Prediction Models for Therapeutic Outcomes in Adult Pulmonary Tuberculosis
Keywords:
pulmonary tuberculosis; predictive models; machine learning; prognosis; algorithms.Abstract
Introduction: Tuberculosis persists as one of the leading causes of death worldwide from infectious diseases and affects 10.8 million people in 2023. Predictive models of therapeutic outcomes have emerged as promising tools to identify patients at high risk of treatment failure, optimize resources, and improve clinical results in pulmonary tuberculosis.
Objective: To determine the methodological quality and clinical applicability of prediction models for therapeutic outcomes in adult pulmonary tuberculosis.
Methods: A systematic review registered in PROSPERO (CRD420251110613) that followed the PRISAME 2020 guidelines. We searched for studies in multiple databases between January 2019 and January 2025. These studies included predictive models developed using logistic regression, machine learning, and neural networks for pulmonary tuberculosis. The risk of bias assessment employed the PROBAST tool. We performed a structured narrative synthesis and a meta‑analysis when appropriate, with a GRADE assessment of the certainty of the evidence.
Results: The meta‑analysis revealed robust predictive factors: diabetes mellitus (OR: 2,159; 95 % CI: 1,433–3,236), pulmonary cavities (OR: 2,707; 95 % CI: 1,840–3,970), tracheobronchial tuberculosis (OR: 2,628; 95 % CI: 1,810–3,808), and HIV infection (OR: 2,034; 95 % CI: 1,322–3,131). Machine learning models showed high precision (AUC > 0,80), with XGBoost, Random Forest, and neural networks standing out.
Conclusions: The predictive models identified provide valuable tools for risk stratification in pulmonary tuberculosis, with diabetes mellitus, pulmonary cavities, and tracheobronchial tuberculosis as consistent predictors. Nevertheless, robust external validation is required before their routine clinical implementation to contribute to the 90% treatment success goal of the End TB Strategy.
Downloads
References
1. Organización Mundial de la Salud. Global tuberculosis report 2024. Ginebra: Organización Mundial de la Salud; 2024 [acceso 28/07/2025]. Disponible en: https://www.who.int/teams/global-programme-on-tuberculosis-and-lung-health/tb-reports/global-tuberculosis-report-2024
2. Organización Mundial de la Salud. Key updates to the treatment of drug-resistant tuberculosis: rapid communication. Ginebra: Organización Mundial de la Salud; 2024 [acceso 28/07/2025]. Disponible en: https://www.who.int/publications/i/item/B09123
3. Peetluk LS, Rebeiro PF, Ridolfi FM, Andrade BB, Cordeiro-Santos M, Kritski A, et al. A Clinical Prediction Model for Unsuccessful Pulmonary Tuberculosis Treatment Outcomes. Clin Infect Dis. 2022 [acceso 28/07/2025];74(6):973-82. Disponible en: https://academic.oup.com/cid/article/74/6/973/6313211
4. Peetluk LS, Ridolfi FM, Rebeiro PF, Liu D, Rolla VC, Sterling TR. Systematic review of prediction models for pulmonary tuberculosis treatment outcomes in adults. BMJ Open. 2021 [acceso 28/07/2025];11(3):e044687. Disponible en: https://bmjopen.bmj.com/content/11/3/e044687
5. Wang Y, Chen L, Zhang M, Liu X, Huang J, Li P. Development of a clinical prediction model for poor treatment outcomes in the intensive phase in patients with initial pulmonary TB treatment. Front Med (Lausanne). 2025 [acceso 28/07/2025];12:1472295. Disponible en: https://www.frontiersin.org/articles/10.3389/fmed.2025.1472295/full
6. Smith A, Rodriguez B, Johnson C, Williams D, Brown E, Davis F. Clinical and bacterial determinants of unfavorable tuberculosis treatment outcomes: an observational study in Georgia. 2025 [acceso 28/07/2025]. Disponible en: https://www.medrxiv.org/content/10.1101/2025.01.20.25320828v1
7. Chen J, Wang X, Li Y, Zhang H, Liu M, Zhao K. Predictive machine learning models for anticipating loss to follow-up in tuberculosis patients throughout anti-TB treatment journey. Sci Rep. 2024 [acceso 28/07/2025];14:24685. Disponible en: https://www.nature.com/articles/s41598-024-74942-z
8. Mariyam KB, Jose SA, Jirawattanapanit A, Mathew K. A comprehensive study on tuberculosis prediction models: Integrating machine learning into epidemiological analysis. J Theor Biol. 2025 [acceso 28/07/2025];597:111988. Disponible en: https://www.sciencedirect.com/science/article/abs/pii/S002251932400273X
9. Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. Declaración PRISMA 2020: una guía actualizada para la publicación de revisiones sistemáticas. Rev Esp Cardiol. 2021 [acceso 28/07/2025];74(9):790-9. Disponible en: https://www.prisma- statement.org/s/PRISMA-2020-Spanish.pdf
10. Steyerberg EW, Moons KGM, van der Windt DA. Prognosis Research Strategy (PROGRESS) 3: prognostic model research. PLoS Med. 2013;10(2):e1001381. DOI: https://doi.org/10.1371/journal.pmed.1001381
11. Kirmaryr M, Quilodán C, Valente B, Loezar C, Garegnani L, Ariel-Franco JV. Metodología GRADE, parte I: cómo evaluar la certeza de la evidencia. Medwave. 2021 [acceso 29/07/2025];21(02):e8109. Disponible en: https://www.medwave.cl/medios/medwave/Marzo2021/PDF/medwave-2021-02-8109.pdf
12. Lu B, Shi Y, Wang M, Jin C, Liu C, Pan X, Chen X. Development of a clinical prediction model for poor treatment outcomes in the intensive phase in patients with initial treatment of pulmonary tuberculosis. Front Med (Lausanne). 2025;12:1472295. DOI: https://doi.org/10.3389/fmed.2025.1472295
13. Mahawan N, Rattananupong T, Sri-Uam P, Jiamjarasrangsi W. Performance of five dynamic models in predicting tuberculosis incidence in three prisons in Thailand. PLoS One. 2025 [acceso 31/07/2025];20(1):e0318089. DOI: https://doi.org/10.1371/journal.pone.0318089
14. Marambire ET, Kabali E, Naicker N. Prediction models for Mtb infection among adolescent and adult household contacts. PLOS Glob Public Health. 2025;5(1):e0004340. DOI: https://doi.org/10.1371/journal.pgph.0004340
15. Testagrose C, Pandey S, Serajian M. Leveraging large language models to predict antibiotic resistance in Mycobacterium tuberculosis. Bioinformatics [Internet]. 2025 [acceso 31/07/2025];41(Supplement_1):i40-8. DOI: https://doi.org/10.1093/bioinformatics/btaf232
16. Ghermi M, Messedi M, Adida C. TubIAgnosis: A machine learning-based web application for active tuberculosis diagnosis using complete blood count data. Digit Health. 2024;10:20552076241278211. DOI: https://doi.org/10.1177/20552076241278211
17. Karmani P, Chandio AA, Korejo IA, Samuel OW, Aborokbah M. Machine learning based tuberculosis (ML-TB) health predictor model. PeerJ Comput Sci. 2024;10:e2397. DOI: https://doi.org/10.7717/peerj-cs.2397
18. Zhu Q, Liu J. A. A united model for diagnosing pulmonary tuberculosis with random forest and artificial neural network. Front Genet. 2023;14:1094099. DOI: https://doi.org/10.3389/fgene.2023.1094099
19. Hall MB, Lima L, Coin LJM, Iqbal Z. Drug resistance prediction for Mycobacterium tuberculosis with reference graphs. Microb Genom. 2023;9(8):mgen001081. DOI: https://doi.org/10.1099/mgen.0.001081
20. Rashidi HH, Khan IH, Dang LT. Prediction of tuberculosis using an automated machine learning platform for models trained on synthetic data. J Pathol Inform. 2022;13:10. DOI: https://doi.org/10.4103/jpi.jpi_75_21
21. Navarro-Ballester A, Marco-Domenech SF, Fernández García P. Modelo predictivo clínico-radiológico para diagnosticar tuberculosis pulmonar activa. Rev Chil Radiol. 2019;25(2):47-59. DOI: https://doi.org/10.4067/S0717-93082019000200047
22. Riza AL, Pearson F, Ugarte-Gil C, Alisjahbana B, van de Vijver S, Panduru NM, et al. Clinical management of concurrent diabetes and tuberculosis and the implications for patient services. Lancet Diabetes Endocrinol. 2024 [acceso 31/07/2025];12(7):501-12. Disponible en: https://www.thelancet.com/journals/landia/article/PIIS2213-8587(24)00135-0/fulltext
23. Baker MA, Harries AD, Jeon CY, Hart JE, Kapur A, Lönnroth K, et al. The impact of diabetes on tuberculosis treatment outcomes: a systematic review. BMC Med. 2023 [acceso 31/07/2025];21(1):345. Disponible en: https://bmcmedicine.biomedcentral.com/articles/10.1186/s12916-023-03043-4
24. Cicek C, Velayati AA, Farnia P. Cavitary tuberculosis: the gateway of disease transmission. Int J Mycobacteriol. 2024 [acceso 31/07/2025];13(2):156-64. Disponible en: https://www.ijmyco.org/article.asp?issn=2212-5531
25. Park JS, Lee JH, Kim JH, Kang HK, Lee SM, Yim JJ, et al. Outcomes of extended duration therapy for drug-susceptible cavitary pulmonary tuberculosis. Ann Transl Med. 2023 [acceso 31/07/2025];11(8):295. Disponible en: https://atm.amegroups.org/article/view/112458
26. Kashyap RS, Kainthla RP, Mudaliar AV, Purohit HJ. Endobronchial tuberculosis. Indian J Med Res. 2024 [acceso 31/07/2025];159(3):298-306. Disponible en: https://journals.lww.com/ijmr/fulltext/2024/03000/endobronchial_tuberculosis.6.aspx
27. Ahmed A, Meintjes G, Variava E, Naidu K, Dunbar R, Mthiyane T, et al. Treatment outcomes among HIV-infected adults with tuberculosis in South Africa. PLoS One. 2023 [acceso 31/07/2025];18(4):e0284532. Disponible en: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0284532
28. Yen YF, Chuang PH, Yen MY, Lin SY, Chuang P. Association of tobacco use with tuberculosis mortality: a population-based cohort study. Chest. 2022 [acceso 31/07/2025];162(4):876-85. Disponible en: https://journal.chestnet.org/article/S0012-3692(22)01059-4/fulltext
29. Millington KA, Innes JA, Hackforth S, Hinks TS, Deeks JJ, Dosanjh DP, et al. Dynamic relationship between IFN-gamma and IL-2 profile of mycobacterium tuberculosis-specific T cells and antigen load. J Immunol. 2021 [acceso 31/07/2025];207(8):2092-105. Disponible en: https://www.jimmunol.org/content/207/8/2092
30. Shah V, Kapoor A, Singh N, Sharma R. Nutritional supplementation in tuberculosis treatment: a mixed methods study of clinical outcomes and patient perceptions. Cureus. [acceso 31/07/2025]. Disponible en: https://www.cureus.com/articles/298551-nutritional-supplementation-in-tuberculosis-treatment
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Martín del Río Sánchez, Omarys Loyola Cabrera
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The Cuban Journal of Medicine protects the author's patrimonial rights. However, it is licensed under a Creative Commons Licensehttps://creativecommons.org/licenses/by-nc/4.0/deed.es_ES which permits unrestricted non-commercial use, distribution and reproduction in any medium, provided that the primary source of publication is duly cited. The author always retains his moral rights.
You are free to:
- Share - copy and redistribute the material in any medium or format.
- Adapt - remix, transform and build upon the material
- The license cannot revoke these freedoms as long as you follow the terms of the license.
Under the following terms:
- Attribution - You must give proper credit, provide a link to the license, and indicate if changes have been made. You may do so in any reasonable manner, but not in such a way as to suggest that you or your use is supported by the licensor.
- Non-Commercial Purpose- You may not make use of the material for commercial purposes.
- No Additional Restrictions - You may not apply legal terms or technological measures that legally restrict others from making any use permitted by the license.
