How AI is Tracking the Outbreak of the Coronavirus
What is the Coronavirus?
The World Health Organisation (WHO) identified a new type of virus called the Coronavirus (2019-nCoV) which can be fatal. This virus is a novel coronavirus, meaning it is a new form of the coronavirus. Other strains of the coronavirus include severe acute respiratory syndrome (SARS) and Middle East respiratory syndrome (MERS).
The human cases of the virus were first identified in early 2020, after a December 2019 outbreak in Wuhan, China with the virus thought to have originated from seafood and a multitude of cases connected to the Huanan seafood wholesale market.
Symptoms can show up anywhere from 2 to 14 days after exposure. Symptoms include:
Fever
Cough
Shortness of breath
Cases have been confirmed in over 20 countries some of which are: Japan, Thailand, Germany and UK.
The role of Artificial Intelligence
An AI-powered stimulation run by a technology executive suggests that the Coronavirus could infect as many as 2.5 billion people within 45 days and kill as many as 52.9 million of them which doctors say is not credible. Fortunately, however, conditions of infection and detection are changing, which in turn changes incredibly important factors that the AI isn’t aware of.
And that probably means that we’re safer than we think.
Probably being the operative word.
A new Coronavirus site that tracks Coronavirus infections globally says that we are currently at 45,204 infected, 1116 dead and 5085 recovered.
This resulted in James Ross, co-founder of fintech startup HedgeChatter to construct a model that estimated the total global reach of the Coronavirus.
I started with day over day growth. [I then] took that data and dumped it into an AI neural net using a RNN (recurrent neural network) model and ran the simulation ten million times. That output dictated the forecast for the following day. Once the following day’s output was published, I grabbed that data, added it to the training data, and re-ran ten million times.
The results so far successfully predicted the following day’s publicly released numbers within 3 percent.

Coronavirus predictions via a neural net, assuming conditions don’t change. Note: Doctors say that the conditions will change and are changing. Image Credit: Google
From almost 50,000 infections and 1,000 deaths after week to 208,000 and almost 4,400 deaths, the numbers keep growing as each infected person in turn infects another.
In 30 days, the model suggests that on average, around 2 million people may die and in a further 15 days, the death toll skyrockets.
Another artificial intelligence model known as BlueDot which uses machine learning and natural language processing methods can detect about 100,000 websites in 65 different languages from all over the world. The AI algorithms are trained in picking up news on communicable diseases from official local news channels, web forums and government and NGO communications. BlueDot scans this information every 15 minutes, 24 hours a day, every day of the year.
BlueDot is helping its clients like public health workers and airlines “anticipate rather than react,” according to Dr Kamran Khan, an infectious disease physician and founder and chief executive of BlueDot.
I think it could reach that [level of SARS], but not more. With all this attention and quarantine, and we have the experience of SARS so we know the public health measures – quarantine, social distance, hand washing – that should knock it on the head.
Although most clinicians only receive a day or two of tropical medicine training in school, their access to information as it is occurring to this day has never been better. BlueDot is helping them to “think global but act local.” But they have their work cut out.
Dr Khan stated that it was easy adage and far more difficult to operationalise.
Progress, he feels, is to be certain.