lancet-header

Preprints with The Lancet is part of SSRN´s First Look, a place where journals identify content of interest prior to publication. Authors have opted in at submission to The Lancet family of journals to post their preprints on Preprints with The Lancet. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early stage research papers that have not been peer-reviewed. The findings should not be used for clinical or public health decision making and should not be presented to a lay audience without highlighting that they are preliminary and have not been peer-reviewed. For more information on this collaboration, see the comments published in The Lancet about the trial period, and our decision to make this a permanent offering, or visit The Lancet´s FAQ page, and for any feedback please contact preprints@lancet.com.

Analysing the Effect of Containment and Mitigation Measures on COVID-19 Infection Rates Using Machine Learning on Data of 95 Countries: An Observational Study

27 Pages Posted: 18 May 2020

See all articles by Ingo W. Nader

Ingo W. Nader

IT Power Services GmbH

Elisabeth Zeilinger

University of Vienna - Faculty of Psychology

Dana Jomar

IT Power Services GmbH

Clemens Zauchner

IT Power Services GmbH

More...

Abstract

Background: Insights on the effect of containment and mitigation measures to control the global COVID-19 outbreak are mostly derived from simulation studies, which work with assumptions based on fragmented knowledge, and a high level of uncertainty. We propose a complementary approach to evaluate the effectiveness of various measures on COVID-19 infection rates and the time these measures need to become effective.

Methods: A non-linear machine learning model was used on data of 95 countries to assess the effect of 31 different containment and mitigation measures on the infection rate (i.e., growth rate of daily cumulative confirmed COVID-19 cases). Accumulated local effect (ALE) plots were used to visualise the changes in the growth rate starting from 14 days prior to measure implementation to 40 days after.

Findings: The model identified three important measures to reduce infection rates: school closures, limit public gatherings, and public services closures. On average, growth rates started to decrease about seven to ten days after implementing the measure.

Interpretation: Our analysis of empirical data indicates that strict reduction of social contact is the most effective way to reduce infection rates of COVID-19. School closure is highlighted as an important measure by the model, which sheds new light on this scientifically and politically controversially discussed measure.

Funding Statement: The authors received no specific funding for this work.

Declaration of Interests: The authors declare no competing interests.

Keywords: COVID-19; coronavirus; mitigation measures; containment measures; government measures; non-pharmaceutical interventions; machine learning; accumulated local effect plots; infection rate; cross-country study

Suggested Citation

Nader, Ingo W. and Zeilinger, Elisabeth and Jomar, Dana and Zauchner, Clemens, Analysing the Effect of Containment and Mitigation Measures on COVID-19 Infection Rates Using Machine Learning on Data of 95 Countries: An Observational Study (4/27/2020). Available at SSRN: https://ssrn.com/abstract=3590467 or http://dx.doi.org/10.2139/ssrn.3590467

Ingo W. Nader

IT Power Services GmbH

Trubelgasse 8/10-11
Vienna
Austria

Elisabeth Zeilinger (Contact Author)

University of Vienna - Faculty of Psychology ( email )

Universitaetsstrasse 7
1010 Vienn
Austria

Dana Jomar

IT Power Services GmbH

Trubelgasse 8/10-11
Vienna
Austria

Clemens Zauchner

IT Power Services GmbH

Trubelgasse 8/10-11
Vienna
Austria