[ad_1]
The first international “bell” on Covid-19 was struck not by a man, but by a US computer with artificial intelligence.
On December 30, 2019, “smart” software on Boston Children’s Hospital’s HealthMap website, which uses artificial intelligence to monitor social media, news, internet searches, and other information that may be evidence of a new epidemic, was that It first identified a report of a new type of pneumonia in Wuhan, China. The program immediately informed recipients of an email list that seven people were in critical condition and assessed the severity of the situation on the “three” on a scale of five.
But people were not late anyway. Doctors in Taiwan have already informed US epidemiologist Marjorie Pollack in New York that the issue has begun to be discussed on the popular Chinese social networking site Weibo.
Polak, according to Science, recalled that something similar had happened in 2003 at the beginning of the outbreak of severe acute respiratory distress syndrome (SARS).
Nearly an hour after HealthMap’s automatic warning signal, Polak made a more detailed post on the Emerging Disease Surveillance Program, which reports to some 85,000 people worldwide. And so, the rest of the world began to focus their attention on something strange that was happening in China.
HealthMap’s “bell” shows the potential of artificial intelligence to control epidemics. As the Covid-19 pandemic continues to spread internationally, AI researchers are trying to “set up” automatic detection and warning systems that will search fleas for fleas in large volumes of data online to discover the first signs of a new . epidemic outbreak somewhere in the world.
Artificial intelligence is not going to replace traditional human epidemiological surveillance, at least not yet. “It just came to our attention then. I don’t think it can replace the evidence,” said epidemiologist Matthew Biggersstaf of the US Centers for Disease Control and Prevention (CDC). USA
Long before Covid-19, the US CDC. USA They had launched an annual competition in 2013 for the most accurate system to predict the severity and spread of a new flu wave in the United States. Dozens of suggestions are sent out every year, and about half of them are about machine learning algorithms (artificial intelligence), which refer to Google searches, Twitter tweets, Facebook posts, Wikipedia websites, etc., to find The first signs of an impending epidemic or outbreak.
Many of these research teams, which until now have been dealing with the flu, have now turned artificial intelligence tools in the direction of Covid-19. Its objective is to assess the current state (now ongoing) of the epidemic and to predict its course (prognosis).
It is not an easy job, nor is success guaranteed. Between 2009 and 2015, Google used a new “smart” tool, Google Flu Trends (which is now integrated into HealthMap), to search for users and detect the first signs, still invisible to scientists, of a new wave of flu. At first, the system worked well and predicted the flu two weeks before CDC.
But then he overestimated the spread of the flu, “terrorizing” epidemiologists for no reason. The main reason for the failure was that Google researchers did not “retrain” their system to account for changes in user behavior during their searches, so they misinterpreted p. Look for flu-related news as a sign of infection in the user himself.
Therefore, skeptics believe that artificial intelligence, which is constantly improving, will be better prepared and useful in the next pandemic. However, what is certain is that artificial intelligence became an instrument of epidemiology.
Source: RES-EIA
[ad_2]
