Maverick Citizen

MAVERICK CITIZEN

Wits develops artificial intelligence project with Canadian university to tackle Covid-19 in Africa

The South African Covid-19 Dashboard includes a range of indexes and monitors the evolution of the pandemic from different standpoints. It also contains a site where the risk index of a second surge for South Africa is updated daily. (Image: Adobe Stock)

The University of the Witwatersrand has teamed up with York University, Canada, to undertake an artificial intelligence project that can be another tool to tackle the Covid-19 pandemic in Africa. The project will be used for predictive modelling and forecasting of the pandemic.

The Africa-Canada Artificial Intelligence and Public Health Data Modelling Consortium has secured a $1.25-million grant from the International Development and Research Centre (IDRC) for the Predictive modelling and forecasting of the transmission of Covid-19 in Africa using Artificial Intelligence project. It is one of nine projects selected for funding through the Global South AI4COVID Response Program, focused on low and middle-income countries.

The project will build on transmission models and simulation technologies developed by both universities and on the South Africa Covid-19 Dashboard developed by the Institute for Collider Particle Physics.

The Covid-19 Dashboard is an analytics dashboard that includes a range of indexes and monitors the evolution of the pandemic from different standpoints. It also contains a site where the risk index of a second surge for South Africa is updated daily.

“This analytics dashboard has played a strong role in engaging with the population, including clinicians and practitioners, on the one hand, and the economic sector, on the other – from whom we get regular feedback – policymakers and the press,” says Professor Bruce Mellado, a member of the Gauteng Premier’s Advisory Committee on Covid-19.

“Our team, in collaboration with the Gauteng Department of Health and its many stakeholders, has developed the modelling for the Gauteng province. 

“Modelling the pandemic belongs to the realm of modelling of complex systems, where there are a lot of variables, factors and unknown dynamics. Artificial intelligence is the most advanced set of tools to learn from the data and transfer that knowledge for the purpose of creating realistic modelling,” says Mellado. 

One example of how AI has helped with modelling is the characterisation and understanding of Covid-19 hot spots, which is extremely complicated because it is dependent on numerous factors which are intrinsic to the community where it develops.

“Artificial intelligence has helped us gain a lot of confidence in the modelling of this complex problem [hot spots], thanks to the fact that we have learnt a big deal from the data,” says Mellado.

He says data flows have improved “greatly” since the start of the pandemic. The team will be able to provide reliable forecasting models based on data that has been extensively scrutinised by an interdisciplinary team of experts.

“We have learnt a big deal about the dynamics of the pandemic in the Gauteng province. This is in part thanks to the use of artificial intelligence and other advanced analytical techniques. For instance, recent modelling efforts, such as the development of a risk index, have been successful in predicting the emergence of the second surge in several regions of the country.”

Mellado adds that the uses of the project extend far beyond the Covid-19 pandemic.

“The project is intended as a template for crisis and disaster management that should go beyond healthcare crises. That said, the current crisis provides a unique opportunity, given the span of the crisis and its complexity, to develop algorithms, methodologies and ideas that can be applied to other types of crises. The project entails transferring this knowledge to other countries in the continent.” 

The consortium, which is international and open to all African countries, is co-chaired by Mellado (University of the Witwatersrand) and Professor Jianhong Wu (York University), while Professor Jude Kong is the Canadian principal investigator.

“Working with organisations in Africa, we will develop models and simulations of Covid-19 that are relevant to specific cities and the areas adjacent to them,” says Kong.

Professor Zeblon Vilakazi, incoming vice-chancellor of Wits University, says that while the pandemic has disrupted life, it has also “galvanised our rapid adaptation to change and the adoption of new technologies”.

“Wits is proud to collaborate with leading scholars from York University on this multidisciplinary project to develop modern technologies to strengthen the fight against Covid-19. We are in a crucial moment in the life of this pandemic and it is important that we work as a collective for the benefit of society.” DM/MC

Like what you’re reading? Sign up to the Maverick Citizen newsletter and get a weekly round-up sent to your inbox every Tuesday. Free. Because paywalls should not stop you from being informed.

Gallery

"Information pertaining to Covid-19, vaccines, how to control the spread of the virus and potential treatments is ever-changing. Under the South African Disaster Management Act Regulation 11(5)(c) it is prohibited to publish information through any medium with the intention to deceive people on government measures to address COVID-19. We are therefore disabling the comment section on this article in order to protect both the commenting member and ourselves from potential liability. Should you have additional information that you think we should know, please email [email protected]"