, doi: 10.1016/j.ecns.2012.12.001.

[36] P. Sedgwick, “Spearman’s rank correlation coefficient,” BMJ, p. g7327, Nov. 2014, doi: 10.1136/bmj.g7327.

[37] S. Arndt, C. Turvey, and N. C. Andreasen, “Correlating and predicting psychiatric symptom ratings: Spearmans r versus Kendalls tau correlation,” J. Psychiatr. Res., vol. 33, no. 2, pp. 97–104, Mar. 1999, doi: 10.1016/S0022-3956(98)90046-2.

[38] A. M. Priyatno and T. Widiyaningtyas, “A SYSTEMATIC LITERATURE REVIEW: RECURSIVE FEATURE ELIMINATION ALGORITHMS,” JITK J. Ilmu Pengetah. Dan Teknol. Komput., vol. 9, no. 2, pp. 196–207, Feb. 2024, doi: 10.33480/jitk.v9i2.5015.

[39] M. D. Tislenko, A. V. Gaidel, and A. V. Kupriyanov, “Comparison of feature selection algorithms for Data classification problems,” in 2022 VIII International Conference on Information Technology and Nanotechnology (ITNT), Samara, Russian Federation: IEEE, May 2022, pp. 1–5. doi: 10.1109/ITNT55410.2022.9848765.

[40] S. Shakeela, N. S. Shankar, P. M. Reddy, T. K. Tulasi, and M. M. Koneru, “Optimal Ensemble Learning Based on Distinctive Feature Selection by Univariate ANOVA-F Statistics for IDS,” Int. J. Electron. Telecommun., pp. 267–275, May 2021, doi: 10.24425/ijet.2021.135975.

[41] H. Zhou, X. Wang, and R. Zhu, “Feature selection based on mutual information with correlation coefficient,” Appl. Intell., vol. 52, no. 5, pp. 5457–5474, Mar. 2022, doi: 10.1007/s10489-021-02524-x.

[42] D. Colledani, P. Anselmi, and E. Robusto, “Machine learning-decision tree classifiers in psychiatric assessment: An application to the diagnosis of major depressive disorder,” Psychiatry Res., vol. 322, p. 115127, Apr. 2023, doi: 10.1016/j.psychres.2023.115127.

[43] M. R. Gohari et al., “Using random forest to identify correlates of depression symptoms among adolescents,” Soc. Psychiatry Psychiatr. Epidemiol., vol. 59, no. 11, pp. 2063–2071, Nov. 2024, doi: 10.1007/s00127-024-02695-1.

[44] K. Taunk, S. De, S. Verma, and A. Swetapadma, “A Brief Review of Nearest Neighbor Algorithm for Learning and Classification,” in 2019 International Conference on Intelligent Computing and Control Systems (ICCS), Madurai, India: IEEE, May 2019, pp. 1255–1260. doi: 10.1109/ICCS45141.2019.9065747.

[45] I. Guyon, J. Weston, S. Barnhill, and V. Vapnik, “Gene Selection for Cancer Classification using Support Vector Machines,” Mach. Learn., vol. 46, no. 1–3, pp. 389–422, Jan. 2002, doi: 10.1023/A:1012487302797.

[46] R. P. Sonjaya, A. R. Gintara, L. S. Riza, M. Nursalman, E. Nugraha, and D. Wahyudin, “Predicting Student Depression Using the Naive Bayes Model on the Student Depression Dataset from Kaggle,” JENTIK J. Pendidik. Teknol. Inf. Dan Komun., vol. 4, no. 1, pp. 9–20, Jun. 2025, doi: 10.58723/jentik.v4i1.448.

[47] M. Skurichina and R. P. W. Duin, “Bagging, Boosting and the Random Subspace Method for Linear Classifiers,” Pattern Anal. Appl., vol. 5, no. 2, pp. 121–135, Jun. 2002, doi: 10.1007/s100440200011.

[48] A. I. Naimi and L. B. Balzer, “Stacked generalization: an introduction to super learning,” Eur. J. Epidemiol., vol. 33, no. 5, pp. 459–464, May 2018, doi: 10.1007/s10654-018-0390-z.

[49] I. Ahmed, A. Brahmacharimayum, R. H. Ali, T. A. Khan, and M. O. Ahmad, “Explainable AI for Depression Detection and Severity Classification From Activity Data: Development and Evaluation Study of an Interpretable Framework,” JMIR Ment. Health, vol. 12, pp. e72038–e72038, Sep. 2025, doi: 10.2196/72038.

[50] A. A. Jo, E. Deni Raj, A. S. Vino, and P. V. Menon, “Exploring Explainable AI for Enhanced Depression Prediction in Mental Health,” in 2024 First International Conference on Innovations in Communications, Electrical and Computer Engineering (ICICEC), Davangere, India: IEEE, Oct. 2024, pp. 1–7. doi: 10.1109/ICICEC62498.2024.10808414.

Author Biographies

Tumpa Rani Shaha
Department of Computer Science and Engineering, Gopalganj Science and Technology University; Assistant Professor.
Momotaz Begum
Dept. of Computer Science and Engineering, Dhaka University of Engineering & Technology, Gazipur, Professor

How to Cite

[1]
T. R. Shaha and M. Begum, “Interpretable AI Pipeline for Ranking Influential Depression Factors from the Burns Depression Checklist”, IJEEI, vol. 14, no. 3, pp. 776–795, Sep. 2026, doi: 10.52549/ijeei.v14i3.7447.