Diagnostic accuracy of an AI based screening system for detection of pulmonary tuberculosis using cough sounds and symptoms

This study aims to evaluate the diagnostic accuracy of an artificial intelligence (AI)-based screening system designed for the detection of pulmonary tuberculosis (TB) using cough sounds and related symptoms. TB remains a significant global health challenge, with 10.6 million new cases and 1.3 million deaths annually. Traditional diagnostic methods like microbiological tests and chest X-rays, though effective, are resource-intensive and often inaccessible in low-resource settings. This has led to significant gaps in the detection and treatment of TB, particularly in rural areas. The AI model developed in this study uses cough sounds—a prominent symptom of TB—and additional symptoms such as fever, weight loss, and night sweats to provide a cost-effective and non-invasive diagnostic tool. The AI-powered mobile application offers rapid, point-of-care screening and can be utilized by frontline healthcare workers, enabling early diagnosis even in resource-limited environments. This technology addresses the need for accessible TB screening, aiming to bridge the gap between diagnosed and undiagnosed cases.