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.

Delivering hypertension care in private-sector clinics of urban slum areas of India: the Mumbai Hypertension Project.

In India, the private sector provides 70% of the total outpatient medical care. This study describes the Mumbai Hypertension Project, which aimed to deliver a standard hypertension management package in private sector clinics situated in urban slums. The project was conducted in two wards (one "lean" and one "intensive") with 82 private providers in each. All hypertensive patients received free drug vouchers, baseline serum creatinine, adherence support, self-management counseling and follow-up calls. In the intensive-ward, project supported hub agents facilitated uptake of services. A total of 13,184 hypertensive patients were registered from January 2019 to February 2020. Baseline blood pressure (BP) control rates were higher in the intensive-ward (30%) compared with the lean-ward (13%). During the 14-month project period, 6752 (51%) patients followed-up, with participants in the intensive-ward more likely to follow-up (aOR: 2.31; p < 0.001). By project end, the 3-6-month cohort control rate changed little from baseline-29% for intensive ward and 14% for lean ward. Among those who followed up, proportion with controlled BP increased 13 percentage points in the intensive ward and 16 percentage points in the lean ward; median time to BP control was 97 days in the intensive-ward and 153 days in lean-ward (p < 0.001). Despite multiple quality-improvement interventions in Mumbai private sector clinics, loss to follow-up remained high, and BP control rates only improved in patients who followed up; but did not improve overall. Only with new systems to organize and incentivize patient follow-up will the Indian private sector contribute to achieving national hypertension control goals.

Phone calls for improving blood pressure control among hypertensive patients attending private medical practitioners in India: Findings from Mumbai hypertension project.

Despite the availability of effective medication, blood pressure control rates are low, particularly in low- and middle-income countries. Adherence to medication and follow-up visits are important factors in blood pressure control. This study assessed the effectiveness of reminder telephone calls on follow-up visits and blood pressure control among hypertensive patients as part of the Mumbai Hypertension Project. This project was initiated by PATH with the support from Resolve to Save Lives from January 2019 to February 2020. The study included hypertensive patients attending 164 private practices in Mumbai, India; practitioners screened all adults visiting their clinic during the project period. Among 13 184 hypertensive patients registered, the mean age was 53 years (SD = 12.38) and 52% were female. Among the 11 544 patients that provided phone numbers and gave consent for follow-up calls, 9528 responded to phone calls at least once and 5250 patients followed up at least once. Of the 5250 patients, 82% visited the clinic for follow-up visit within one month after receiving the phone call. The blood pressure control rate among those who answered phone calls and who did not answer phone calls increased from 23.6% to 48.8% (P <.001) and 21.0% to 44.3% (P <.001), respectively. The blood pressure control rate at follow-up was significantly associated with phone calls (OR: 1.51, 95% CI: 1.34 - 1.71). The study demonstrates that telephone call intervention and follow-up visits can improve patient retention in care and, subsequently, blood pressure control among hypertensive patients attending urban private sector clinics in India.

Map, know dynamics and act; a better way to engage private health sector in TB management. A report from Mumbai, India.

BACKGROUND: India, world's leading Tuberculosis burden country envisions to End-TB by optimally engaging private-sector, in-spite of several unsuccessful attempts of optimal private sector engagement. Private Provider Interface Agency (PPIA), a new initiative for private-sector engagement, studied the private-sector networking and dynamics to understand the spread, typology of providers and facilities and their relations in TB case management, which was critical to design an intervention to engage private-sector. We report the observations of this exercise for a larger readership. METHOD: ology: It is a descriptive analysis of mapping data (quantitative) and perceived factors influencing their engagement in the PPIA network (qualitative). RESULTS: Of 7396 doctors, 2773 chemists and 747 laboratories mapped, 3776 (51%) doctors, 353 (13%) chemists and 255 (34%) laboratories were prioritized and engaged. While allopathic doctors highly varied between wards (mean ratio 48/100,000 population; range 13-131), non-allopathic doctors were more evenly distributed (mean ratio 58/100,000 population; range 36-83). The mean ratio between non-allopathic to allopathic doctors was 1.75. Return benefit, apprehension on continuity of funding and issues of working with the Government were top three concerns of private providers during engagement. Similarly, irrational business expectations, expectation of advance financing for surety and fear of getting branded as TB clinic were three top reasons for non-engagement. CONCLUSION: A systematic study of dynamics of existing networking, typology and spread of private providers and using this information in establishing an ecosystem of referral network for TB control activities is crucial in an effort towards optimal engagement of private health providers. Understanding the factors influencing the network dynamics helped PPIA in effective engagement of private health providers in the project.