Machine Learning Model for Predicting Number of COVID19 Cases in Countries with Low Number of Tests

  1. Samy Hashim
  2. Sally Farooq
  3. Eleni Syriopoulos
  4. Kai de la Lande Cremer
  5. Alexander Vogt
  6. Nol de Jong
  7. Victor L. Aguado
  8. Mihai Popescu
  9. Ashraf K. Mohamed
  10. Muhamed Amin

Reviewed by

Read the full article

Listed in

Log in to save this article

Abstract

The COVID-19 pandemic has presented a series of new challenges to governments and health care systems. Testing is one important method for monitoring and therefore controlling the spread of COVID-19. Yet with a serious discrepancy in the resources available between rich and poor countries not every country is able to employ widespread testing. Here we developed machine learning models for predicting the number of COVID-19 cases in a country based on multilinear regression and neural networks models. The models are trained on data from US states and tested against the reported infections in the European countries. The model is based on four features: Number of tests Population Percentage Urban Population and Gini index. The population and number of tests have the strongest correlation with the number of infections. The model was then tested on data from European countries for which the correlation coefficient between the actual and predicted cases R 2 was found to be 0.88 in the multi linear regression and 0.91 for the neural network model. The model predicts that the actual number of infections in countries where the number of tests is less than 10% of their populations is at least 26 times greater than the reported numbers.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2021.07.12.21260298: (What is this?)

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

    Table 1: Rigor

    NIH rigor criteria are not applicable to paper type.

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    The multiple linear regression model was built using Scikit-learn library16.
    Scikit-learn
    suggested: (scikit-learn, RRID:SCR_002577)

    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.

    Results from scite Reference Check: We found no unreliable references.

    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 10.1101/2021.07.12.21260298v1 on medRxiv