SBIR Phase II: A Clinical Decision Making tool to improve diagnosis, management and research

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project advances healthcare through creating an innovation consisting of a self-learning system that combines real life patient data with existing literature and genomic databases to help diagnose patients faster at the point of care, treat them more accurately, and uncover new insights. The market opportunity lies in the need for tools that speed up diagnosis and guide treatment. The value proposition offers personalized recommendations at the point of care that reduce inefficiencies and provide expert medical care regardless of the location. This technology provides a durable competitive advantage through its seamless integration into existing systems and ease of use by patients and providers alike. This Small Business Innovation Research (SBIR) Phase II project develops an artificial intelligence (AI)-supported platform to improve diagnosis and management. The project consists of a patient-facing application that aggregates multimodal data from different types of electronic health record (EHR) portals, building backend analytics infrastructure with application programming interfaces (APIs) and retrieval-augmented generation (RAG) models drawn from validated medical sources, and deploying EHR-integrated alerts for real-time clinical decision support. The proposed research involves deployment of the technology across multiple institutions adapting to different EHR systems, increasing patient app availability, and subsequent assessment of impacts on diagnoses, referrals, and healthcare utilization. Methods incorporate large language models for guideline synthesis, secure data handling with encryption and relational databases, and automated updates from public resources like national databases. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.