The number of deaths from coronavirus in China has already increased to 54, and the number of infected has exceeded 1600. More than 12 cities are quarantined and the situation is not improving. All forces are thrown into the fight against a dangerous virus, including advanced technologies.
Artificial intelligence sounded the alarm on December 31
Artificial intelligence monitoring platform BlueDot predicted an outbreak of the 2019-nCov virus back on December 31st. The World Health Organization made an official statement only 9 days later. BlueDot was able to identify the danger by checking massive animal disease data with information on plane ticket sales. The platform also predicted an outbreak of the virus in Thailand and Japan. At the moment, the third case of the disease has been recorded in Japan, and in Thailand – the seventh..
The BlueDot algorithm does not use data from social media posts because it is too messy and unreliable. The algorithm turned out to be correct and even predicted the direction of the spread of the virus: Wuhan – Bangkok – Seoul ‒ Taipei – Tokyo.
How do mathematicians model infectious disease outbreaks?
BlueDot was launched in 2014 and has raised $ 9.4 million in venture funding. The company currently has 40 employees, including doctors and programmers. The job of the programmers is to develop natural language processing and machine learning techniques that will allow monitoring news in 65 languages, combined with processing airline ticket information and animal disease outbreaks. However, after automated data selection, it is the turn of human analysis, to which epidemiologists are connected..
BlueDot reports are sent to public health officials in over 12 countries, as well as airlines and hospitals where infected patients may end up.
History does not teach
The development of the BlueDot algorithm began in 2003, when future founder Kamran Khan was working as an infectious disease specialist at a hospital in Toronto during the SARS epidemic. Then the virus spread from Hong Kong to Toronto, where it caused the death of 44 people. Han is now experiencing déjà vu: «In 2003, I watched a virus take over a city and kill people. Let’s not do this again».
Twelve years ago, Google already launched a service that detected flu outbreaks using human searches. The 2009 swine flu pandemic was detected by the service 2 weeks before the official announcement by US health officials. However, Google constantly overestimated the spread of influenza, so the research results were released much later..
Daniel Straker, a science researcher at the University of Glasgow, argues that AI is better than other tools at collecting data on the movement of people from transport and airline traffic. Various private and public companies have been engaged in similar activities for a long time..
Seattle has used AI to qualitatively simulate Ebola outbreaks, while Harvard School of Public Health is using AI in Bangladesh to process mobile data to monitor travelers and predict where they might be..
Similar activities are carried out at Johns Hopkins University, where Twitter data is used to collect information about dangerous foci of the spread of the disease..
How to apply technology to detect coronavirus
Despite the clear benefits of AI in predicting disease outbreaks, Straker also notes that AI systems are still not accurate enough: «The problem with the coronavirus in China is that we don’t have proven models to tell us exactly whether our predictions make sense.». The next step in using AI should be to link diseases to specific individuals using social media and mobile data, but this step already raises ethical questions..
In China, the government uses AI to control the population and restrict access to certain services based on their «trust», which can easily turn into an automatic quarantine system. A tool for identifying sick people and preventing them from traveling would be very useful, but the problem is that the system can be wrong or discriminate against certain classes of people..
Dr. Straker argues that it is necessary to develop an AI that will be able to accurately simulate disease outbreaks at an individual level, and only then can this system be applied in practice..