Machine learning investigation of tuberculosis with medicine immunity impact

Tuberculosis (T.B.) remains a prominent global cause of health challenges and death, exacerbated by drug-resistant strains such as multidrug-resistant tuberculosis MDR-TB and extensively drug-resistant tuberculosis XDR-TB. For an effective disease management strategy, it is crucial to understand the dynamics of T.B. infection and the impacts of treatment. In the present article, we employ AI-based machine learning techniques to investigate the immunity impact of medications. SEIPR epidemiological model is incorporated with MDR-TB for compartments susceptible to disease, exposed to risk, infected ones, preventive or resistant to initial treatment, and recovered or healed population. These masses' natural trends, effects, and interactions are formulated and described in the present study. Computations and stability analysis are conducted upon endemic and disease-free equilibria in the present model for their global scenario. Both numerical and AI-based nonlinear autoregressive exogenous NARX analyses are presented with incorporating immediate treatment and delay in treatment. This study shows that the active patients and MDR-TB, both strains, exist because of the absence of permanent immunity to T.B. Furthermore, patients who have recovered from tuberculosis may become susceptible again by losing their immunity and contributing to transmission again. This article aims to identify patterns and predictors of treatment success. The findings from this research can contribute to developing more effective tuberculosis interventions.