VINES: Track 2: CERTAIN: Connectivity Effectiveness and Reliability Through AI-native Networking

Demand for remote medical care is accelerating as chronic illness grows, the population ages, and patients seek more accessible and affordable treatment. While emerging networking technologies show great promise of flexibility, there are few solutions that correlate device safety requirements to concrete network policies that maintain the required service levels for emerging healthcare applications. Further barriers to wide adoption of next generation (NextG) wireless networking in connected healthcare include gaps in quality-of-service monitoring, unclear roles and agreements, limited communication Key Performance Indicators (KPIs), and a lack of evaluation methods for NextG-enabled medical device functions. This project, Connectivity Effectiveness and Reliability Through AI-native Networking (CERTAIN), addresses these gaps with healthcare-focused solutions to bring NextG into clinical use. The project advances U.S. competitiveness in next generation (NextG) telecommunications by leading the development of “safety-as-a-service” technology. The project will develop and demonstrate a platform that ensures connected medical device safety by integrating real-time medical device safety reasoning with intelligent, telemetry-driven network diagnostics and management. It is designed to address the urgent need for trustworthy and resilient connected health infrastructures by linking medical device safety engineering with advanced networking. Programmable dynamic safety assurance cases (SACs) drive CERTAIN’s operation from network infrastructure to medical applications. For example, current infusion pumps use static SACs, while those connected through proposed technology will gain dynamic, continuously updated SACs, to support real-time safety assurances allowing pumps to function as part of an integrated, remotely managed network system. CERTAIN will reduce barriers for integrating advanced connectivity into healthcare to support the expansion of remote and home-based care, reduce healthcare costs, improve access for populations in rural communities, and accelerate the responsible adoption of AI in clinical workflows. The project is aligned with the national priority for accelerating adoption of advanced digital technologies, in particular AI, in critical sectors. 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. NSF Award ID: 2554527 | Program: 01002829DB NSF RESEARCH & RELATED ACTIVIT,01002728DB NSF RESEARCH & RELATED ACTIVIT,01002627DB NSF RESEARCH & RELATED ACTIVIT | Principal Investigator: Tian Lan | Institution: George Washington University, WASHINGTON, DC | Award Amount: $1,699,107 View on NSF Award Search: https://www.nsf.gov/awardsearch/show-award/?AWD_ID=2554527 View on Research.gov: https://www.research.gov/awardapi-service/v1/awards/2554527.html