Tuberculosis

As an official AI partner of the Central TB Division (CTD), we are developing multiple interventions across the TB care cascade and helping India’s National TB Elimination Programme (NTEP) become AI-ready.

Tuberculosis (TB) is a curable and preventable airborne disease that usually affects the lungs. One infected patient can spread the disease to 10-15 people within a year. In 2019, 2.6 million new cases and 440,000 TB-related deaths were reported in India, which continues to have the highest burden (26%) of all TB cases in the world.

Through its End TB Strategy, the WHO aims to end the global TB epidemic, with targets to reduce TB-related deaths by 95% and to cut new cases by 90% by 2035. With its ambitious National Strategic Plan (NSP) 2017-2025, the Government of India through NTEP plans to achieve a reduction in TB deaths by 90% and to reduce TB incidence by 80% by 2025, five years ahead of global timelines set for the country.

Identifying challenges at various stages in the TB care cascade. Source Global TB Report 2020; India TB Report 2020

Wadhwani AI is a close ally of the CTD, Ministry of Health & Welfare (MoHFW). We have also partnered with USAID to launch the TRACE-TB (Transformative Research and Artificial Intelligence Capacity for Elimination of TB and Responding to Infectious Diseases) programme, to support the NTEP.

Within the TB care cascade, we have identified specific areas for developing differentiated interventions. These include:

Interpretation of Line Probe Assay (LPA) strips
LPA is used to diagnose Drug Resistant TB cases (DR-TB). According to NTEP guidelines, all microbiologically confirmed pulmonary TB patients (an estimated 1 million) should be tested for drug sensitivity using LPA. At present, 400,000 tests are performed per year across 64 Culture and Drug Sensitivity Test (CDST) Labs. Errors in interpretation, in manual entry of results, and a prolonged turnaround time are causes for delays in initiation of TB treatment.

Risk for Loss to Follow Up (LFU)
Treatment Success for TB patients is dependent on their adherence to the treatment regimen. An extreme form of non-adherence is Lost to follow up (LFU), defined as a TB patient whose treatment was interrupted for one or more consecutive month(s). Despite increased efforts, total diagnosed TB patients who were LFU along the TB care cascade in 2019 was over 4% of the total incidents. Early prediction is critical since these patients may be silent TB transmitters showing no symptoms and are at higher risk of development and amplification of DR-TB.

TB Ultrasound
Chest X-ray is the leading screening tool for pulmonary TB. However, anywhere between 30-60% of patients do not get X-rays in spite of being given free coupons. There is a need for a portable, point-of-care screening system with automated readout.