Could AI Help Prevent Future Epidemics?

A new study suggests that ChatGPT could be used to prevent future epidemics. AP
A new study suggests that ChatGPT could be used to prevent future epidemics. AP
TT

Could AI Help Prevent Future Epidemics?

A new study suggests that ChatGPT could be used to prevent future epidemics. AP
A new study suggests that ChatGPT could be used to prevent future epidemics. AP

A new study suggests that ChatGPT could be used to prevent future epidemics. For the study, researchers developed a model that simulates the spread of an illness similar to Covid-19.

According to the Daily Beast newspaper, the fake model developed by a team of researchers at Virginia Tech, was a Covid-like deadly airborne pathogen called the “Catasat virus”, causing symptoms that range from a light cough at best, to a fever and moderate cough at worst.

For their model, the researchers created 100 different personas with names, ages, personality traits, all living in the fictional town of Dewberry Hollow.

ChatGPT predicted the behaviors of those personas after the outbreak of the virus in three different experiments. In the first, the personas were given no additional health-related information like how much the virus is spreading in the town and how Catasat was affecting them. In the second, the personas were given information about their own health—allowing them the ability to self-quarantine if it chose to do so. In the third, the personas were given information about their own health and the town’s growing number of cases.

The first experiment resulted in the epidemic spreading until nearly every citizen of Dewberry Hollow was infected. However, once the personas were informed of their own health situation in the second experiment, there was a sharp decline in generative agents leaving their house and number of overall Catasat cases.

Armed with the full gamut of information and context about the virus, though, the generative agents in the third experiment were able to reduce the number of cases and bend the curve much more quickly than the previous experiments.

“We coupled an epidemic model with ChatGPT, in a unique and innovative way to predict human behaviors during epidemics,” said Ross Williams, a doctoral student in industrial and systems engineering at Virginia Tech.

“We think generative AI has the potential to provide us with synthetic data on human behavior so policy makers can make more informed choices,” Williams added.

According to the team, their findings indicate that AI could significantly help prevent future epidemics by providing a fairly accurate picture of how we’d respond to a potential disease outbreak.



Blogs to Bluesky: Social Media Shifts Responses after 2004 Tsunami

Teuku Hafid Hududillah, 28, an Indonesia's Meteorology, Climatology and Geophysics Agency (BMKG) officer, shows the seismograph system that recorded the 9.1 magnitude quake on the 2004 Indian Ocean earthquake and tsunami, at the monitoring station in Aceh Besar, Aceh, Indonesia, December 23, 2024. (Reuters)
Teuku Hafid Hududillah, 28, an Indonesia's Meteorology, Climatology and Geophysics Agency (BMKG) officer, shows the seismograph system that recorded the 9.1 magnitude quake on the 2004 Indian Ocean earthquake and tsunami, at the monitoring station in Aceh Besar, Aceh, Indonesia, December 23, 2024. (Reuters)
TT

Blogs to Bluesky: Social Media Shifts Responses after 2004 Tsunami

Teuku Hafid Hududillah, 28, an Indonesia's Meteorology, Climatology and Geophysics Agency (BMKG) officer, shows the seismograph system that recorded the 9.1 magnitude quake on the 2004 Indian Ocean earthquake and tsunami, at the monitoring station in Aceh Besar, Aceh, Indonesia, December 23, 2024. (Reuters)
Teuku Hafid Hududillah, 28, an Indonesia's Meteorology, Climatology and Geophysics Agency (BMKG) officer, shows the seismograph system that recorded the 9.1 magnitude quake on the 2004 Indian Ocean earthquake and tsunami, at the monitoring station in Aceh Besar, Aceh, Indonesia, December 23, 2024. (Reuters)

The world's deadliest tsunami hit nations around the Indian Ocean two decades ago before social media platforms flourished, but they have since transformed how we understand and respond to disasters -- from finding the missing to swift crowdfunding.

When a 9.1-magnitude quake caused a tsunami that smashed into coastal areas on December 26, 2004, killing more than 220,000 people, broadcasters, newspapers and wire agencies were the main media bringing news of the calamity to the world.

Yet in some places, the sheer scale took days to emerge.

Survivor Mark Oberle was holidaying in Thailand's Phuket when the giant waves hit Patong beach, and penned a blog post to fend off questions from family, friends and strangers in the days after the disaster.

"The first hints of the extent were from European visitors who got text messages from friends back home," said Oberle, adding people initially thought the quake was local and small, when its epicenter was actually near western Indonesia, hundreds of miles away.

"I wrote the blog because there were so many friends and family who wanted to know more. Plus, I was getting many queries from strangers. People were desperate for good news tales," said the US-based physician, who helped the injured.

The blog included images of cars ploughed into hotels, water-filled roads and locals fleeing on scooters because rumors produced "a stampede from the beach to higher ground".

Bloggers were named "People of the Year" by ABC News in 2004 because of the intimacy of first-hand accounts like those published in the days following the tsunami.

But today billions can follow major events in real-time on social media, enabling citizen journalism and assistance from afar, despite the real risk of rumor and misinformation.

During Spain's worst floods for decades in October, people voluntarily managed social media accounts to assist relatives trying to locate their missing loved ones.

After Türkiye's devastating earthquake last year, a 20-year-old student was rescued thanks to a post of his location while buried under the rubble.

- 'Fast picture' -

Two decades ago, the online social media landscape was vastly different.

Facebook was launched early in 2004 but was not yet widely used when the tsunami hit.

One of YouTube's founders reportedly said an inspiration for the platform's founding in early 2005 was an inability to find footage of the tsunami in its aftermath.

Some tsunami images were posted on photo site Flickr. But X, Instagram and Bluesky now allow for instant sharing.

Experts are clear that more information saves lives -- hours lapsed between the tremor's epicenter near Indonesia and the giant waves that crashed into Sri Lanka, India and Thailand's coastal areas.

Daniel Aldrich, a professor at Northeastern University, conducted interviews in India's Tamil Nadu where many said they had no idea what a tsunami was and had no warnings in 2004.

"In India alone nearly 6,000 people were taken by surprise and drowned in that event," he said.

Mobile apps and online accounts now quickly publicize information about hospitals, evacuation routes or shelters.

"Social media would have provided an immediate way to help locate other survivors and get information," said Jeffrey Blevins, head of journalism at the University of Cincinnati.

Oberle also noted that "knowing what help was locally available... would have provided a clearer perspective of what to expect in the days to come".

- Citizen science -

Beyond emergency rescue, social media clips can also be a boon to understanding a disaster's cause.

When giant waves crashed into Indonesia's Aceh province, footage remained largely confined to handheld camcorders capturing the carnage.

Fast forward to 2018, when a quake-tsunami hit Indonesia's Palu city, killing more than 4,000 people, enough videos were taken on smartphones that scientists researching seismic activity were later able to use the clips to reconstruct its path and time between waves.

The piece of citizen science in 2020 used amateur videos to conclude it happened so fast because of underwater landslides close to shore.

But it's not all good news.

Scholars warn that disinformation and rumors have also hindered disaster responses.

When Hurricane Helene struck North Carolina in September, relief efforts were disrupted as tensions between locals and emergency workers rose over unfounded rumors including a higher hidden death toll and diverted aid.

Workers faced reported threats from local armed militias.

"This information was so malicious that FEMA (Federal Emergency Management Agency) had to withdraw its teams from the area," said Aldrich.

"Social media has absolutely altered the field of disaster response for the good and the bad."

Yet perhaps the biggest change -- the free flow of information to the vulnerable -- has been beneficial.

Laura Kong of the Honolulu-based International Tsunami Information Center recently recalls how "2004 was such a tragedy".

"Because... we might have known there was an event, but we didn't have a way to tell anyone."