Software proposal for predicting therapeutic failure in pulmonary tuberculosis
Keywords:
Algoritmos; Predicción; Programas Informáticos; Técnica Delphi; Tuberculosis; Valor Predictivo de las PruebasAbstract
Introduction: treatment failure in pulmonary tuberculosis represents a critical adverse outcome that compromises patient health and promotes sustained transmission and the development of resistance. The manual application of predictive models is not feasible in daily clinical practice, thus requiring automated tools.
Objective: to evaluate the perceptions of a panel of experts regarding the need for, usefulness of, and feasibility of implementing predictive software to assess the risk of treatment failure in pulmonary tuberculosis.
Methods: An observational, descriptive, and cross-sectional study was conducted in March 2026 in Ciego de Ávila, Cuba. A validated self-administered survey was administered to 20 specialists, and the Delphi method was used to reach a consensus on risk factors and software functionalities.
Results: 100 % of the experts agreed or strongly agreed with the need for and usefulness of the software. The main barriers identified were: complexity of the calculation (90 %), lack of time during consultations (85 %), and high risk of errors (80 %). Fifteen risk factors were prioritized, and a proposal with six functional modules was designed, achieving a consensus of relevance exceeding 85 %.
Conclusions: the experts unanimously recognize the need for predictive software for pulmonary tuberculosis. The structured proposal is viable and relevant, although prospective clinical validation studies are required before its widespread implementation in the Cuban National Health System.
Downloads
References
Organización Mundial de la Salud (OMS). Tuberculosis. Washington DC: OMS [Internet]. 2022 [citado 20/01/2026]. Disponible en: https://www.who.int/es/news-room/fact-sheets/detail/tuberculosis
Organización Panamericana de la Salud (OPS). La Tuberculosis en las Américas. Informe Regional 2021. Washington DC: OPS/OMS [Internet]. 2022 [citado 20/01/2026]. Disponible en: https://iris.paho.org/bitstream/handle/10665.2/57084/9789275326497_spa.pdf?sequence=11&isAllowed=y
Secretaría de Salud 129. México avanza en la reducción de incidencia y mortalidad por tuberculosis. México: Gobierno de México [Internet]. 2021 [citado 20/01/2026]. Disponible en: https://www.gob.mx/salud/prensa/129-mexico-avanza-en-la-reduccion-de-incidencia-y-mortalidad-por-tuberculosis
Zhao CY, Song C, Lu YB, Huang AC, Zeng CM, Liu RH, Li WW, Xie ZH, Zhu QD. A New Era in Tuberculosis Prevention and Treatment: Breakthroughs in Drug Development and Future Prospects. Infect Dis Ther. [Online]. 2025 [cited 20/01/2026];14(10):2205-2219. DOI: http://doi.org/10.1007/s40121-025-01221-3
Oña Cerna HY, Guanca Sarmiento NB, Miranda Velazquez E. Factores asociados al fracaso del tratamiento antifímico de pacientes con tuberculosis pulmonar. Rev Ciencia Latina [Internet]. 2025 [citado 20/01/2026]; 9 (1). DOI: https://doi.org/10.37811/cl_rcm.v9i1.16073
Centro para el Control Estatal de Medicamentos, Equipos y Dispositivos Médicos (CECMED). Resolución No. 45/2025. Regulación E 130-25 Requisitos para la Inscripción de Fabricantes y el Registro Sanitario del Software de Uso Médico. Ámbito Regulador [Internet]. 2025 [citado 20/01/2026]. Disponible en: https://www.cecmed.cu/reglamentacion/ambito-regulador/indice?page=34%2C1
Cowley LE, Farewell DM, Maguire S, Kemp AM. Methodological standards for the development and evaluation of clinical prediction rules: a review of the literature. Diagnostic and Prognostic Research [Online]. 2019 [cited 20/01/2026];3:16. DOI: https://doi.org/10.1186/s41512-019-0060-y
Lai J, Cheng C, Liang T, Tang L, Guo X, Liu X. Development and multi-cohort validation of a machine learning-based simplified frailty assessment tool for clinical risk prediction. J Transl Med. [Online]. 2025 [cited 20/01/2026];23:921. Available from: https://link.springer.com/article/10.1186/s12967-025-06728-4
Coppola C, Andrew JJ, Ruggieri M, La Spina M, La Bianca MR, Leonardi S, et al. Machine learning prediction of oxygen therapy in pediatric Mycoplasma pneumoniae pneumonias. Front Digit Health. [Online]. 2026 [cited 20/01/2026]; 8:1755878. Available from: https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2026.1755878/full
Alzghaibi H. Healthcare practitioners' perceptions of mHealth application barriers: challenges to adoption and strategies for enhancing digital health integration. Healthcare. [Online]. 2025 [cited 20/01/2026];13(5):494. Available from: https://www.mdpi.com/resolver?pii=healthcare13050494
Olawade DB, Da'Costa A, Origbo JE, Osonuga A, Egbon E, Teke J, et al. Smart emergency care: a narrative review of predictive machine learning models. Ann Transl Med. [Online]. 2025 [cited 20/01/2026];13(5):60. Available from: https://atm.amegroups.org/article/view/144876/html
Armijos-Hernández A, Sánchez-Pozo NN. Modelos impulsados por inteligencia artificial para la predicción de la respuesta al tratamiento antituberculoso: estudio de cohorte retrospectivo en el subtrópico ecuatoriano. BioNatura Journal. [Internet]. 2026 [cited 20/01/2026];3(1):2. Disponible en: https://bionaturajournal.com/2026.03.01.2.html
Zhang F, Zhang F, Li L, Pang Y. Clinical utilization of artificial intelligence in predicting therapeutic efficacy in pulmonary tuberculosis. J Infect Public Health. [Online]. 2024 [cited 20/01/2026];17(4):633-40. Available from: https://doi.org/10.1016/j.jiph.2024.02.012
Subbaraman R, de Mondesert L, Musiimenta A, Pai M, Mayer KH, Thomas BE, et al. Digital adherence technologies for the management of tuberculosis therapy: mapping the landscape and research priorities. BMJ Glob Health. [Online]. 2018 [cited 20/01/2026];3(5):e001018. Available from: https://pmc.ncbi.nlm.nih.gov/articles/PMC6195152/pdf/bmjgh-2018-001018.pdf
Organismo Andino de Salud – Convenio Hipólito Unanue (ORAS-CONHU). Manual de algoritmos para el diagnóstico de tuberculosis. [Internet] Lima: ORAS-CONHU; 2018. [citado 20/01/2026]. Disponible en: https://www.paho.org/sites/default/files/2019-cde-manual-algoritmos-dx-tb-comisca.pdf
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Martín del Río Sánchez, Luis Eugenio Valdés García , Enrique Beldarrain Chaple , Omarys Loyola-Cabrera
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
