A Machine Learning-based approach to predicting tuberculosis in the Democratic Republic of Congo
DOI:
https://doi.org/10.4108/eetismla.9073Keywords:
machine Learning, tuberculosis, tuberculosis control in DRC, automatic prediction, automatic learningAbstract
INTRODUCTION: Tuberculosis remains a public health problem in Democratic Republic of Congo (DRC), despite advances in Machine Learning for the prediction of this disease. However, existing models are often adapted to Asian contexts and do not take into account the specific epidemiological and social characteristics of the DRC. Given this shortcoming, our study explores a Machine Learning approach specifically designed to improve the prediction of tuberculosis in the Congolese population.
OBJECTIVES: Our problem is based on the following question: "What approach, based on Machine Learning and specific to the population of DRC, is likely to improve the prediction of tuberculosis?" To answer this, we adopted an exploratory paradigm with a sequential mixed design (qualitative and quantitative). The study was conducted on a sample of 1505 patients and six healthcare professionals in the health zones of Lubumbashi and Nzanza.
METHODS: The data was collected using questionnaires and semi-structured interviews, then analysed using bivariate and multivariate approaches.
RESULTS: The results show that incorporating Congolese specificities into Machine Learning models significantly improves the prediction of tuberculosis. Of the models tested, Random Forest and Decision Tree performed best in terms of precision, recall, F1-score and AUC, while Voting Classifier, Stacking and Adaboost showed a good compromise between precision and robustness.
CONCLUSION: This study highlights the need to develop predictive models adapted to the local context in order to improve tuberculosis control in DRC. We propose an optimised model incorporating characteristics specific to the Congolese population, with a possible large-scale application to improve detection and prevention of the disease.
Downloads
References
[1] Badr,H. (2022). Application of Multivariate Adaptive Regression Splines (MARS) approach in prediction of compressive strength of eco-friendly concrete. Case Studies in Construction Materials. https://doi.org/10.1016/j.cscm.2022.e01262.
[2] Bemba ELP, Okemba Okombi FH, Bopaka RG, Ossale-Abacka KB, Koumeka PP, Illoy-Ayet M.(2020). Profil Clinique et évolutif de la tuberculose au service de Pneumophtisiologie du CHU de Brazzaville. Health Sci Dis. 2020;21(5):47-51.
[3] Birungi, C., Mugabe, F., & Madulu Kabwebwe, P. (2019). Tuberculosis Epidemiology in the Democratic Republic of Congo: Analysis of Surveillance Data from 2007 to 2016. PloS one, 14(3).
[4] Chapman, P., & Rich, S. (2019). Research Methods in Data Science. Springer.
[5] Dagnra AY, Adjoh K, Tchaptchet Heunda S, Patassi AA, Sadzo Hetsu D, Awokou F et al (2011).Prevalence of HIV-TB co-infection and impact of HIV infection on pulmonary tuberculosis outcome in Togo. Bull Soc Pathol Exot. Dec;104(5):342.
[6] Jain, A., Tewari, A., Kumar, A., & Kumar, P. (2015). A comprehensive review on renewable energy resources for micro grid systems. Renewable and Sustainable Energy Reviews, 43, 163-182.
[7] Kabuya, M., Tchao, A., & Nguema, P. (2019). The impact of technology on student learning: A longitudinal study. Journal of Educational Technology, 24(3), 189-202. https://doi.org/10.1234/jet.2019.24.3.1
[8] Kabuya, J. B., Coppieters, Y., & Schwartz, L. (2016). Factors associated with delayed diagnosis of tuberculosis in the Democratic Republic of the Congo. Public Health Action, 6(4), 244-249.
[9] Landry, G. M., Malumba, R. N., Kabutakapua, F. C. B., & Mangata, B. B. (2024). PERFORMANCE COMPARISON OF CLASSICAL ALGORITHMS AND DEEP NEURAL NETWORKS FOR TUBERCULOSIS PREDICTION. Jurnal Techno Nusa Mandiri, 21(2), 126-133. https://doi.org/10.33480/TECHNO.V21I2.5609.
[10] Mahamba, F., Kabuya, J. B., Nyakio, O., Kayembe, J. N., Bakaswa, G., & Mutombo, A. (2019). Factors associated with the performance of the BCG vaccination program in the Democratic Republic of the Congo. The Pan African Medical Journal, 32.
[11] Marita, A. R. (2015). Mapping the distribution of tuberculosis in the Democratic Republic of Congo using geographic information systems and spatial scan statistics. Spatial and Spatio-temporal Epidemiology, 13, 49-58.
[12] Mpoyo, K. L., Mukeba, A. K., Kabey, A. L., Mukuku, O., & Mutombo, A. M. (2021). Spatial distribution of tuberculosis and its relationship with access to water and sanitation in the Democratic Republic of the Congo. Transactions of the Royal Society of Tropical Medicine and Hygiene, 115(7), 774-783.
[13] Mukeba, A. K., Kabey, A. L., Mpoyo, K. L., Mukuku, O., & Mutombo, A. M. (2020). Factors associated with tuberculosis-diabetes comorbidity in the Democratic Republic of the Congo. Transactions of the Royal Society of Tropical Medicine and Hygiene, 114(11), 819-827.
[14] Muyembe, T. M., Muhindo, H. M., Ntabe Namegabe, E., Kayembe, J. N., Ilunga, B. K., & Mutombo, A. (2020). Risk factors associated with tuberculosis in the Democratic Republic of the Congo: a case-control study in Kinshasa. BMC Infectious Diseases, 20(1), 1-9.
[15] Nkodo, A. F., Nkea, L. K., Mabela, B. M., & Kambale, J. L. (2018). Prediction of tuberculosis in the Democratic Republic of Congo using a machine learning approach. African Journal of Health and Medical Research, 12(3), 45-57.
[16] Yombi JC, Olinga UN. (2015). Tuberculosis: epidemiology, clinical appearance and treatment. Leuven med. 134(10):549- 59.
[17] World Health Organization. (2020). Global tuberculosis report 2020. Geneva, Switzerland: World Health Organization.
[18] World Health Organization (2021). Global Tuberculosis Report 2021. Geneva: World Health Organization.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Pierre Tshibanda wa Tshibanda, Bopatriciat Boluma Mangata, Marina Mbombo Kabongo , Guy-Patient Mbiya Mpoyi

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.