I-Corps: Translation Potential of Edge-Artificial Intelligence (AI) Personalized Risk Prediction for International Travelers

This I-Corps project is based on the development of a mobile health platform that uses artificial intelligence (AI) to provide infectious disease risk predictions for international travelers. Static travel advisories and pre-trip clinic consultations only consider what is known before travelers leave the airport. Once abroad, travelers have no reliable way to assess their risk based on their symptoms, locations, environmental conditions, and social exposure. This also hinders public health agencies, which lack real-time data on disease patterns among travelers. This technology is a privacy-preserving, on-device AI system that learns from each traveler's data to deliver tailored risk assessments without sending personal health information to external servers. The technology may benefit travelers, travel clinics, hospital systems, occupational health departments, and public health agencies. This I-Corps project utilizes experiential learning coupled with first-hand investigation of the industry ecosystem to assess the translation potential of an artificial intelligence (AI)-powered mobile platform for personalized health prediction for travelers. This technology comprises three interconnected innovations: an edge architecture that performs AI model training directly on the user's smartphone, operating reliably under intermittent internet connectivity typical of international travel; a “warm-up” transition method that solves the cold-start personalization problem by dynamically shifting from a general population model to an individualized model as enough data accumulates on the phone; and a passive Bluetooth proximity algorithm that estimates social mixing and crowd density by detecting nearby devices, without requiring those devices to run any application. Previous research demonstrated real-time participatory data collection and higher user engagement and data completion rates than comparable tools. The platform's edge architecture ensures that personal health data remains on the device, establishing a new standard for privacy-preserving mobile health AI that benefits users through actionable, location-aware health guidance while contributing aggregated, anonymized insights to public health monitoring. 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.