<![CDATA[Tuberculosis (TB) remains a major health challenge, and predicting treatment outcomes continues to be difficult in real-world settings. Recent advances in Artificial Intelligence (AI), particularly transformer-based models, have shown promise in modelling longitudinal, multimodal, and heterogeneous TB data. However, their clinical adoption is constrained by limited interpretability, fairness concerns, and deployment challenges. This study presents a systematic literature review of explainable transformer and machine learning models used for TB prognosis. Following PRISMA guidelines, searches across ACM, IEEE Xplore, PubMed, and ScienceDirect identified 17 peer-reviewed studies published between 2020 and 2025 that met the inclusion criteria. The review synthesises evidence on predictive performance, explainability techniques, and deployment considerations. Findings indicate that transformer-based and deep learning models generally outperform conventional machine learning approaches on longitudinal and multimodal data. In contrast, traditional models remain competitive for tabular clinical datasets. Explainability approaches are dominated by feature importance methods and SHAP, with limited use of intrinsic transformer interpretability mechanisms. Persistent challenges include data scarcity, limited generalisability, computational overhead, insufficient evaluation of fairness, and weak alignment with real-world TB care workflows. Building on these findings, the study proposes the Explainable Transformer Adoption Model for TB Prognosis (ETAMTB) as a conceptual clinical adoption framework integrating multimodal transformers, explainability layers, clinician-facing interfaces, and deployment enablers. Overall, the review concludes that effective AI adoption in TB care requires balancing predictive performance, interpretability, and equity, and that explainable transformers should currently be viewed as promising but largely experimental tools rather than deployment-ready solutions.]]>
