Tuberculosis (TB) remains a significant global health challenge, with over 80% of reported cases and deaths originating from low and middle-income countries (LMICs) worldwide. Among these countries, India shoulders a substantial burden, accounting for a quarter of all TB cases and resulting in approximately 89,000 deaths in the year 2019 alone.

The private sector plays a crucial role in TB diagnosis in India, handling twice as many cases as the public sector. It comprises various healthcare providers, clinics, and practitioners who lack integration. Both Informal healthcare providers and AYUSH (Ayurveda, Yoga & Naturopathy, Unani, Siddha, or Homoeopathy) combined, referred to as AIPs, serve as the first point of contact in patient pathways for most TB cases in India.

Molecular diagnostic tests for TB, such as Xpert MTB/RIF, remain expensive, difficult to access, and challenging to maintain in low- and middle-income countries (LMICs). The clinical diagnosis based on chest X-rays (CXRs) remains the mainstay among private providers (including AIPs) in India. WHO recommends CXR for screening, triaging, and assisting in diagnosing TB. However, there is a shortage of adequately trained radiologists proficient in analysing CXRs and producing high-quality reports.

In the absence of qualified radiologists, the presence of automated AI systems for interpreting CXRs could prove to be highly advantageous. Employing AI-assisted interpretation of CXRs can improve the speed and accuracy of TB diagnosis and reduce the screening cost.

AIPs' willingness to incorporate AI-enhanced CXR systems into decision-making is vital to AI adoption. For our study, we conducted a cross-sectional survey of 406 AIPs across the states of Jharkhand (162 participants) and Gujarat (244 participants) to assess AIPs' beliefs in the diagnostic capabilities of AI and their willingness to adopt AI for TB diagnosis.

Methodology

The study used a cross sectional survey to collect the data through an extensive questionnaire.