EUVIMEDEUVIMED entdecken
QuerschnittstudieOpen Access · CC BY 4.0

AI-Based Risk Stratification for Latent Tuberculosis Among Urban Slum Dwellers: A Cross-Sectional Study

Ali Dost, Afeera Bint-e-Tanveer, Ajmal Khan, Kamran Ali, Sajjad Ahmad, Zubia Shahid

Link Medical Journal · 31.12.2025 · 1-12

DOI: 10.61919/m227h628 ↗

Kurz gefasst

Querschnittstudie in der Zeitschrift Link Medical Journal, online erschienen am 31.12.2025. Verfasst von Ali Dost und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Dost, A., Bint-e-Tanveer, A., Khan, A., Ali, K., Ahmad, S., & Shahid, Z. (2025). AI-Based Risk Stratification for Latent Tuberculosis Among Urban Slum Dwellers: A Cross-Sectional Study. Link Medical Journal, 1-12. https://doi.org/10.61919/m227h628

Vancouver

Dost A, Bint-e-Tanveer A, Khan A, Ali K, Ahmad S, Shahid Z. AI-Based Risk Stratification for Latent Tuberculosis Among Urban Slum Dwellers: A Cross-Sectional Study. Link Medical Journal. 2025:1-12. doi:10.61919/m227h628

BibTeX
@article{Dost2025,
  author = {Dost, Ali and Bint-e-Tanveer, Afeera and Khan, Ajmal and Ali, Kamran and Ahmad, Sajjad and Shahid, Zubia},
  title = {AI-Based Risk Stratification for Latent Tuberculosis Among Urban Slum Dwellers: A Cross-Sectional Study},
  journal = {Link Medical Journal},
  year = {2025},
  pages = {1--12},
  doi = {10.61919/m227h628}
}
Kostenlos starten →