Population Health News

AI System to Leverage Social Media to Predict, Prevent Future Pandemics

Researchers at the University of California have received a $1 million grant to develop an AI-based early warning system that will examine social media posts to help predict future pandemics.

a graphic of people standing in the shape of a pie chart with 1/3 of the chart being pulled out for emphasis

Source: Getty Images

By Shania Kennedy

- Researchers at the University of California, Irvine (UCI) and the University of California, Los Angeles (UCLA) have received a $1 million grant from the National Science Foundation (NSF) to develop an artificial intelligence (AI)-based early warning system to predict future pandemics using Twitter posts.

According to the press release, the researchers note that infectious diseases “are sociobiological phenomena and leave both social and microbiological footprints,” and using both AI and public data, such as tweets, may help “monitor human society for signs of unusual activities that reflect the emergence of novel pathogens with pandemic potential.”

The project builds on earlier work by UCI and UCLA researchers, including a searchable database of 2.3 billion US Twitter posts collected since 2015, to monitor public health trends. Using the NSF grant, the researchers aim to analyze tweets and other data in the months leading up to the COVID-19 outbreak to determine if any patterns or trends could have provided an early warning of the virus.

“It’s a little like searching for a needle in a haystack,” said Andrew Noymer, PhD, an associate professor of population health and disease prevention at UCI, in the press release. “But the stakes are high, so it’s worth trying some different approaches.”

Much of the challenge lies in figuring out which tweets are meaningful and then using them to train algorithms to help pinpoint trends. For example, the press release notes that the word ‘fever’ appears in too many non-health-related contexts to be relevant, but ‘cough’ can yield useable results that provide insights into location, time period, and other variables that may indicate patterns.

However, the project has one major limitation — the coronavirus originated in China, where Twitter is officially blocked. The researchers are also leveraging data from news media stories, anonymous student health and absence statistics, biological data, and other public information resources, but to help address the lack of COVID-related Twitter data from China, they have turned to monkeypox as a test case.

“If we can’t find harbingers for outbreaks of COVID-19 or monkeypox, our concept is sledding uphill,” Noymer stated. “And even if we do find them, that doesn’t guarantee they’ll foreshadow the next pandemic. But the potential payoff makes the idea worth investigating.”

Chen Li, PhD, a computer science professor spearheading the project at UCI, compared the project to “weather forecasting, where advances in big data technologies and information analysis have resulted in better forecasts that are further out.”

Using this type of technology in a pandemic-focused early detection system could enable “faster responses in public health, medicine and government,” he added.

The project is part of the NSF Predictive Intelligence for Pandemic Prevention grant program, which funds “high-risk, high-payoff” research that “aims to identify, model, predict, track and mitigate the effects of future pandemics,” the press release states.

Researchers have launched the project amid growing interest in leveraging AI and machine learning (ML) to protect public health.

Last week, researchers from New York University’s Machine Learning for Good Laboratory (ML4G Lab), Carnegie Mellon University, and the New York City Department of Health and Mental Hygiene (NYC DOHMH) shared that they have developed an automated ML system designed to detect rare or previously unseen disease clusters that can pose a threat to public health.