COVID-19 Epidemic in Switzerland: Growth Prediction and Containment Strategy Using Artificial Intelligence and Big Data

  1. Marcello Marini
  2. Ndaona Chokani
  3. Reza S. Abhari

Reviewed by

Read the full article See related articles

Listed in

Log in to save this article

Abstract

Using a previously developed agent-based artificial intelligence simulation platform (EnerPol) coupled with ‘Big Data,’ the evolution and containment of COVID-19 in Switzerland is examined. The EnerPol platform has been used in a broad range of case studies in different sectors in all of Europe, USA, Japan, South Korea and sub Saharan Africa over the last 10 years. In the present study, the entire Swiss population (8.57 million people), including cross-border commuters, and the entire Swiss public and private transport network that is simulated to assess transmission of the COVID-19 virus. The individual contacts within the population, and possible transmission pathways, are established from a simulation of daily activities that are calibrated with micro-census data. Various governmental interventions with regards to closures and social distancing are also implemented. The epidemiology of the COVID-19 virus is based on publicly available statistical data and adapted to Swiss demographics. The predictions estimate that between 22 February and 11 April 2020, there will be 720 deaths from 83’300 COVID-19 cases, and 73’300 will have recovered; our preliminary variability in these estimates is about 21% over the aforementioned period. In the absence of governmental intervention, 42.7% of the Swiss population would have been infected by 25 April 2020 compared to our prediction of a 1% infection over this time period, saving thousands of lives. It is argued that future scenarios regarding relaxation of the lockdown should be carefully simulated, as by 19 April 2020, there will still remain a substantial number of infected individuals, who could retrigger a second spread of COVID-19. Through the use of a digital tool, such as Enerpol, to evaluate in a data-driven manner the impacts of various policy scenarios, the most effective measures to mitigate a spread of COVID-19 can be devised while we await the deployment of large-scale vaccination for the population globally. By tailoring the spatio-temporal characteristics of the spread to match the capacity of local healthcare facilities, appropriate logistic needs can be determined, in order not to overwhelm the health care services across the country.

Article activity feed

  1. ScreenIT

    SciScore for 10.1101/2020.03.30.20047472: (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:
    Once additional data become available, this limitation can be addressed in future work. As the first peak subsides, the role of imported new COVID-19 cases will again play a more significant role in the containment of COVID-19. With large scale vaccination of the population some time away, the key question for the emergency management team would be on how to manage the pandemic, while minimizing the enormous economic and social impacts of isolation and the full-to-partial shutdown of the society including the transportation system and crossborder movement. Thus, in on-going work we are using scenario-based analysis to quantify the sensitivity of various interventions in order to better match the resulting demand for healthcare to the available local resources, in order to avoid overwhelming the system while waiting for the deployment of vaccination, which will hopefully come soon.

    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 10.1101/2020.03.30.20047472v2 on medRxiv
  3. Version published to 10.1101/2020.03.30.20047472v1 on medRxiv