AI-Based Risk Stratification for Latent Tuberculosis Among Urban Slum Dwellers: A Cross-Sectional Study
DOI:
https://doi.org/10.61919/m227h628Keywords:
Artificial intelligence; community health; latent tuberculosis; machine learning; risk stratification; tuberculin skin test; urban slumsAbstract
Background: Latent tuberculosis infection (LTBI) poses a critical public health challenge in urban informal settlements, where structural deprivation, household overcrowding, and limited healthcare access sustain high transmission risk. Traditional screening methods fail to reach the most vulnerable individuals, underscoring the need for targeted, data-driven approaches. Objective: This study aimed to evaluate the predictive performance of AI-assisted machine learning models for LTBI risk stratification among adults in urban informal settlements in Lahore, Pakistan. Methods: A cross-sectional analytical study enrolled 150 adult participants from densely populated slum communities. Data were collected via structured questionnaires, clinical assessments, and tuberculin skin testing (TST; ≥10 mm threshold). Three supervised machine learning algorithms, logistic regression, random forest, and gradient-boosted decision trees, were developed using a stratified 70:30 train-test split with 10-fold cross-validation. Model performance was assessed using accuracy, sensitivity, specificity, positive and negative predictive values, and area under the receiver operating characteristic curve (AUC) with 95% bootstrap confidence intervals. Variable importance was evaluated using normalised feature gain scores. Results: TST positivity was 42.0% (n=63). The gradient-boosted model achieved the highest performance (AUC 0.91, sensitivity 90.5%, specificity 88.5%), followed by random forest (AUC 0.88) and logistic regression (AUC 0.82). Prior TB contact history, household crowding, and poor ventilation were the strongest predictors. Overall classification accuracy was 89.3% (95% CI 83.3–93.7%). Conclusion: AI-assisted risk stratification using community-collectible sociodemographic and environmental variables can effectively identify individuals at elevated LTBI risk in urban slum settings, supporting targeted screening and preventive intervention strategies.
References
1. World Health Organization. Global Tuberculosis Report 2023. Geneva: WHO; 2023.
2. Pakistan National Tuberculosis Control Programme. National TB Programme Annual Report 2022–2023. Islamabad: Ministry of National Health Services; 2023.
3. Houben RM, Dodd PJ. The global burden of latent tuberculosis infection: a re-estimation using mathematical modelling. PLoS Med. 2016;13(10):e1002152.
4. Ayubi E, Doosti-Irani A, Sanjari Moghaddam A, Sani M, Yousefi-Tenhaei I, Chamavi S. The clinical relevance of risk factors for latent tuberculosis infection: a systematic review and meta-analysis. Int J Infect Dis. 2017;65:100–9.
5. Fatima R, Harris RJ, Eichner M, Hinderaker SG, Hall J, Reynolds M, et al. Diagnosing and treating 2 million cases of TB annually in Pakistan: challenges and the way forward. Infect Dis Poverty. 2016;5(1):49.
6. World Health Organization. WHO Consolidated Guidelines on Tuberculosis: Module 1: Prevention – Tuberculosis Preventive Treatment. Geneva: WHO; 2020.
7. Farooq S, Bhatt BA, Yaqoob A, Sajjad K, Ali J, Saleem M. Comparison of tuberculin skin test and interferon-gamma release assay in diagnosis of LTBI among healthcare workers in Pakistan. J Pak Med Assoc. 2021;71(4):1045–9.
8. Rajpurkar P, Chen E, Banerjee O, Topol EJ. AI in health and medicine. Nat Med. 2022;28(1):31–8.
9. Qin ZZ, Sander MS, Rai B, Bhatt RC, Bhatt S, Shrestha B, et al. Using artificial intelligence to read chest radiographs for tuberculosis detection: a multi-site evaluation of the diagnostic accuracy of three deep learning systems. Sci Rep. 2019;9(1):15000.
10. Guo Y, Hao Z, Zhao S, Gong J, Yang F. Artificial intelligence in health care: bibliometric analysis. J Med Internet Res. 2020;22(7):e18228.
11. Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019;366(6464):447–53.
12. Setia MS. Methodology series module 3: cross-sectional studies. Indian J Dermatol. 2016;61(3):261–4.
13. Shilo S, Rossman H, Segal E. Axes of a revolution: challenges and promises of big data in healthcare. Nat Med. 2020;26(1):29–38.
14. Lienhardt C. From exposure to disease: the role of environmental factors in susceptibility to and development of tuberculosis. Epidemiol Rev. 2001;23(2):288–301.
15. Menzies D, Pai M, Comstock G. Meta-analysis: new tests for the diagnosis of latent tuberculosis infection, areas of uncertainty and recommendations for research. Ann Intern Med. 2007;146(5):340–54.
16. Ministry of National Health Services Pakistan. National Guidelines for Diagnosis and Treatment of Tuberculosis. 5th ed. Islamabad: NTP Pakistan; 2019.
17. Chen T, Guestrin C. XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016 Aug 13–17; San Francisco, CA. New York: ACM; 2016. p. 785–94.
18. Hastie T, Tibshirani R, Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. 2nd ed. New York: Springer; 2009.
19. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: machine learning in Python. J Mach Learn Res. 2011;12:2825–30.
20. Dye C, Williams BG. The population dynamics and control of tuberculosis. Science. 2010;328(5980):856–61.
21. Pareek M, Greenaway C, Noori T, Munoz J, Zenner D. The impact of migration on tuberculosis epidemiology and control in high-income countries. BMC Med. 2016;14(1):48.
22. Kik SV, Denkinger CM, Chedraui Granada M, Pai M, Horsburgh CR. Prospects of a novel diagnostic test for the management of LTBI. Curr Opin Pulm Med. 2014;20(3):269–75.
23. Wynants L, Van Calster B, Collins GS, Riley RD, Heinze G, Schuit E, et al. Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal. BMJ. 2020;369:m1328.
24. Morrison J, Pai M, Hopewell PC. Tuberculosis and latent tuberculosis infection in close contacts of people with pulmonary tuberculosis in low-income and middle-income countries: a systematic review and meta-analysis. Lancet Infect Dis. 2008;8(6):359–68.
25. Nardell EA. Transmission and institutional infection control of tuberculosis. Cold Spring Harb Perspect Med. 2016;6(2):a018192.
26. Lin HH, Murray M, Cohen T, Colijn C, Ezzati M. Effects of smoking and solid-fuel use on COPD, lung cancer, and tuberculosis in China: a time-based, multiple risk factor, modelling study. Lancet. 2008;372(9648):1473–83.
27. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44–56.
28. Brennan P, Silman A. Statistical methods for assessing observer variability in clinical measures. BMJ. 1992;304(6840):1491–4.
29. Andrews JR, Noubary F, Walensky RP, Cerda R, Losina E, Horsburgh CR. Risk of progression to active tuberculosis following reinfection with Mycobacterium tuberculosis. Clin Infect Dis. 2012;54(6):784–91.
30. Sterne JA, White IR, Carlin JB, Spratt M, Royston P, Kenward MG, et al. Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls. BMJ. 2009;338:b2393.
31. Char DS, Shah NH, Magnus D. Implementing machine learning in health care, addressing ethical challenges. N Engl J Med. 2018;378(11):981–3.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ali Dost, Afeera Bint-e-Tanveer, Ajmal Khan, Kamran Ali, Sajjad Ahmad, Zubia Shahid (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
© The Authors. This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
.png)
