A new study by a team of international scientists emphasizes the role of AI in better predicting and managing disease outbreaks, urging global collaboration to ensure ethical and effective deployment.
In a new study published in the journal Nature, a team of international scientists unveiled how advancements in artificial intelligence (AI) could revolutionize pandemic preparedness over the next five years. The research highlights that integrating AI into country response systems could save countless lives by predicting the location and trajectory of disease outbreaks more accurately.
The collaborative study, which followed the recent AI Action Summit, comes amid a growing global debate about AI investment and regulation. It underscores the need for enhanced cooperation among academia, government and industry to ensure the ethical use of AI in infectious disease research.
“In the next five years, AI has the potential to transform pandemic preparedness,” lead author Moritz Kraemer, an associate professor of computational and genomic epidemiology at the University of Oxford’s Pandemic Sciences Institute, said in a news release. “It will help us better anticipate where outbreaks will start and predict their trajectory, using terabytes of routinely collected climatic and socio-economic data.”
The study, authored by scientists from institutions worldwide, calls for a transparent environment where datasets and AI models are shared openly. It stresses the importance of safety, accountability and ethics in deploying AI for this crucial field.
While medical applications of AI have traditionally focused on individual patient care — enhancing diagnostics, precision medicine and clinical decision-making — this research explores AI’s potential impact on population health. The review shows that recent advancements in AI methodologies are excelling, even with limited data, breaking long-standing barriers.
Key opportunities for AI in pandemic preparedness outlined in the research include:
- Enhancing models of disease spread to improve robustness and accuracy
- Pinpointing high-transmission areas to allocate health care resources more efficiently
- Accelerating vaccine development by improving genetic data in disease surveillance
- Determining properties of new pathogens and predicting cross-species transmission likelihood
- Integrating population-level data with individual-level data from wearable technologies for better outbreak detection and monitoring.
“While AI has remarkable transformative potential for pandemic mitigation, it is dependent upon extensive worldwide collaboration and from comprehensive, continuous surveillance data inputs,” co-author Eric Topol, the founder and director of the Scripps Research Translational Institute, said in the news release.
The study not only highlights AI’s ability to anticipate disease spread and improve pandemic response but also discusses its limitations. The authors stress the importance of integrating human feedback into AI modeling workflows to overcome existing limitations, ensuring that AI does not operate in a vacuum.
“Infectious disease outbreaks remain a constant threat, but AI offers policymakers a powerful new set of tools to guide informed decisions on when and how to intervene,” added co-lead author Samir Bhatt, a professor of statistics and public health at Imperial College London and a professor of machine learning and public health at the University of Copenhagen.
The authors call for rigorous benchmarks to evaluate AI models and advocate for strong collaborations between government, society, industry and academia for sustainable development. They also voice concerns about the quality and representativeness of training data and the risks associated with black-box models in decision-making.
The research underlines a pivotal shift in how we approach pandemic preparedness, pointing to a future where AI can significantly enhance global health security.