Covid-19: Low risk for third wave in SA - AI powered algorithm predicts
But the country is still highly vulnerable
Amid fears of the possibility of the country experiencing a third wave of Covid-19 infections, models show there is a low risk although the country remains vulnerable.
This is according to a finding using an artificial intelligence (AI)-based algorithm designed by the University of the Witwatersrand in partnership with iThemba LABS, the provincial government of Gauteng and York University in Canada.
Wits University said the AI-powered early detection system functions by predicting future daily confirmed cases based on historical data from SA’s past infection history. It includes features such as mobility indices, stringency indices and epidemiological parameters.
“These parameters are consistent with clinical public health measures that can contain, control and mitigate against the Covid-19 pandemic,” said Dr James Orbinski, director of the York University Dahdaleh Institute for Global Health Research.
The AI-based algorithm works in parallel and supports the data of an already existing algorithm based on more classical analytics. Both algorithms work independently and are updated daily. The existence of two independent algorithms adds robustness to the predictive capacity of the algorithms. The data of the AI-based analysis is published on a website updated daily.
“Current data shows us the risk for a third infection wave of Covid-19 is small across most of provinces in SA, but we still remain highly vulnerable,” said Prof Bruce Mellado, director of the Institute for Collider Particle Physics at Wits University.
While algorithm-based predictions can never be 100% accurate, Mellado expressed his confidence that the model presents a very good prediction over at least a two-week period. While predictions can be made over longer periods, these predictions become less accurate.
Despite the good indications, it is crucial South Africans continue to adhere to the government’s Covid-19 regulations and take all necessary precautions to prevent the spread of the pandemic.
The advent of infection waves is driven by circumstances that are difficult to predict and therefore to control. In this complex environment, early detection algorithms can provide an early warning to policymakers and the population. Early detection algorithms are able to issue an alert when the data displays a significant change consistent with the advent of a new wave.
The model is trained on the interim period between waves one and two in all the provinces. The algorithm was tested with data taken during the period of past peaks to evaluate its performance.
“AI technology provides us with invaluable potential to develop early detection and alert systems that are highly needed for rapid and dynamic decision-making under risk and uncertainty under the current pandemic,” said Ali Asgary, professor of Disaster and Emergency Management and associate director of York University’s Advanced Disaster, Emergency and Rapid-response Simulation.
“Our team’s development of an early detection algorithm for the third wave speaks to the power of AI to generate data-based solutions to highly complex problems,” Mellado said.
The project is supported by the Canadian International Development Research Centre through the Africa-Canada Artificial Intelligence and Data Innovation Consortium.