The prevalence of tuberculosis (TB) in Kibera slum hospitals in Madagascar is high, necessitating innovative diagnostic methods. A mixed-methods approach including clinical data analysis and qualitative interviews with healthcare workers was employed to assess the impact of digital tools on TB detection rates and patient outcomes. During the study, a significant increase in diagnostic accuracy was observed, with a 15% rise in positive TB test results compared to traditional methods (90% confidence interval: +7.2% - +23.8%). The digital health solutions demonstrated promising efficacy in improving TB diagnosis rates and patient management. Further research is recommended to validate these findings and integrate the technologies into routine healthcare practices. Treatment effect was estimated with $\text{logit}(p_i)=\beta_0+\beta^\top X_i$, and uncertainty reported using confidence-interval based inference.