Artificial intelligence to predict the risk of mortality from Covid-19: Insights from a Canadian Application

  1. Brett Snider
  2. Paige Phillips
  3. Aryn MacLean
  4. Edward McBean
  5. S. Andrew Gadsden
  6. John Yawney

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

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.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2020.09.29.20201632: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    Institutional Review Board Statementnot detected.
    Randomizationnot detected.
    Blindingnot detected.
    Power Analysisnot detected.
    Sex as a biological variablenot detected.

    Table 2: Resources

    No key resources detected.

    Results from OddPub: We did not detect open data. We also did not detect open code. Researchers are encouraged to share open data when possible (see Nature blog).

    Results from LimitationRecognizer: An explicit section about the limitations of the techniques employed in this study was not found. We encourage authors to address study limitations.

    Results from TrialIdentifier: No clinical trial numbers were referenced.

    Results from Barzooka: We did not find any issues relating to the usage of bar graphs.

    Results from JetFighter: We did not find any issues relating to colormaps.

    Results from rtransparent:
    • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
    • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
    • No protocol registration statement was detected.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.

  2. Version published to 10.1101/2020.09.29.20201632v1 on medRxiv