No abstract

The Severe Acute Respiratory Syndrome Coronavirus 2 pandemic has challenged medical systems to the brink of collapse around the globe. In this paper, logistic regression and three other artificial intelligence models (XGBoost, Artificial Neural Network and Random Forest) are described and used to predict mortality risk of individual patients. The database is based on census data for the designated area and co-morbidities obtained using data from the Ontario Health Data Platform. The dataset consisted of more than 280,000 COVID-19 cases in Ontario for a wide-range of age groups; 0–9, 10–19, 20–29, 30–39, 40–49, 50–59, 60–69, 70–79, 80–89, and 90+. Findings resulting from using logistic regression, XGBoost, Artificial Neural Network and Random Forest, all demonstrate excellent discrimination (area under the curve for all models exceeded 0.948 with the best performance being 0.956 for an XGBoost model). Based on SHapley Additive exPlanations values, the importance of 24 variables are identified, and the findings indicated the highest importance variables are, in order of importance, age, date of test, sex, and presence/absence of chronic dementia. The findings from this study allow the identification of out-patients who are likely to deteriorate into severe cases, allowing medical professionals to make decisions on timely treatments. Furthermore, the methodology and results may be extended to other public health regions.

With the recent outbreak of COVID-19, the reach and scale of COVID-19 cases is top of mind for everyone and many research groups are actively monitoring and exploring the potential spread. A positive consequence of past epidemics and pandemics is that there are sound epidemiological compartmental modelling approaches that can effectively model disease spread. With minor changes to the underlying dynamical system of equations, many different strategies and situations can be explored. In particular, one such strategy of social distancing is top of mind for many Canadians as our political leaders, local businesses, and fellow Canadians promote and adopt this approach with the hopes that it will effectively 'flatten the curve' and reduce or prevent further spread. In this paper, the baseline model is introduced with its close counterpart, the model. Social distancing is modelled through the isolation of a subset of the susceptible population and comparative studies are performed considering a range in the proportion of individuals isolated. Robust and accurate numerical approximation techniques are used to simulate the pessimistic base case for which no preventative measures are taken and for various social distancing regimes. The results of social distancing are consolidated into two groups-those that flatten the curve and those that completely halt the disease spread. Mathematical formulations show that the turning point between these two regimes is when the effective reproductive rate, denoted , is equal to 1. Conclusions are made regarding the impacts and extent of the spread in relation to the severity of social distancing measures.

No abstract

No abstract