Artificial intelligence to predict the risk of mortality from COVID-19: Insights from a Canadian Application
Snider, B.; Phillips, P.; MacLean, A.; McBean, E. A.; Gadsden, A.; Yawney, J.
Show abstract
The Severe Acute Respiratory Syndrome COVID-19 virus (SARS-CoV-2) has had enormous impacts, indicating need for non-pharmaceutical interventions (NPIs) using Artificial Intelligence (AI) modeling. Investigation of AI models and statistical models provides important insights within the province of Ontario as a case study application using patients physiological conditions, symptoms, and demographic information from datasets from Public Health Ontario (PHO) and the Public Health Agency of Canada (PHAC). The findings using XGBoost provide an accuracy of 0.9056 for PHO, and 0.935 for the PHAC datasets. Age is demonstrated to be the most important variable with the next two variables being Hospitalization and Occupation. Further, AI models demonstrate identify the importance of improved medical practice which evolved over the six months in treating COVID-19 virus during the pandemic, and that age is absolutely now the key factor, with much lower importance of other variables that were important to mortality near the beginning of the pandemic. An XGBoost model is shown to be fairly accurate when the training dataset surpasses 1000 cases, indicating that AI has definite potential to be a useful tool in the fight against COVID-19 even when caseload numbers needed for effective utilization of AI model are not large.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- A multipurpose machine learning approach to predict COVID-19 negative prognosis in Sao Paulo, Brazil 94%
- A new, simple method of describing COVID-19 trajectory and dynamics in any country based on Johnson Cumulative Distribution Function fitting 93%
- Several countries in one: a mathematical modeling analysis for COVID-19 in inner Brazil 93%
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.