AI Predicted the Wuhan Virus Before WHO
Sun, April 18, 2021

AI Predicted the Wuhan Virus Before WHO

In Wuhan, the city where the first cases of the virus were reported, restrictions were tightened, with officials banning most vehicles from the roads. Reports showed that airports, train stations, and railway stations have all been shut since the lockdown began / Photo by: Tauno Tõhk via Flickr

 

January isn’t over yet but our world has had so much to endure already since the beginning of 2020, from deadly earthquakes, volcano explosions, and bushfires to a deadly pandemic known as the novel coronavirus (2019-nCoV). The new virus, which started in Wuhan, China, is a large family of viruses that can cause respiratory illnesses such as the common cold. The coronavirus commonly affects animals, rarely humans. So it’s really unusual for this kind of virus to evolve and spread from animals to humans. Unfortunately, this is exactly what’s happened.

The spread of the coronavirus is similar to the Middle East Respiratory Syndrome coronavirus (MERS-CoV) and the severe acute respiratory syndrome coronavirus (SARS-CoV), both of which are known to cause more severe symptoms. As of January 27, the death toll in China from the deadly viral outbreak has reached more than 100, and more than 4,400 confirmed cases. China has implemented a lockdown across almost all cities in the country in an attempt to stop the spread of the virus. 

In Wuhan, the city where the first cases of the virus were reported, restrictions were tightened, with officials banning most vehicles from the roads. Reports showed that airports, train stations, and railway stations have all been shut since the lockdown began. The city’s streets have also been deserted for days, with residents mostly staying home. 

“Looking out of the window every day, I can see one or two cars and pedestrians on the street. The streets are relatively deserted. Now, at night, it is like a dead city. I look at the neighborhood and there are very few lights,” Wuhan resident Mr. Wang, who was speaking before the traffic ban was implemented, said. 

Unfortunately, the new virus has gradually spread across the world in the past days. Live Science, a science news website that features groundbreaking developments in science, space, technology, health, the environment, our culture, and history, reported that the virus has spread to various other countries such as, Thailand (8), Macau (6), Australia (5), Singapore (5), Taiwan (5), the US (5), Japan (4), Malaysia (4), South Korea (4), and even Hong Kong (8). What’s worse is that it may be much more contagious than initially thought.

An analysis by researcher Natsuko Imai and her colleagues at Imperial College London suggested that each person infected with the virus passes it to between 1.5 and 3.5 other people. Using the same estimates, Robin Thompson at the University of Oxford predicted there is a one-in-three chance that a person who brings the virus to the UK will pass it on to others in the country.

How AI Predicted the New Virus

It has been clear that the virus started in animals and then transmitted to humans. Reports showed that it first popped up in a local seafood and animal market in Wuhan. A study published in the Journal of Medical Virology suggested that the virus likely originated from snakes. According to the researchers, two snakes are common to southeastern China where the outbreak originated: the many-banded krait (Bungarus multicinctus) and the Chinese cobra (Naja atra). However, some experts opposed this, emphasizing the fact that it’s still unclear if the coronavirus can indeed infect snakes.

In a matter of days, the virus spread to thousands of people in many countries but mostly in China. The Centers for Disease Control and Prevention (CDC) reported that human coronaviruses are most commonly spread between an infected person and others through the air (viral particles from a cough or sneeze), close personal contact (touching or shaking hands), an object or surface with viral particles on it, and rarely from fecal contamination. But before all of this happened, artificial intelligence has predicted it. 

Normally, the World Health Organization and other agencies and governments across the world would be the ones sending out warnings to the public about the virus. But the world now has better information tools than it did decades ago. Through AI, Canadian company Bluedot predicted the outbreak ahead of other major organizations. Bluedot alerted its clients to the outbreak last December 31 with the help of an AI-driven algorithm that scours platforms like foreign news reports and animal and plant disease networks.

According to Quartz, an online site that aims to serve a new kind of business leader with bracingly creative and intelligent journalism that’s built for users first, Bluedot uses big data analytics to track and anticipate the spread of the world’s most dangerous infectious diseases. Aside from that, the company uses natural-language processing and machine-learning techniques to sift through global news reports, airline data, and reports of animal disease outbreaks. 

“What we have done is use natural language processing and machine learning to train this engine to recognize whether this is an outbreak of anthrax in Mongolia versus a reunion of the heavy metal band Anthrax,” Bluedot founder Kamran Khan said.

Khan added that the company didn’t use social media in predicting the spread of diseases since the data was too variable and messy to be of use. Instead, the researchers created a model from all of their sources to predict where infections begin and where infected people may travel next. Bluedot indeed correctly predicted that the Wuhan virus would spread to Taipei, Tokyo, Seoul, and Bangkok within a few days of its manifestation. 

According to Unite.AI, an online site that offers detailed analysis and news on the latest robotics and AI breakthroughs, the company’s human analysts double-checked the data and ensured that the model’s conclusions seem sound. “On the one hand, the world is rapidly changing, where diseases are emerging and spreading faster. On the other hand, we happen to have growing access to data we can use…to generate insights and spread them faster than the diseases spread themselves,” Khan said. 

It has been clear that the virus started in animals and then transmitted to humans. Reports showed that it first popped up in a local seafood and animal market in Wuhan / Photo by: SISTEMA 12 via Wikimedia Commons

 

How AI Can Fight the Coronavirus

It’s not unusual to see AI solving medical problems, thus, experts are hoping that it can also solve the new virus. While the role of AI in the healthcare industry is still in its early stages, it has already made several significant leaps. For instance, computer models can now accurately diagnose breast cancer from mammograms and even identify Alzheimer’s disease from brain scans.

Dr. Daniel Streicker, a life sciences researcher at Glasgow University, stated that AI may be able to help to combat the virus. “AI can collect data on human movement from things like airline records, traffic information...you can even imagine information collected through Google.” As of now, the potential of AI solving the outbreak is huge, considering the current studies that researchers are working on. For instance, Seattle-based Vulcan is currently using AI to better model Ebola outbreaks using movement data. 

According to The Telegraph, a national British daily broadsheet newspaper, the Harvard School of Public Health is also conducting a study in Bangladesh that aims to track people as they travel across the country and see whether that can predict where outbreaks of diseases using data from mobile phone networks. “The power of AI is that you can start to integrate all those data sources together. The challenge with newly emerging viruses such as the one in China is that we don’t have validated models that can tell us whether the predictions we have are meaningful,” Streicker said.