Credit score: Pixabay/CC0 Public Area
The best way to establish the following harmful virus earlier than it spreads amongst individuals is the central query in a brand new Remark in The Lancet Infectious Illnesses. In it, researchers focus on how AI, mixed with the One Well being method, can contribute to improved prediction and surveillance.
“Artificial intelligence cannot by itself prevent pandemics, but the technology can be a powerful supplement to the knowledge and methods we already use. The better we become at integrating data from humans, animals, and the environment, the better prepared we will be,” says Professor Frank Møller Aarestrup from the DTU Nationwide Meals Institute in Denmark, one of many authors of the Remark.
It was co-authored by Professor Marion Koopmans from the Erasmus Medical Heart within the Netherlands. She warns that after a illness begins spreading, it is rather laborious to convey beneath management.
“The interventions required are drastic—as we saw during COVID-19. That is why it is crucial to detect new pathogens before they gain a foothold,” says Koopmans, noting that after established, new ailments can change into persistent challenges, as COVID-19 has additionally proven.
The crew of authors, which additionally contains consultants from Eötvös Loránd College (ELTE) in Hungary, the College of Bologna in Italy, and the UK Animal and Plant Well being Company, speaks from their expertise as collaborators over years, specializing in One Well being approaches to rising illness preparedness within the VEO consortium—a European analysis initiative creating data-driven instruments to detect and monitor rising infectious ailments.
Pandemics typically originate in animals
The outbreaks of ailments akin to SARS-CoV-2, avian influenza, and mpox exhibit the problem of controlling new potential epidemics. Many pathogens originate in animals, however when and the place they are going to spill over into people is unpredictable.
The authors of the Remark spotlight how local weather change, intensive animal manufacturing, and human encroachment into pure habitats improve the chance of so-called spillover occasions—conditions during which pathogens cross from animals to people and, within the worst case, turn into epidemics.
Spillovers have been likened to sparks: most extinguish, however some ignite fires that unfold uncontrollably. With the ability to detect such spillovers as early as doable is a problem that the crew has been finding out utilizing large information approaches.
AI can reveal patterns in complicated datasets
Synthetic intelligence might help to investigate such datasets from numerous sources—akin to local weather, land use, animal manufacturing, transport, inhabitants actions, and socio-economics. When these datasets are mixed, AI can reveal patterns that will in any other case be tough to discern.
“AI can help us identify where in the world surveillance should be intensified geographically, but also in specific animal species, in wastewater, or in humans. In this way, we can prioritize efforts where the risks are greatest, so-called hotspots,” says Aarestrup.
Genetic indicators as early warning
As soon as such hotspots are predicted, metagenomic sequencing may be added as a catch-all method for detection of pathogens, each identified and new ones. Metagenomic sequencing is the evaluation of genetic materials—in samples from wastewater, air, meals, or the surroundings. It’s more and more used to offer perception into an enormous variety of identified and unknown microorganisms. Lots of the genetic fragments recognized aren’t but characterised.
“When we sequence a sample, we may find millions of genetic fragments. Most resemble something familiar and harmless, but we are left with thousands of unknowns. Here, AI can help detect patterns and point to what might be dangerous,” explains Aarestrup.
As soon as it’s clear there’s a potential pathogen, questions can come up about how harmful it’s. The potential for viruses from animals to contaminate people, unfold and trigger illness partly is embedded within the genetic code. AI-based instruments can be utilized to foretell how mutations may alter viral properties.
“We see huge developments in this area. AI-based protein models can provide an indication of what a mutation does to the structure of viruses, and how that then can be translated to risk of spread, or risk of severe disease. While challenging now, we see great potential for the use of AI to speed up risk assessment,” says Koopmans.
AI as a co-scientist—alternatives and limitations
The remark additionally describes early prototypes of so-called AI “co-scientists,” able to conducting a complete analysis cycle—from speculation era and literature evaluate to information evaluation and reporting.
“I envisage AI becoming a recognized competence at the table—on a par with different types of researchers. AI can deliver analyses or suggestions that we as scientists can evaluate. In that way, the technology becomes a supplement that can strengthen our decision-making processes,” says Aarestrup.
“That also implies that we need to learn what our future role is as teachers and supervisors. How do we make sure that the novel ways of working provide trustworthy output? Will we be able to recognize mistakes with advancements of AI models? We also need to go back to the classroom. Really exciting,” says Koopmans.
The authors conclude that synthetic intelligence presents intriguing prospects for enhancing pandemic preparedness. Nonetheless, it should be seen as a complement—not a substitute—to the classical surveillance and analysis approaches already in use.
Extra info:
Marion Koopmans et al, Synthetic intelligence and One Well being: potential for spillover prediction?, The Lancet Infectious Illnesses (2025). DOI: 10.1016/s1473-3099(25)00498-0
Offered by
Technical College of Denmark
Quotation:
AI can strengthen pandemic preparedness (2025, October 2)
retrieved 3 October 2025
from https://medicalxpress.com/information/2025-10-ai-pandemic-preparedness.html
This doc is topic to copyright. Aside from any honest dealing for the aim of personal research or analysis, no
half could also be reproduced with out the written permission. The content material is offered for info functions solely.
