The Cary Institute hopes machine learning could help identify future outbreaks

The Cary Institute hopes machine learning could help identify future outbreaks

The Cary Institute of Ecosystem Studies in Dutchess County recently hosted a virtual conference on using artificial intelligence to predict the next pandemic.

Zoonotic diseases like coronaviruses, Ebola, Zika and Monkeypox spread from wild and domestic animals to humans. Researchers say millions of people die every year as a result of such outbreaks, which are increasing in frequency.

The Cary Institute held a conference featuring disease ecologist Dr. Barbara Han in conversation with Cary President Dr. Joshua Ginsberg. Han has led research on global patterns of zoonotic diseases in mammals and currently focuses on ecology, informatics and global public health. Han says COVID has transformed society.

“Where are we at right now? We’re on Zoom, we would normally do this in person, right? An auditorium full of unmasked people,” Han said. “Yeah, disease ecology, I think that’s amazingly, really front and center now. It’s part of the national dialogue in a way that I’ve never seen before in my career.”

Han also points out that zoonotic diseases are emerging in humans at a faster rate than in the past.

“Even after correcting things like the advent of the internet, where disease information spreads faster and becomes available much more readily, even after controlling that, the incidence of those diseases and the emergence events increased since the 1980s,” Han said. “So I think it’s a real phenomenon.”

What if we could predict pathogen spillovers and intervene before they evolve into new variants that harm humans, other animals or ecosystems? That’s what Han studies, using artificial intelligence machine programs to look for patterns and make predictions.

“Train an algorithm to distinguish, you know, the characteristics of something that’s carrying the disease versus something that’s not,” Han said. “So it’s a very simple method that was the very first way we’re trying to apply machine learning to this question about the spread of infectious diseases and what species should we be concerned about? Are there any ways to do that, what the algorithms can suggest about those species that will then allow us to go out and test hypotheses in an intelligent way.

Han’s calculations identified the mammalian species most likely to harbor COVID-19 and transmit variants to humans. She is helping to advance an infectious disease surveillance system with real-time data streams to determine when, where and why zoonotic diseases pass from animals to humans. Han notes that computer programs depend on human actions.

“But we’re still really dependent on those monitoring efforts, like people going into the field and catching bats and testing bats,” Han said. “It’s really incredibly hard work. And these things still remain underfunded despite, despite the obvious need for these things. So I think machine learning, it’s really about the data, the quality of the data that you have, and you can’t expect to go anywhere with machine learning and AI, it’s a magic wand or something without the hard work of the people who collect and curate and put that data available to the world.

Han says that as interactions between people and wildlife increase, the likelihood of pandemics and the spread of disease also increases.

“The system we probably know best is Lyme disease, because the story is that by reducing biodiversity, you leave behind species that are quite successful at amplifying the Borrelia pathogen and allowing ticks that are responsible for feeding mostly on humans, until they persist in large numbers,” Han said. “And so it’s been studied for decades, the ecological data is so strong, it’s the studies that inspired me to get into the field that I’m in now. But there are other systems where the answers to This question are quite complicated, aren’t they? Because in some cases you have higher biodiversity. And that means you might have more individuals of a species that is actually super competent for an agent. pathogen. And then you have to think about the interactions between species? And how do those interactions change when a human, when development comes in and changes the interactions.

Han says society cannot let its guard down when it comes to communicable diseases.

“Everyone says ‘well, things are going to be different now that we’ve had COVID. It is a learning experience. And is it going to be a learning experience,” Han asked.

“Well, monkeypox wouldn’t suggest we learned much,” Ginsberg replied.

“I know, no,” Han said. “And are people going to say we’ve had a pandemic next year? Like, are people going to say, ‘ah, we’ve been through this, whatever’ now it’s like, are we going to attract attention? And we know what to do now like, Hong Kong was so good at it, but SARS two after SARS one, okay, they knew masks worked. And it wasn’t a social taboo to wearing a mask. It was just something you were doing. And that’s what worries me the most, I think. The technology that I’m so optimistic about that collaborations with computer scientists are incredible. And with virologists , I mean, I think all the motivations are there. It’s the complacency in all of this, in our inability to kind of map that to social behavior and how to communicate well. That’s what m prevents you from sleeping at night.

Han believes that education and information dissemination are essential whenever people are faced with a new pathogen.

#Cary #Institute #hopes #machine #learning #identify #future #outbreaks

Leave a Comment

Your email address will not be published. Required fields are marked *