Innovations in Tuberculosis Disease Screening

Tuberculosis (TB), an infectious disease caused by mycobacterium tuberculosis (M. tb), is the number one cause of death from an infectious agent worldwide, despite the large scale vaccination in place since a century. This emphasizes the importance of having efficient screening for early detection of TB to facilitate treatment of infected individuals. Clinical screening methods in practice include invasive assays i.e. tuberculin skin tests (TST) and interferon-gamma release assays (IGRA) and non-invasive chest X ray (CXRs) imaging. The limitations of these screening methods include the possibility of false negatives and false positives. Artificial intelligence (AI) and machine learning (ML) have been utilized to improve the current screening methods and introduce new approaches. The innovations in this field include a mobile health application for TB screening and various imaging technologies such as computer-aided detection (CAD) software for interpreting digital CXRs. ML algorithms can be used for interpreting CXRs images, gene expression analysis for biomarkers. Other AI-driven tools can be used for risk prediction and stratification. Addressing the challenges of cost-effectiveness, scalability, access, and adoption of these new technologies is crucial. The importance of quality assurance, standardization, and ethical considerations in the use of AI in TB screening is emphasized to ensure equitable and patient-centric healthcare practices. Overall, this chapter provides a thorough review of the current TB screening methods, the limitations they pose, and the promising role that AI and ML in overcoming these challenges for more effective and accessible TB diagnosis and management.