30-01-2020 5:19 am Published by Nederland.ai Leave your thoughts

artificial intelligence will not stop the new coronavirus or replace the role of expert epidemiologists. But for the first time in a global outbreak, it is becoming a useful tool in efforts to monitor and respond to the crisis, according to health data specialists.

In previous outbreaks, AI offered only limited value, as there was a shortage of data needed to provide updates quickly. But in recent days, millions of messages about the coronavirus on social media and news sites have allowed algorithms to generate near-real-time information for public health officials to track its spread.

“The field has evolved dramatically,” said John Brownstein, a computational epidemiologist at Boston Children's Hospital, who operates a public health surveillance site called healthmap.org that uses AI to extract data from government reports, social media, news sites, and analyze other sources.

“During SARS, there was not a huge amount of information coming from China,” he said, referring to a 2003 outbreak of a previous corona virus that came from China, infecting more than 8,000 people and killing nearly 800 people. “Now we are constantly busy with the news and social media.”

Brownstein emphasized that his AI is not intended to replace the information collection of public health leaders, but to complement their efforts by collecting and filtering information to help them make decisions in rapidly changing situations.

“We use machine learning to scrape, classify, mark and filter all information – and then push that information to our colleagues at the WHO who look at this information all day and make assessments,” said Brownstein. “There is still the challenge of parsing whether some of that information makes sense or not.”

These AI surveillance tools have been available in public health for over a decade, but recent advances in machine learning, combined with greater data availability, make them much more powerful. They also enable applications beyond basic surveillance to help officials more accurately predict how far and how quickly outbreaks will spread and what types of people are most likely to be affected.

“Machine learning is very good at identifying patterns in the data, such as risk factors that could identify zip codes or cohorts of people associated with the virus,” said Don Woodlock, a vice president at InterSystems, a global supplier. electronic health reports that help suppliers in China analyze data on coronavirus patients.

As several treatments are being tried out, he added, “we can also use machine learning to determine what might work for the virus.”

It's too early in the outbreak to do that kind of analysis, but AI tools can help accelerate that investigation as more data becomes available. The true impact of AI in response to the coronavirus outbreak is likely to become known in a few years.

Brownstein said efforts to harness the power of AI to predict the course of the disease – and the magnitude of its impact – are unfolding at breakneck speed. “Groups across the country are developing models for the spread (of coronavirus) domestically and internationally,” he said, adding that healthmap.org is partnering with a Bostonse startup called Buoy Health to build a symptom checker to assess the symptoms of coronavirus that distinguish it from the seasonal flu.

That promises to be a huge challenge for public health officials in the coming months as they work to allocate resources to contain the virus and manage a possible influx of cases to emergency rooms. “The more we focus our intervention efforts, identify the cases as quickly as possible and quarantine those cases, the more likely we are to mitigate the global impact of this virus,” said Brownstein.

Tags: , , , , ,

Leave a Reply

Your email address will not be published.

4 × four =

The maximum upload file size: 256 MB. You can upload: image, audio, video, document, spreadsheet, interactive, text, archive, code, other. Links to YouTube, Facebook, Twitter and other services inserted in the comment text will be automatically embedded. Drop file here