CARE-GEN

While artificial intelligence offers transformative potential for enhancing healthcare access and  quality, it faces substantial challenges in the realms of transparency, trust, and clinical accuracy. These issues are particularly pronounced in underserved communities, where data scarcity further hampers AI's efficacy. The central aim of this research initiative is to harness the capabilities of generative AI to elevate the standard of primary care in such marginalized populations on a global scale.

Our project will pioneer the use of a collective intelligence-based Reinforcement Learning with Expert Feedback (RLEF) methodology to rigorously assess and refine the clinical outputs generated by large language models (LLMs). This innovative approach addresses the critical data gap that hinders the application of healthcare AI in underserved settings. You will assist us in generating and evaluating synthetic patient data using machine learning models, as well as configuring an experimental platform to collect initial provider data.