Extending the range of symptoms in a Bayesian Network for the Predictive Diagnosis of COVID-19

Emerging digital technologies have taken an unprecedented position at the forefront of COVID-19 management. This paper extends a previous Bayesian network designed to predict the probability of COVID-19 infection, based on a patient's profile. The structure and prior probabilities have been amalgamated from the knowledge of peer-reviewed articles. The network accounts for demographics, behaviours and symptoms, and can mathematically identify multivariate combinations with the highest risk. Potential applications include patient triage in healthcare systems or embedded software for contact-tracing apps. Specifically, this paper extends the set of symptoms that are a marker for COVID-19 infection and the differential diagnosis of other conditions with similar presentations.