Researchers at the Medical College of Georgia (MCG) are developing an artificial intelligence (AI)-aided coronavirus phone app to help individuals get a fast, at-home risk assessment based on how they feel and where they’ve been, and direct those who are calculated to be at risk of coronavirus infection to the nearest testing facility.
The app, which could be available within the next few weeks, will also provide local and public health officials with additional real-time information on the emerging demographics of those most at risk of coronavirus infection. This will help to better target prevention and treatment initiatives, reported Arni S.R. Srinivasa Rao, PhD, director of the Laboratory for Theory and Mathematical Modeling in the MCG Division of Infectious Diseases at Augusta University (AU), and Jose Vazquez, MD, chief of the MCG Division of Infectious Diseases. Rao and Vazquez are working with developers to finalize the app, which will be free because it addresses a public health concern. Rao is corresponding author of a report on development of the app, which is published in the journal Infection Control & Hospital Epidemiology, and titled, “Identification of COVID-19 Can be Quicker through Artificial Intelligence framework using a Mobile Phone-Based Survey in the Populations when Cities/Towns Are Under Quarantine.”
Rao said, “We wanted to help identify people who are at high risk for coronavirus, help expedite their access to screening and to medical care, and reduce the spread of this infectious disease.” As the authors noted, “It is imperative that we evaluate novel models in an attempt to control the rapidly spreading virus … In order to reduce the time to identification of a person under investigation (PUI) for the COVID-19 infection, and the rapid isolation of this individual, we propose to collect the basic travel history along with the more common manifestations using a phone-based online survey.”
The app will ask for basic demographic details, including where the individual lives, their gender, age, and race, and for information on recent contact with any individual who is known to have coronavirus, or who has traveled to areas such as Italy and China that have witnessed a relatively high incidence of the viral infection in the last 14 days.
Users will also be asked about common symptoms of infection and duration, including fever, cough, shortness of breath, fatigue, sputum production, headache, diarrhea, and pneumonia. The app will, in addition, collect similar information for individuals who live with the user but who cannot fill out their own survey.
The artificial intelligence framework will then use an algorithm that Rao has developed to rapidly assess the information, and send the individual a risk assessment—i.e., no risk, minimal risk, moderate, or high risk—and alert the nearest testing facility if a health check is likely needed. In the event that the patient is unable to travel, the test site will also be notified of the need for a mobile assessment and possible remote testing.
“Thousands of data points are able to be collected and processed through an artificial intelligence (AI) framework which can ultimately evaluate individuals that may be infected and stratify them into no-risk, minimal-risk, moderate-risk, and high-risk of being infected with the virus,” Rao and Vazquez wrote. “The identification of the high-risk cases can then be quarantined earlier, thus decreasing the chance of spread.” Conversely, the authors noted, if a respondent is at no immediate risk of having symptoms or signs related to the viral infection, then the AI-based health alert will be sent to notify them that there is no current risk of COVID-2019.
The collective information of many individuals will aid rapid and accurate identification of regions, including cities, counties, towns, and villages, where the virus is showing prevalence, and help to indicate the relative risk in that region so healthcare facilities and providers can better prepare the required resources, Rao said. It also will help investigators learn more about how the virus is spreading. Once the app is ready, it will live on the augusta.edu domain and likely in app stores on the iOS and Android platforms.
Technology can assist faster identification of possible cases and aid timely intervention, the investigators suggested, noting that the coronavirus app could be easily adapted for other infectious diseases. The accessibility and rapidity of the app coupled with machine intelligence means it could also be utilized for screening wherever large crowds gather, such as major sporting events. “Apart from cost-effectiveness, the proposed modeling will be of great assistance in identifying and controlling when populations are closed due to virus spread,” the authors stated. “In addition to these, our proposed algorithm can be easily extended to identify individuals who might have any mild symptoms and signs.”
While symptoms like fever and cough are a wide net, they are needed in order to not miss patients, Vazquez noted. “We are trying to decrease the exposure of people who are sick to people who are not sick. We also want to ensure that people who are infected get a definitive diagnosis and get the supportive care they may need.”
The scientists noted that at the time of reporting, infection with coronavirus was not a pandemic—which is defined by the World Health Organization as the worldwide spread of a new disease, including numerous flu pandemics like HINI, or swine flu, in which people find themselves exposed to a virus for which they have no immunity. However, Vazquez noted, “This is what you have to do with pandemics. You don’t want to expose an infected person to an uninfected person.” If problems with infections persist and grow, drive-thru testing sites may be another need, he commented.
The investigators hope that a readily available method to assess an individual’s risk will actually help to suppress any developing panic over the COVID-19 infection. “People will not have to wait for hospitals to screen them directly,” said Rao. “We want to simplify people’s lives and calm their concerns by getting information directly to them.”
If concern about coronavirus prompted a lot of people to show up at hospitals, many of which already are at capacity with flu cases, it would further overwhelm those facilities and increase potential exposure for those who come, suggested Vazquez.
Tests for the SARS-CoV-2 coronavirus, which include a nostril and mouth swab and sputum analysis, are now being more widely distributed by the CDC. FDA has also given permission for some of the more sophisticated academic labs, including those at Augusta University Medical Center, to use their own methods to look for signs of the viral infection, and this is something that the hospital will be pursuing. People presenting at the emergency department at AU Medical Center with concerns about the virus are brought in by a separate entrance and are escorted to a negative pressure room by employees dressed in hazmat suits, in accordance with CDC protocols, Vazquez said. As of March 5, all those who had presented at AU Medical Center had tested negative.