This real-world study found that an AI-powered clinical decision support tool, AI Consult, led to a significant reduction in diagnostic and treatment errors made by clinicians in primary care clinics in Nairobi, Kenya. The tool improved clinician performance across various areas, including history taking, investigations, diagnosis, and treatment, with particularly strong effects observed after the introduction of active deployment strategies. While there was no statistically significant difference found in patient-reported outcomes, the study suggests the potential of LLM-based tools to improve the quality of care in real-world settings.

Several authors are affiliated with Penda Health, where the study was conducted. OpenAI, which developed the AI tool, also provided funding for the study and was involved in analysis and reporting.

This study demonstrates a real-world implementation of an LLM-based clinical decision support tool and its impact on clinician performance. Despite some limitations like the relatively short study duration and limited generalizability, the findings are promising and suggest that AI can be useful in improving healthcare delivery in resource-constrained settings. The study also highlights the importance of carefully considering ethical considerations and potential conflicts of interest in AI research.