Retrieval-Augmented Clinical Benchmarking for Contextual Model Testing in Kenyan Primary Care: A Methodology Paper
This work addresses the problem of safe AI deployment in African health systems by providing a replicable model for guideline-driven, dynamic benchmarking, though it is incremental as it adapts existing RAG methods to a new domain.
The paper tackled the underexplored effectiveness of LLMs in African primary care by developing a methodology for creating a benchmark dataset and evaluation framework focused on Kenyan clinical care, revealing significant performance gaps when LLMs are applied to localized scenarios, consistent with lower accuracy on African medical content compared to US-based benchmarks.
Large Language Models(LLMs) hold promise for improving healthcare access in low-resource settings, but their effectiveness in African primary care remains underexplored. We present a methodology for creating a benchmark dataset and evaluation framework focused on Kenyan Level 2 and 3 clinical care. Our approach uses retrieval augmented generation (RAG) to ground clinical questions in Kenya's national guidelines, ensuring alignment with local standards. These guidelines were digitized, chunked, and indexed for semantic retrieval. Gemini Flash 2.0 Lite was then prompted with guideline excerpts to generate realistic clinical scenarios, multiple-choice questions, and rationale based answers in English and Swahili. Kenyan physicians co-created and refined the dataset, and a blinded expert review process ensured clinical accuracy, clarity, and cultural appropriateness. The resulting Alama Health QA dataset includes thousands of regulator-aligned question answer pairs across common outpatient conditions. Beyond accuracy, we introduce evaluation metrics that test clinical reasoning, safety, and adaptability such as rare case detection (Needle in the Haystack), stepwise logic (Decision Points), and contextual adaptability. Initial results reveal significant performance gaps when LLMs are applied to localized scenarios, consistent with findings that LLM accuracy is lower on African medical content than on US-based benchmarks. This work offers a replicable model for guideline-driven, dynamic benchmarking to support safe AI deployment in African health systems.