JMIR Publications

ABSTRACT

COVID-19 has impacted billions of people globally, especially those with severe COVID-19 cases, millions of whom have died. However, there still remains to be seen a publicly available chat bot for patients and care providers to determine the potential severity of a person’s COVID-19 infection and an in-depth understanding of the system responses and co-morbidities that can contribute to the development of a severe case of COVID-19. The main objective was to construct a decision tree for chat bot application based on literature review for clinical decision support of severe cases of COVID-19. After reviewing relevant literature, we constructed a decision tree using the suite of tools that supported building decision tree frameworks for chat bot application. We established 212 nodes that were stratified from lung to heart conditions along body systems, medical conditions, co-morbidities and relevant manifestations described in the literature. This construction of the knowledge-based decision tree resulted in a possible 63,360 scenarios, which provide a method to understanding the data needed to validate the decision tree, and which show the complicated nature of severe cases of COVID-19. The decision tree does indicate that stratification of the viral infection with the body system, incorporating co-morbidities and manifestations, strengthened the framework. Despite some modest limitations, the application can provide modelling aspects as well as provide insight into the type of data required for an accurate and precise decision-support tool for severe COVID-19 assessments.