How AI is helping COVID-19 Diagnostics and Detection

The Vice-Chancellor & Principal of the University of Johannesburg, Prof Tshilidzi Marwala recently penned an opinion article published by Forbes Africa in the June/July 2020 edition.

In the early hours of New Year’s Eve last year, BlueDot’s artificial intelligence (AI) warning system, which sifts through 100,000 articles and online posts daily in 65 languages, flagged a news report about a few “unusual pneumonia” cases happening in the crowded metropolis of Wuhan in China.

The Toronto based startup had spotted the coronavirus, or COVID-19, nine days before the World Health Organization (WHO) released a statement alerting people to the emergence of the virus. BlueDot, which is based on big data and machine learning, was created by healthcare professor Kamran Khan. It sends out alerts of disease outbreaks that its AI has discovered, and the potential risks posed to healthcare, government, business, and public health clients. Khan founded the startup following the Severe Acute Respiratory Syndrome (SARS) epidemic in 2003, which affected 26 countries, resulted in more than 8,000 cases, killed 774 people and cost an estimated $40 billion globally, in just six months. BlueDot signalled a warning that many at the time did not heed.

Since then, the coronavirus has been declared a pandemic by WHO and has had a devastating impact globally, with very few countries emerging unscathed. Large-scale quarantines, in some instances complete lockdowns, travel restrictions and social-distancing have seen economies ravaged, unemployment rise, and there are now expectations of a recession far worse than the global financial crisis of 2008-09.

Yet, in this global health crisis, proponents of AI have been swift to act. The use of AI to combat the coronavirus has ranged from robotic cleaners spraying disinfectant at segregated wards to voice assistants calling people to advise on home-quarantine to AI-powered infrared sensors that detect body temperatures on the foreheads of moving passengers. The autonomous robots, for instance, have replaced human cleaners, which has reduced infection rates and can also work nonstop for more than three hours. This has been particularly effective in China and South Korea where there has been a marked slowdown in infection rates in recent weeks.

This is also mainly because detection has been made easier with AI. Damo Academy, a research institute under Chinese e-commerce company Alibaba, has developed an AI device capable of detecting the coronavirus in just under 20 seconds with 96% accuracy. The AI was trained using 5,000 samples from confirmed cases and can now identify the virus from chest CT scans, differentiating between infected patients and general viral pneumonia cases. South Korea was swift to act following the outbreak in China, anticipating a spread into its borders. The government mobilised the private sector to develop testing kits for the virus.

It is not just pockets of AI that have cropped up in these regions. The opportunity for AI to speed up the discovery of vaccines, drugs and diagnostics is gaining traction elsewhere. Projects such as the COVID-19 Open Research Dataset provide free access to the texts of almost 25,000 research papers while the COVID-net open access neural network is working on systems similar to those deployed by the Damo Academy. Vir Biotechnology and Atomwise, startups in the United States, are using AI to identify a molecule that could serve as the basis of treatment.

Similarly, there has been a shift to find AI solutions on the continent with Africa’s cases sitting at around 5,000 by the end of March. Data science competition platform Zindi, which is based in South Africa and Ghana, has launched a challenge sponsored by the Artificial Intelligence for Development-Africa Network (AI4D-Africa). This challenge asks data scientists to build an epidemiological model that predicts the spread of COVID-19 throughout the world over the next few months, which is critical for both policymakers and health workers to make informed decisions and take action. In Kenya, startup Afya Rekod is deploying AI and Blockchain to establish a health data platform which allows users to store their health records, access health information and connect to health service providers.

While the disruptions caused by the coronavirus will undoubtedly be our new normal for a while, we are far more technologically equipped than we were with the SARS outbreak of 2003, let alone the Spanish Flu outbreak which followed a similar trajectory a century ago. The end of the coronavirus may just lie in the same technology that anticipated it would be a pandemic.

*The views expressed in the article is that of the author/s and does not necessarily reflect that of the University of Johannesburg.

prof tshilidzi marwala
Prof Tshilidzi Marwala Vice- Chancellor & Principal of the University of Johannesburg
Share this

Latest News

All News