AI algorithm system predicts low risk of third wave in SA



Published Apr 13, 2021


MANY South Africans anticipated the arrival of the third Covid-19 wave in the country shortly after Easter. However, an artificial-intelligence-based algorithm predicts otherwise.

Wits University, which designed the early-detection system in partnership with iThemba LABS, reports that the system works by predicting future daily confirmed Covid-19 cases, based on historical data from South Africa’s past infection rate and mortality rate. It makes use of numerous indexes and parameters such as lockdown interventions like travel bans.

“These parameters are consistent with clinical public health measures that can contain, control and mitigate against the Covid-19 pandemic,” says Dr James Orbinski, the director of the York University Dahdaleh Institute for Global Health Research.

The AI system’s predictions are freely accessible to the public. Although they are predictions, the developers say in the forecast produced within a two-week period, as anything more than that may be less accurate.

“The current data shows us the risk for a third infection wave of Covid-19 is small across most of provinces in South Africa, but we still remain highly vulnerable,” says Professor Bruce Mellado, the director of the Institute for Collider Particle Physics at Wits University.

The AI-algorithm regularly updates with the latest data, using newly acquired data to adjust complex predictions and learn even more. Such tools can be used to issue alerts once identifying significant changes that may lead to the beginning of a new wave.

Ali Asgary, a professor of disaster and emergency management and the associate director of York University's Advanced Disaster, Emergency, and Rapid-Response Simulation, says: “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.”