Abstract
The worldwide rapid spread of the severe acute respiratory syndrome coronavirus 2 has affected millions of individuals and caused unprecedented medical challenges by putting healthcare services under high pressure. Given the global increase in number of cases and mortalities due to the current COVID-19 pandemic, it is critical to identify predictive features that assist identification of individuals most at-risk of COVID-19 mortality and thus, enable planning for effective usage of medical resources. The impact of individual variables in an XGBoost artificial intelligence model, applied to a dataset containing 57,390 individual COVID-19 cases and 2,822 patient deaths in Ontario, is explored with the use of SHapley Additive exPlanations values. The most important variables were found to be: age, date of the positive test, sex, income, dementia plus many more that were considered. The utility of SHapley Additive exPlanations dependency graphs is used to provide greater interpretation of the black-box XGBoost mortality prediction model, allowing focus on the non-linear relationships to improve insights. A “Test-date Dependency” plot indicates mortality risk dropped substantially over time, as likely a result of the improved treatment being developed within the medical system. As well, the findings indicate that people of lower income and people from more ethnically diverse communities, face an increased mortality risk due to COVID-19 within Ontario. These findings will help guide clinical decision-making for patients with COVID-19.
Highlights
With issues of the second wave of the COVID-19 pandemic ongoing in 2021 and the world in a continuing crisis, interest continues to escalate to improve the understanding of features resulting in virus caseload increases
Of the 57,390 cases included in the dataset, 2,822 patients died of COVID-19 and the remaining 54,568 either recovered from COVID-19 or remained hospitalized as of January 1, 2021
The X axis represents the SHAP value associated with each variable and patient within the training dataset
Summary
With issues of the second wave of the COVID-19 pandemic ongoing in 2021 and the world in a continuing crisis, interest continues to escalate to improve the understanding of features resulting in virus caseload increases. Of particular interest are opportunities to improve modeling prediction capabilities which can provide more accurate information as it becomes available from the first and second waves of COVID-19. In this regard, until recently, data security and privacy issues have limited accessibility to alternate and detailed data sources, but opportunities are opening up and showing real potential. AI models in general, and Snider et al (2021) in particular, provide dimensions including the ability to uncover and understand the value of an array of “base” information, including co-morbidity data, that influence mortality rates including at the case-by-case level. Findings on the risks of mortality for individual patients have the potential to influence many important actions such as helping identify “most at-risk populations” providing insights on hospitalizations/medical strategies and opportunities to aid delivery of COVID-19 vaccination priority strategies in the future
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
