Detecting infection via surrogates and learning system

OVERVIEW

Georgetown University researchers have invented a triage system that determines whether a user is likely to have contracted a disease based on sensor data received from a user device (e.g., a smartphone or activity tracker). It is designed to detect symptoms of various diseases using indirect body monitoring sensor systems. It utilizes heart rate variability, sound analysis, activity tracking, and more to diagnose symptoms indirectly.

Its wide application includes use as a quick and effective viral infections prescreening tool. The method is based on its ability to determine whether a user is likely to have contracted a disease based on sensor data (compared to a predetermined either population baseline or individualized baseline) received from a user device, such as a smartphone.

Utilizing intelligent computing devices and body monitoring sensor systems, a machine learnable, interpretable assessment score can be computed, to serve as a comprehensive prescreening tool which identifies whether a user is likely to have contracted a disease. The system collects and analyzes a multitude of body readings, such as heart rate variability, sleep patterns, and movement data, to assess the likelihood of infection based on medically-sound surrogates for symptoms.

In the event of a future epidemic or pandemic, the system provides a platform that can also be used to recognize the symptoms of a future virus, bacteria, parasite, engineered bioweapon, etc.

BACKGROUND

The development of a distributed system for detecting symptoms of viral infections, with existing sensor technology and surrogates, addresses critical challenges in healthcare and population health issues. Traditional methods of identifying infected individuals and conducting contact tracing could be inaccessible to many patients.

With sensors in smartphones and wearable fitness devices, this system continuously monitors physiological parameters and environmental data to infer symptoms, even when direct measurement is not feasible. Software-based triage systems can adapt and evolve as medical consensus on symptom correlations evolves. Furthermore, the system is able to track user location and facilitates efficient contact tracing, aiding in containment efforts.

Benefit

• Identifying symptoms while reducing exposure risk by enabling remote prescreening and contact tracing. The system minimizes the need for in-person medical visits and testing, reducing exposure for both patients and caregivers.
• Enhanced User Experience with digital interface, automated analysis, and guidance for necessary actions, enlarge scope of target users

Market Application

• Public Health Agencies including Government agencies can enhance disease surveillance, and design response strategies during outbreaks.
• Corporate, schools, and other businesses can deploy the system to safeguard the health and safety of visitors, facilitating early detection and containment of infections within a public space.
• Hospitals, clinics, and healthcare providers can implement the system to streamline prescreening and contact tracing processes.

Publications

• US Patent No.: US 11,728,042 B2
• Hoilett, O.S., et al. (Jul. 2018). Kick L: A Smartwatch for Monitoring Respiration and Heart Rate using Photoplethysmography. 2018 40th Annual International Conference of the lEEE Engineering in Medicine and Biology Society (EMBC). https://doi.org/10.1109/embc.2018.8513356.