Current Trends in Tuberculosis Diagnosis: Advancements and Challenges

Abstract

Tuberculosis [TB] is still a worldwide health issue, and early and accurate diagnosis of TB is essential for the management of the disease. Although conventional diagnostic methods, including sputum smear microscopy and culture methods, provide some diagnostic information, these methods have challenges in terms of sensitivity, specificity, and turnaround time. Recent TB diagnostics include molecular-based diagnostics, such as GeneXpert MTB/RIF and line-probe assays, which provide rapid and highly sensitive TB detection, including in drug-resistant cases. Next-generation sequencing and whole genome sequencing [and other “omics” technology] show potential for isolating strains of Mycobacterium tuberculosis and identifying resistance typing and epidemiological surveillance. However, there remain challenges, including high cost, availability of resources in low-resource settings, and reliance on a skilled workforce. The role of artificial intelligence [AI] is being studied, particularly with respect to TB detection in imaging, to test the accuracy of AI programs and their ability to predict TB on chest radiographic interpretation. Future directions in TB diagnostics include further development of point-of-care diagnostics, reliance on AI- and machine learning-driven algorithms in imaging and data interpretation, and advancements in access to genomic sequencing and molecular diagnostics. Increased investment in research [and studies on the cost] and supportive policy frameworks for regulatory approval pathways and reducing costs will be important to ensure further implementation and uptake of diagnostics to achieve the goal of ending TB by 2035.