A Prototype for Covid Risk Assessment: Designing a Chatbot for Users to Determine Personalized Risk of Severe Outcome

Abstract

This paper overviews the creation of a COVID Risk Assessment (CRA) Chatbot prototype designed to support recommendations for individuals based on the assessment of their COVID-related risk profile. Among rapidly emerging digital technologies, AI-enabled chatbots have the potential to offer real-time interaction with users via immediate responses, notifications, and reminders; interestingly, these intelligent agents can also be designed to offer personalized advice based on specific user characteristics and may even be scaled to interface with many users concurrently. Drawing from prior research, we designed a CRA-chatbot prototype to incorporate a variety of parameters affecting the severity of COVID-19 systems. These factors include the number of vaccine doses, the date of last vaccination, previous COVID-19 infection history, age, and risk factors such as disease history. Broadly, the prototype is envisioned to take the users’ input with their personalized risk assessment of severe symptoms to further educate them; in so doing, suggestions for treatments, additional serological testing, and supplementary vaccine doses can then be made. We conclude that, within the current learning health system environments, AI-enabled chatbots are digital health tools well-suited for empowering personalized COVID-19 education and related knowledge dissemination.