[New methods of tuberculosis diagnostics].

Tuberculosis remains the leading cause of death by a single infectious agent worldwide, with over 10 million cases annually. Despite global efforts, delayed or missed diagnoses continue to fuel transmission and mortality, particularly in resource-limited settings. This review outlines both the current diagnostic standards - microscopy, culture, and nucleic acid amplification tests - and highlights promising innovations aimed at improving diagnosis of tuberculosis disease. Novel approaches include stool polymerase chain reaction (PCR), CRISPR (clustered regularly interspaced short palindromic repeats)-based detection of circulating cell-free DNA (cfDNA), transcriptomic signatures, molecular bacterial load assay (MBLA), lipoarabinomannan (LAM) detection in urine or sputum, and non-invasive sampling techniques using exhaled breath condensate, face masks or oral swabs. Furthermore, advancements in imaging technologies and AI (artificial intelligence)-based tools may enhance diagnostic accuracy. Together, these developments have the potential to accelerate and simplify tuberculosis diagnostics in the future.