PREDICTION OF DRUG-RESISTANT TUBERCULOSIS USING MACHINE LEARNING

Abstract

Drug-resistant tuberculosis (DR-TB) is one of the most serious global public health challenges, leading to increased mortality, prolonged treatment duration, and higher healthcare costs. Conventional methods for diagnosing drug resistance often require considerable time, delaying the initiation of effective therapy. Recent advances in machine learning (ML) have created new opportunities for predicting drug-resistant tuberculosis through the analysis of clinical, demographic, radiological, and genomic data. Machine learning algorithms can identify complex patterns associated with the development of drug resistance and assist clinicians in making faster and more informed clinical decisions. This paper reviews the application of machine learning methods for predicting drug-resistant tuberculosis, including commonly used algorithms, data sources, performance metrics, and the major challenges associated with implementing these technologies in clinical practice.