Implementing a chest X-ray artificial intelligence tool to enhance tuberculosis screening in India: Lessons learned.

Artificial Intelligence (AI) based chest X-ray (CXR) screening for tuberculosis (TB) is becoming increasingly popular. Still, deploying such AI tools can be challenging due to multiple real-life barriers like software installation, workflow integration, network connectivity constraints, limited human resources available to interpret findings, etc. To understand these challenges, PATH implemented a TB REACH active case-finding program in a resource-limited setting of Nagpur in India, where an AI software device (qXR) intended for TB screening using CXR images was used. Eight private CXR laboratories that fulfilled prerequisites for AI software installation were engaged for this program. Key lessons about operational feasibility and accessibility, along with the strategies adopted to overcome these challenges, were learned during this program. This program also helped to screen 10,481 presumptive TB individuals using informal providers based on clinical history. Among them, 2,303 individuals were flagged as presumptive for TB by a radiologist or by AI based on their CXR interpretation. Approximately 15.8% increase in overall TB yield could be attributed to the presence of AI alone because these additional cases were not deemed presumptive for TB by radiologists, but AI was able to identify them. Successful implementation of AI tools like qXR in resource-limited settings in India will require solving real-life implementation challenges for seamless deployment and workflow integration.

Quality of active case-finding for tuberculosis in India: a national level secondary data analysis.

BACKGROUND: India has been implementing active case-finding (ACF) for TB among marginalised and vulnerable (high-risk) populations since 2017. The effectiveness of ACF cycle(s) is dependent on the use of appropriate screening and diagnostic tools and meeting quality indicators. OBJECTIVES: To determine the number of ACF cycles implemented in 2021 at national, state (n = 36) and district (n = 768) level and quality indicators for the first ACF cycle. METHODS: In this descriptive study, aggregate TB program data for each ACF activity that was extracted was further aggregated against each ACF cycle at the district level in 2021. One ACF cycle was the period identified to cover all the high-risk populations in the district. Three TB ACF quality indicators were calculated: percentage population screened (≥10%), percentage tested among screened (≥4.8%) and percentage diagnosed among tested (≥5%). We also calculated the number needed to screen (NNS) for diagnosing one person with TB (≤1538). RESULTS: Of 768 TB districts, ACF data for 111 were not available. Of the remaining 657 districts, 642 (98%) implemented one, and 15 implemented two to three ACF cycles. None of the districts or states met all three TB ACF quality indicators' cut-offs. At the national level, for the first ACF cycle, 9.3% of the population were screened, 1% of the screened were tested and 3.7% of the tested were diagnosed. The NNS was 2824: acceptable (≤1538) in institutional facilities and poor for population-based groups. Data were not consistently available to calculate the percentage of i) high-risk population covered, ii) presumptive TB among screened and iii) tested among presumptive. CONCLUSION: In 2021, India implemented one ACF cycle with sub-optimal ACF quality indicators. Reducing the losses between screening and testing, improving data quality and sensitising stakeholders regarding the importance of meeting all ACF quality indicators are recommended.

Estimation of tuberculosis incidence at subnational level using three methods to monitor progress towards ending TB in India, 2015-2020.

OBJECTIVES: We verified subnational (state/union territory (UT)/district) claims of achievements in reducing tuberculosis (TB) incidence in 2020 compared with 2015, in India. DESIGN: A community-based survey, analysis of programme data and anti-TB drug sales and utilisation data. SETTING: National TB Elimination Program and private TB treatment settings in 73 districts that had filed a claim to the Central TB Division of India for progress towards TB-free status. PARTICIPANTS: Each district was divided into survey units (SU) and one village/ward was randomly selected from each SU. All household members in the selected village were interviewed. Sputum from participants with a history of anti-TB therapy (ATT), those currently experiencing chest symptoms or on ATT were tested using Xpert/Rif/TrueNat. The survey continued until 30 Mycobacterium tuberculosis cases were identified in a district. OUTCOME MEASURES: We calculated a direct estimate of TB incidence based on incident cases identified in the survey. We calculated an under-reporting factor by matching these cases within the TB notification system. The TB notification adjusted for this factor was the estimate by the indirect method. We also calculated TB incidence from drug sale data in the private sector and drug utilisation data in the public sector. We compared the three estimates of TB incidence in 2020 with TB incidence in 2015. RESULTS: The estimated direct incidence ranged from 19 (Purba Medinipur, West Bengal) to 1457 (Jaintia Hills, Meghalaya) per 100 000 population. Indirect estimates of incidence ranged between 19 (Diu, Dadra and Nagar Haveli) and 788 (Dumka, Jharkhand) per 100 000 population. The incidence using drug sale data ranged from 19 per 100 000 population in Diu, Dadra and Nagar Haveli to 651 per 100 000 population in Centenary, Maharashtra. CONCLUSION: TB incidence in 1 state, 2 UTs and 35 districts had declined by at least 20% since 2015. Two districts in India were declared TB free in 2020.

STEPS - a patient centric and low-cost solution to ensure standards of TB care to patients reaching private sector in India.

BACKGROUND: More than half of the TB patients in India seek care from the private sector. Two decades of attempts by the National TB Program to improve collaboration between the public and private sectors have not worked except in a few innovative pilots. The System for TB Elimination in Private Sector (STEPS) evolved in 2019 as a solution to ensure standards of TB care to every patient reaching the private sector. We formally evaluated the STEPS to judge the success of the model in achieving its outcomes and to inform decisions about scaling up of the model to other parts of the country. METHODS: An evaluation team was constituted involving all relevant stakeholders. A logic framework for the STEPS model was developed. The evaluation focused on (i) processes - whether the activities are taking place as intended and (ii) proximal outcomes - improvements in quality of care and strengthening of TB surveillance system. We (i) visited 30 randomly selected STEPS centres for assessing infrastructure and process using a checklist, (ii) validated the patient data with management information system of National TB Elimination Program (NTEP) by telephonic interview of 57 TB patients (iii) analysed the quality of patient care indicators over 3 years from the management information system (iv) conducted in-depth interviews (IDI) with 33 beneficiaries and stakeholders to understand their satisfaction and perceived benefits of STEPS and (v) performed cost analysis for the intervention from the perspective of NTEP, private hospital and patients. RESULTS: Evaluation revealed that STEPS is an acceptable model to all stakeholders. IDIs revealed that all patients were satisfied about the services received. Data in management information system of NTEP were consistent with the hospital records and with the information provided by the patient. Quality of TB care indicators for patients diagnosed in private hospitals showed improvements over years as proportion of TB patients notified from private sector with a microbiological confirmation of diagnosis improved from 25% in 2018 to 38% in 2020 and the documented treatment success rate increased from 33% (2018 cohort) to 88% (2019 cohort). Total additional programmatic cost (deducting cost for patient entitlements) per additional patient with successful treatment outcome was estimated to be 67 USD. Total additional expense/business loss for implementing STEPS for the hospital diagnosing 100 TB patients in a year was estimated to be 573 USD while additional minimum returns for the hospital was estimated to be 1145 USD. CONCLUSION: Evaluation confirmed that STEPS is a low cost and patient-centric strategy. STEPS successfully addressed the gaps in the quality of care for patients seeking care in the private sector and ensured that services are aligned with the standards of TB care. STEPS could be scaled up to similar settings.