A prediction model for COVID-19 prevalence based on demographic and healthcare parameters in Iran

  1. Parimah Emadi Safavi
  2. Karim Rahimian
  3. Alireza Doustmohammadi
  4. Mahla Safari dastjerdei
  5. Ahmadreza Rasouli
  6. Javad Zahiri

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

Coronavirus Disease 2019 (COVID-19) pandemic has become the greatest threat to global health in only a matter of months. Iran struggling with COVID-19 coincidence with Nowruz vacations has led to horrendous consequences for both people and the public health workforce. Modeling approaches have been proved to be highly advantageous in taking appropriate actions in the early stages of the pandemic. To this date, no study has been conducted to model the disease to investigate the disease, especially after travel restrictions in Iran. In this study, we exploited the opportunities that Artificial neural networks offer to investigate contributing factors of early-stage coronavirus spread via generating a model to predict daily confirmed cases in Iran. We collected publicly available data of confirmed cases in 24 provinces from April 4, 2020, to May 2, 2020, with a list of explanatory factors. The factors were checked separately for any linear associations and to train and validate a multilayer perceptron network. The accuracy of the models was evaluated, the R2 scores were 0.842 for population distribution, 0.822 for health index, and 0.864 for the population in the provinces. Our results suggest the significant impact of the mentioned factors on disease spread in the time of travel restrictions when the vacation ended. Accordingly, this information can be implicated in assessing the risk of epidemics and future policy makings in this area.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2021.01.27.21250551: (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
    All the procedure was performed in the python environment using scikitlearn library on a PC with a six-core 2.6 GHz processor and 16 GBs RAM.
    python
    suggested: (IPython, RRID:SCR_001658)

    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:
    In the course of our research, we faced some limitations mostly due to the lack of data in the case of both variables and daily cases. Many factors may be involved in the virus spread across the country which was not accessible at the province level. Also, we were not able to verify our predicted data to the real data since the data was not published for provinces. characterizing the main factors of the early-stage outbreak of such a contagious virus provides opportunities to comprehend the early dynamics of the outbreak. Also, it could be of great importance in confronting the future epidemics, in terms of taking preventive action or implementing control measures by policymakers based on prior knowledge.

    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 10.1101/2021.01.27.21250551v1 on medRxiv