Princeton Professors Launch AI COVID Screening Tool

PRINCETON, NJ—NeuTigers, an artificial intelligence company spun out of Princeton University, has launched CovidDeep, a clinically validated solution that can triage those needing further testing for COVID-19 using physiological sensors data derived from wearable devices.

The CovidDeep app is 90%-plus accurate in predicting whether a person is virus-free or virus-positive, and is twice as effective as current triage tools, such as temperature checks and questionnaires, according to the developers.

“CovidDeep has been developed as a rapid screening tool to help businesses such as hospitality venues maintain a COVID-19 safe environment,” said Dr. Adel Laoui, CEO/founder, NeuTigers. “Currently, venues rely on screening tools such as temperature checks, which are only used to detect symptomatic cases and are less than 50% accurate in detecting whether a person has COVID-19. CovidDeep combines wearable sensors signals and advanced artificial intelligence analytics for a more accurate screening assessment. Proven rigorous clinical studies show it to be 90% accurate in detecting if a person is SARS-CoV-2 virus positive, even if they have no symptoms (asymptomatic). It is able to do this at scale, in real-time and cost-effectively.”

He added, “Whether it is staff or guests, people can be tested using CovidDeep app and wearable devices in less than two minutes. It is currently in use in nursing homes and senior care facilities in Europe and the U.S., as well as government facilities in France.”

Early in the pandemic, NeuTigers realized its StarDeep Smart Healthcare Platform, which delivers AI-powered solutions to augment healthcare professionals’ productivity, could be used in the fight against COVID-19. CovidDeep was developed through rigorous clinical research and validation trials beginning at San Matteo Hospital in Pavia, Italy, during the acute phase of the COVID-19 pandemic in April 2020, with further expanded prospective field studies in hospitals in France and the U.S. to explore its robustness.

CovidDeep works by collecting physiological sensor data from the Empatica E4 wristband, blood pressure and blood oxygen levels from any off-the-shelf, standalone monitors as well as personal health symptoms from a brief questionnaire. As a potential game-changer in the rapid and cost-effective screening of COVID-19, it is already being adapted to work with connected health products from Fitbit, Withings, Apple, Samsung and other devices.

How it Works
CovidDeep brings forth groundbreaking science as an app that can predict COVID-19 accurately, safely, quickly and importantly by preserving people’s privacy. Users simply answer a questionnaire regarding symptoms and health history (based on CDC guidelines) and input their health sensor’s data. Data is entered by connecting CovidDeep to an Empatica E4 Wristband as well as inputting blood pressure and blood oxygen readings using any off-the-shelf device. All data remains local to the device, is never shared and stays securely and privately under the user’s control.

CovidDeep then analyzes the data and provides a prediction as to whether someone is likely to be negative or positive for SARS CoV-2/COVID-19. The process takes around two minutes, allowing one Empatica device, blood pressure monitor and pulse oximeter to screen unlimited numbers of people after being sanitized between usages.

Available globally on Android with iOS availability coming soon, users can try CovidDeep for free with unlimited screening results for seven days.