Explanatory Modeling of Tuberculosis Treatment Outcomes: The Role of Community Engagement and Clinical Governance

Background: Treatment adherence and outcomes for drug-resistant tuberculosis (DR-TB) continue to be subpar in rural South Africa, where structural health system limitations, comorbid conditions, and diverse resistance patterns make clinical management more challenging. This study aimed to assess how demographic, clinical, and programmatic factors, including a Community Engagement–Clinical Governance (CE–CG) implementation period, affect DR-TB treatment outcomes using explanatory predictive modeling. Methods: A retrospective cohort study was conducted using routine program data from 694 DR-TB patients. A complete-case analysis was performed for multivariable modeling (n = 282). Logistic regression and decision tree models were used to examine the relationships between treatment success and selected predictors, including age, sex, treatment regimen, resistance phenotype, comorbidities, and the CE–CG implementation period. Model discrimination and performance were evaluated using receiver operating characteristic (ROC) curves, pseudo-R2 statistics, likelihood ratio tests, and multicollinearity diagnostics. Results: The cohort had a mean age of 40.7 years, and 58.8% of patients were male. Overall treatment success was 59.9%. Severe resistance phenotypes were rare (1.7%) but clinically significant. Comparative analysis showed no notable demographic or outcome differences between included and excluded patients, indicating minimal selection bias. In adjusted models, treatment initiation during the CE–CG implementation period was significantly linked to lower odds of treatment success (adjusted odds ratio [aOR] = 0.443; 95% CI: 0.240–0.818; p = 0.009). Severe resistance phenotypes were strongly negatively associated with treatment success (aOR = 0.303; p = 0.056). Logistic regression models had limited discriminatory ability (AUC: 0.523–0.548), while the decision tree model showed modest improvement (AUC: 0.626). Overall, the model’s explanatory power was limited (pseudo-R2 = 0.029), although no evidence of multicollinearity was found. Conclusions: Programmatic implementation periods and resistance severity were important factors associated with treatment outcomes in this rural DR-TB cohort. Although model discrimination was modest and explanatory power was limited, the findings provide useful insights into structural and programmatic vulnerabilities that affect treatment success in real-world settings. Strengthening clinical governance, improving routine program documentation, and incorporating more granular adherence, social, and governance indicators into routine data systems may improve both program evaluation and future predictive modeling.