Prediction of the effective reproduction number of COVID-19 in Greece. A machine learning approach using Google mobility data

  1. Environmental Informatics Research Group, School of Mechanical Engineering, Aristotle University of Thessaloniki, Greece
  2. Athanasios Arvanitis
  3. Irini Furxhi
  4. Deptartment of Accounting and Finance, Kemmy Business School, University of Limerick, Ireland
  5. Thomas Tasioulis
  6. Environmental Informatics Research Group, School of Mechanical Engineering, Aristotle University of Thessaloniki, Greece
  7. Konstantinos Karatzas
  8. Environmental Informatics Research Group, School of Mechanical Engineering, Aristotle University of Thessaloniki, Greece

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

This paper demonstrates how a short-term prediction of the effective reproduction number (Rt) of COVID-19 in regions of Greece is achieved based on online mobility data. Various machine learning methods are applied to predict Rt and attribute importance analysis is performed to reveal the most important variables that affect the accurate prediction of Rt. Work and Park categories are identified as the most important mobility features when compared to the other attributes, with values of 0.25 and 0.24, respectively. Our results are based on an ensemble of diverse Rt methodologies to provide non-precautious and non-indulgent predictions. Random Forest algorithm achieved the highest R2 (0.8 approximately), Pearson’s and Spearman’s correlation values close to 0.9, outperforming in all metrics the other models. The model demonstrates robust results and the methodology overall represents a promising approach towards COVID-19 outbreak prediction. This paper can help health-related authorities when deciding on non-nosocomial interventions to prevent the spread of COVID-19.

Article activity feed

  1. Version published to 10.31181/jdaic1001202201f
  2. ScreenIT

    SciScore for 10.1101/2021.05.14.21257209: (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

    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: We detected the following sentences addressing limitations in the study:
    Limitations imposed to mobility are varying in each country so direct comparisons are not reliable. For the shake of reference we note that in a similar study analysing google mobility data from 11 different countries, (Bryant and Elofsson 2020) found that grocery and pharmacy sector displayed the most significant correlations and had the highest influence in the prediction of R0. Other, similar studies (Wang and Yamamoto 2020, Kuo and Fu 2021) come in line with our work; predicting infection level using mobility data with or without evaluating countermeasures, such as face covering and social distancing, they demonstrated high mobility variances in Park ranking it as second parameter in prediction importance. It should be noted, that the least contributing mobility sector to Rt, Retail, has been often the focus of control measures, sometimes limiting the number of visitors inside shops, often closing them completely. Those measures resulted in shrinking the economic activity of retail subsectors that could not compensate customer visits with online shopping, like clothing shops, for instance, that in Q4-2020 suffered losses greater than 50% in their economic activity compared to 201910. Our results do not justify Retail to be the focus of mobility control measures to reduce Rt, probably because face covering and social distancing had been respected inside stores more than in workplaces and parks11. Training the predictive models using data from mid-June 2020 to January 2021 ...

    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.

  3. Version published to 10.1101/2021.05.14.21257209v1 on medRxiv