Impact of Artificial Intelligence Assessment of Diabetic Retinopathy on Referral Service Uptake in a Low-Resource Setting: The RAIDERS Randomized Trial.

Purpose: This trial was designed to determine if artificial intelligence (AI)-supported diabetic retinopathy (DR) screening improved referral uptake in Rwanda. Design: The Rwanda Artificial Intelligence for Diabetic Retinopathy Screening (RAIDERS) study was an investigator-masked, parallel-group randomized controlled trial. Participants: Patients ≥ 18 years of age with known diabetes who required referral for DR based on AI interpretation. Methods: The RAIDERS study screened for DR using retinal imaging with AI interpretation implemented at 4 facilities from March 2021 through July 2021. Eligible participants were assigned randomly (1:1) to immediate feedback of AI grading (intervention) or communication of referral advice after human grading was completed 3 to 5 days after the initial screening (control). Main Outcome Measures: Difference between study groups in the rate of presentation for referral services within 30 days of being informed of the need for a referral visit. Results: Of the 823 clinic patients who met inclusion criteria, 275 participants (33.4%) showed positive findings for referable DR based on AI screening and were randomized for inclusion in the trial. Study participants (mean age, 50.7 years; 58.2% women) were randomized to the intervention (n = 136 [49.5%]) or control (n = 139 [50.5%]) groups. No significant intergroup differences were found at baseline, and main outcome data were available for analyses for 100% of participants. Referral adherence was statistically significantly higher in the intervention group (70/136 [51.5%]) versus the control group (55/139 [39.6%]; P = 0.048), a 30.1% increase. Older age (odds ratio [OR], 1.04; 95% confidence interval [CI], 1.02-1.05; P < 0.0001), male sex (OR, 2.07; 95% CI, 1.22-3.51; P = 0.007), rural residence (OR, 1.79; 95% CI, 1.07-3.01; P = 0.027), and intervention group (OR, 1.74; 95% CI, 1.05-2.88; P = 0.031) were statistically significantly associated with acceptance of referral in multivariate analyses. Conclusions: Immediate feedback on referral status based on AI-supported screening was associated with statistically significantly higher referral adherence compared with delayed communications of results from human graders. These results provide evidence for an important benefit of AI screening in promoting adherence to prescribed treatment for diabetic eye care in sub-Saharan Africa.

Strengths and Weaknesses of Strategic Health Purchasing for Universal Health Coverage in Rwanda.

In the context of scarce resources and increasing health care costs, strategic purchasing is viewed as a key mechanism to spur countries' progress toward universal health coverage (UHC), by using limited resources more effectively. We applied the Strategic Health Purchasing Progress Tracking Framework to examine the health purchasing arrangements in three health financing schemes in Rwanda-the Community Based Health Insurance (CBHI) scheme, the Rwanda Social Security Board (RSSB) medical scheme, and performance-based financing (PBF). Data were collected from secondary and primary sources between September 2020 and March 2021.The objective of the study was to identify areas of progress in strategic purchasing that can be built on, and to identify areas of overlap, duplication, or conflict that limit progress in strategic purchasing to advance UHC goals. This study found that Rwanda has made progress in many areas of strategic purchasing and has a strong foundation for building further. However, some overlaps and duplication of functions weaken the power of purchasers to improve resource allocation, incentives for providers, and accountability. In addition, some of the policies within the purchasing functions could be made more strategic. In particular, open-ended fee-for-service payment in the CBHI scheme not only threatens the scheme's financial sustainability but also imposes a high administrative burden. Better alignment and integration of contracting, incentives, and information system design to provide timely and relevant information for purchasing decisions would contribute to more strategic health purchasing and ensure that Rwanda's health sector achievements are sustained and expanded.

Creating a pathway for public hospital accreditation in Rwanda: progress, challenges and lessons learned.

QUALITY PROBLEM: Weaknesses in the quality of care delivered at hospitals translates into patient safety challenges and causes unnecessary harm. Low-and-middle-income countries disproportionately shoulder the burden of poor quality of hospital care. INITIAL ASSESSMENT: In the early 2000s, Rwanda implemented a performance-based financing (PBF) system to improve quality and increase the quantity of care delivered at its public hospitals. PBF evaluations identified quality gaps that prompted a movement to pursue an accreditation process for public hospitals. CHOICE OF SOLUTION: Since it was prohibitively costly to implement an accreditation program overseen by an external entity to all of Rwanda's public hospitals, the Ministry of Health developed a set of standards for a national 3-Level accreditation program. IMPLEMENTATION: In 2012, Rwanda launched the first phase of the national accreditation system at five public hospitals. The program was then expected to expand across the remainder of the public hospitals throughout the country. EVALUATION: Out of Rwanda's 43 public hospitals, a total of 24 hospitals have achieved Level 1 status of the accreditation process and 4 have achieved Level 2 status of the accreditation process. LESSONS LEARNED: Linking the program to the country's existing PBF program increased compliance and motivation for participation, especially for those who were unfamiliar with accreditation principles. Furthermore, identifying dedicated quality improvement officers at each hospital has been important for improving engagement in the program. Lastly, to improve upon this process, there are ongoing efforts to develop a non-governmental accreditation entity to oversee this process for Rwanda's health system moving forward.

Rwanda 20 years on: investing in life.

Two decades ago, the genocide against the Tutsis in Rwanda led to the deaths of 1 million people, and the displacement of millions more. Injury and trauma were followed by the effects of a devastated health system and economy. In the years that followed, a new course set by a new government set into motion equity-oriented national policies focusing on social cohesion and people-centred development. Premature mortality rates have fallen precipitously in recent years, and life expectancy has doubled since the mid-1990s. Here we reflect on the lessons learned in rebuilding Rwanda's health sector during the past two decades, as the country now prepares itself to take on new challenges in health-care delivery.

Shared learning in an interconnected world: innovations to advance global health equity.

The notion of "reverse innovation"--that some insights from low-income countries might offer transferable lessons for wealthier contexts--is increasingly common in the global health and business strategy literature. Yet the perspectives of researchers and policymakers in settings where these innovations are developed have been largely absent from the discussion to date. In this Commentary, we present examples of programmatic, technological, and research-based innovations from Rwanda, and offer reflections on how the global health community might leverage innovative partnerships for shared learning and improved health outcomes in all countries.