Identification of spatial variations in COVID-19 epidemiological data using K-Means clustering algorithm: a global perspective

  1. Viswa Chaitanya Chandu

Reviewed by

Read the full article

Listed in

Log in to save this article

Abstract

Background

Discerning spatial variations of COVID-19 through quantitative analysis operating on the geographically designated datasets relating to socio-demographics and epidemiological data facilitate strategy planning in curtailing the transmission of the disease and focus on articulation of necessary interventions in an informed manner.

Methods

K-means clustering was employed on the available country-specific COVID-19 epidemiological data and the influential background characteristics. Country-specific case fatality rates and the average number of people tested positive for COVID-19 per every 10,000 population in each country were derived from the WHO COVID-19 situation report 107, and were used for clustering along with the background characteristics of proportion of country’s population aged >65 years and percentage GDP spent as public health expenditure.

Results

The algorithm grouped the 89 countries into cluster ‘1’ and Cluster ‘2’ of sizes 54 and 35, respectively. It is apparent that Americas, European countries, and Australia formed a major part of cluster ‘2’ with high COVID-19 case fatality rate, higher proportion of country’s population tested COVID-19 positive, higher percentage of GDP spent as public health expenditure, and greater percentage of population being more than 65 years of age.

Conclusion

In spite of the positive correlation between high public health expenditure (%GDP) and COVID-19 incidence, case fatality rate, the immediate task ahead of most of the low and middle income countries is to strengthen their public health systems realizing that the correlation found in this study could be spurious in light of the underreported number of cases and poor death registration.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2020.06.03.20121194: (What is this?)

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

    Table 1: Rigor

    Institutional Review Board Statementnot detected.
    RandomizationK-means clustering with K=2 was performed, and it took 4 iterations for the data points to stably cluster into 2 groups with the initial randomly selected centroids moved to the true centroids of the clusters.
    Blindingnot detected.
    Power Analysisnot detected.
    Sex as a biological variablenot detected.

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    4 After selecting the aforementioned attributes to be used in the partitioning algorithm, K-means clustering analysis was performed using SPSS version 20 software (IBM SPSS statistics for windows version 20, Armonk, NY, USA).
    SPSS
    suggested: (SPSS, RRID:SCR_002865)

    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 10.1101/2020.06.03.20121194v1 on medRxiv