Development of an Early Alert System for an Additional Wave of COVID-19 Cases using a Recurrent Neural Network with Long Short-Term Memory

18 Pages Posted: 4 May 2021

See all articles by Finn Stevenson

Finn Stevenson

University of the Witwatersrand

Kentaro Hayasi

University of the Witwatersrand

Nicola Luigi Bragazzi

University of Parma

Jude Dzevela Kong

Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC); University of Toronto

Ali Asgary

York University

Benjamin Lieberman

University of the Witwatersrand

Xifeng Ruan

University of the Witwatersrand

Thuso Mathaha

University of the Witwatersrand

Salah-Eddine Dahbi

University of the Witwatersrand

Nalomotse Choma

University of the Witwatersrand

Mary Kawonga

University of the Witwatersrand

Mduduzi Mbada

Gauteng Health Department

Nidhi Tripathi

University of the Witwatersrand

James Orbinski

York University

Bruce Mellado

University of the Witwatersrand

Jianhong Wu

York University - Laboratory for Industrial and Applied Mathematics; Africa-Canada Artificial Intelligence and Data Innovation Consortium

Date Written: May 3, 2021

Abstract

The impact of the still ongoing “Coronavirus Disease 2019” (COVID-19) pandemic has been and is still vast, affecting not only global human health and stretching healthcare facilities, but also profoundly disrupting societal and economic systems worldwide. The nature of the way the virus spreads causes cases to come in further recurring waves. This is due a complex array of biological, societal and environmental factors, including the novel nature of the emerging pathogen. Other parameters explaining the epidemic trend consisting of recurring waves are logistic-organizational challenges in the implementation of the vaccine roll-out, scarcity of doses and human resources, seasonality, meteorological drivers, and community heterogeneity, as well as cycles of strengthening and easing/lifting of the mitigation interventions. Therefore, it is crucial to be able to have an early alert system to identify when another wave of cases is about to occur. The availability of a variety of newly developed indicators allows for the exploration of multi-feature prediction models for case data. Ten indicators were selected as features for our prediction model. The model chosen is a Recurrent Neural Network with Long Short-Term Memory. This paper documents the development of an early alert/detection system that functions by predicting future daily confirmed cases based on a series of features that include mobility and stringency indices, and epidemiological parameters. The model is trained on the intermittent period in between the first and the second wave, in all of the South African provinces.

Suggested Citation

Stevenson, Finn and Hayasi, Kentaro and Bragazzi, Nicola Luigi and Kong, Jude Dzevela and Asgary, Ali and Lieberman, Benjamin and Ruan, Xifeng and Mathaha, Thuso and Dahbi, Salah-Eddine and Choma, Nalomotse and Kawonga, Mary and Mbada, Mduduzi and Tripathi, Nidhi and Orbinski, James and Mellado, Bruce and Wu, Jianhong, Development of an Early Alert System for an Additional Wave of COVID-19 Cases using a Recurrent Neural Network with Long Short-Term Memory (May 3, 2021). Available at SSRN: https://ssrn.com/abstract=3838420 or http://dx.doi.org/10.2139/ssrn.3838420

Finn Stevenson

University of the Witwatersrand ( email )

1 Jan Smuts Avenue
Johannesburg, GA Gauteng 2000
South Africa

Kentaro Hayasi

University of the Witwatersrand ( email )

1 Jan Smuts Avenue
Johannesburg, GA Gauteng 2000
South Africa

Jude Dzevela Kong

Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC) ( email )

University of Toronto
Toronto, Ontario M5R 0A3
Canada

University of Toronto ( email )

105 St George Street
Toronto, Ontario M5S 3G8
Canada

HOME PAGE: http://https://aimmlab.org/

Ali Asgary

York University ( email )

4700 Keele Street
Toronto, Ontario M3J 1P3
Canada

Benjamin Lieberman

University of the Witwatersrand ( email )

1 Jan Smuts Avenue
Johannesburg, GA Gauteng 2000
South Africa

Xifeng Ruan

University of the Witwatersrand ( email )

1 Jan Smuts Avenue
Johannesburg, GA Gauteng 2000
South Africa

Thuso Mathaha

University of the Witwatersrand ( email )

1 Jan Smuts Avenue
Johannesburg, GA Gauteng 2000
South Africa

Salah-Eddine Dahbi

University of the Witwatersrand ( email )

1 Jan Smuts Avenue
Johannesburg, GA Gauteng 2000
South Africa

Nalomotse Choma

University of the Witwatersrand ( email )

1 Jan Smuts Avenue
Johannesburg, GA Gauteng 2000
South Africa

Mary Kawonga

University of the Witwatersrand ( email )

1 Jan Smuts Avenue
Johannesburg, GA Gauteng 2000
South Africa

Mduduzi Mbada

Gauteng Health Department ( email )

GDOH, 78 Fox Street, Marshalltown
Johannesburg, Gauteng
South Africa

Nidhi Tripathi

University of the Witwatersrand ( email )

South Africa
South Africa

James Orbinski

York University

4700 Keele Street
Toronto, Ontario M3J 1P3
Canada

Bruce Mellado

University of the Witwatersrand ( email )

1 Jan Smuts Avenue
Johannesburg, GA Gauteng 2000
South Africa

Jianhong Wu

York University - Laboratory for Industrial and Applied Mathematics ( email )

Canada

Africa-Canada Artificial Intelligence and Data Innovation Consortium ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
112
Abstract Views
709
Rank
454,772
PlumX Metrics