I believe this artificial intelligence is going to be our partner. If we misuse it, it will be a risk. If we use it right, it can be our partner. ~Masayoshi Son
There is certainly a lot of pessimism around the Coronavirus, much of it well deserved. However, AI (artificial intelligence and machine learning) is poised to help save us! I’ve covered AI in the past. See Issue #8: Healthy Artificial Intelligence for a good summary.
In this issue, you’ll see how AI is used to monitor infectious disease outbreaks, help reduce the spread, and help find a cure.
An AI Epidemiologist Sent the First Warnings of the Wuhan Virus
You’ve probably heard of AI-powered chess software, facial recognition, and self-driving cars. Who knew that AI could predict outbreaks of infection?
On January 9, the World Health Organization notified the public of a flu-like outbreak in China: a cluster of pneumonia cases had been reported in Wuhan, possibly from vendors’ exposure to live animals at the Huanan Seafood Market. The US Centers for Disease Control and Prevention had gotten the word out a few days earlier, on January 6. But a Canadian health monitoring platform had beaten them both to the punch, sending word of the outbreak to its customers on December 31.
Good News: Public health officials had to rely on tight-lipped Chinese health officials for Coronavirus monitoring. But now, BlueDot uses AI to scour foreign-language news reports, animal and plant disease networks, official proclamations, and global airline ticketing data to give warning of disease outbreaks.
AI Firms Deploy Fever Detection Systems in Beijing to Fight Outbreak
So now that we know there is an outbreak, how do we stop the spread of these virulent infections?
In many public areas, such as supermarkets and rail stations, monitoring staff typically use handheld temperature-measuring devices to screen each person at a site. Apart from being a slow and relatively inefficient approach, it also puts staff at risk of being infected.
Now, AI is being put to good use. You may not be fond of the idea of AI-powered facial recognition, and I don’t blame you. However, in this case, the AI was trained to find those with fevers.
Good News: In China, AI-powered remote fever detection systems can measure a person’s temperature in a crowd at a distance of up to 15 feet. They are designed to work through masks and hats, and some systems have a margin of error within 0.05 degrees Celsius. They are rolling out detection systems to the subway entrances connected to train stations. Additional AI initiatives are robotic cleaners spraying disinfectant in hospital wards and AI voice assistants calling people to advise on home quarantine.
AI Predicts Coronavirus Vulnerable to HIV’s Atazanavir
The number of people infected with the Coronavirus from China has surpassed 30,000, exceeding the toll of the 2003 SARS epidemic. Fortunately, the number of new cases seems to be dropping.
Multiple companies have already reported working on vaccine production, including a collaboration between the mRNA company Moderna and the National Institute of Allergy and Infectious Diseases (NIAID), a branch of NIH. But, even quick vaccine development may be too slow to catch up with a growing outbreak.
Ok, so what AI tools are available to help speed the cure for those infected?
Good News: A collaboration between researchers at universities in South Korea and Emory University have published a prediction model for antiviral drugs that may be effective on the Coronavirus. The result showed that atazanavir, an antiretroviral medication used to treat and prevent HIV, is the most promising chemical compound.
Again, technology in the form of AI and machine learning is our partner, helping to save us. AI enables early detection of outbreaks, identification of those infected so they can be treated early, and eventually will help to perfect new drug treatments.
Dr. Rod Murray