Artificial intelligence for modelling infectious disease epidemics

Kraemer, Moritz U G; Tsui, L.-H; Chang, Serina Y; Lytras, Spyros; Khurana, Mark P; Vanderslott, Samantha; Bajaj, Sumali; Scheidwasser, Neil; Curran-Sebastian, Jacob Liam; Semenova, Elizaveta; Zhang, Mengyan; Unwin, H. Juliette T.; Watson, Oliver J; Mills, Cathal; Dasgupta, Abhishek; Ferretti, Luca; Scarpino, Samuel V; Koua, Etien; Morgan, Oliver; Tegally, Houriiyah; Paquet, Ulrich; Moutsianas, Loukas; Fraser, Christophe; Ferguson, Neil M; Topol, Eric J; Duchêne, David A; Stadler, Tanja; Kingori, Patricia; Parker, Michael J; Dominici, Francesca; Shadbolt, Nigel; Suchard, Marc A; Ratmann, Oliver; Flaxman, Seth; Holmes, Edward C; Gomez-Rodriguez, Manuel; Schölkopf, Bernhard; Donnelly, Christl A; Pybus, Oliver G; Kraemer, Moritz U G; Tsui, L.-H; Chang, Serina Y; Bhatt, Samir

Abstract

Infectious disease threats to individual and public health are numerous, varied and frequently unexpected. Artificial intelligence (AI) and related technologies, which are already supporting human decision making in economics, medicine and social science, have the potential to transform the scope and power of infectious disease epidemiology. Here we consider the application to infectious disease modelling of AI systems that combine machine learning, computational statistics, information retrieval and data science. We first outline how recent advances in AI can accelerate breakthroughs in answering key epidemiological questions and we discuss specific AI methods that can be applied to routinely collected infectious disease surveillance data. Second, we elaborate on the social context of AI for infectious disease epidemiology, including issues such as explainability, safety, accountability and ethics. Finally, we summarize some limitations of AI applications in this field and provide recommendations for how infectious disease epidemiology can harness most effectively current and future developments in AI. AI 1 is transforming many aspects of contemporary science 2 and has the potential to similarly change the landscape of infectious disease epidemiology. AI can be defined as intelligent behaviour exhibited by machines and computers and has been an active area of research since the 1950s 3. Over the past decade, the focus of AI methods has shifted substantially from logic-based approaches 4 to those associated with deep learning 5. In this Perspective, we define AI and related data science approaches broadly and therefore include methods from machine learning (ML) 6 , probability theory 7 , numerical optimization 8 and new directions in scalable computation 9,10. Infectious disease epidemiology is the study of why infectious diseases emerge, how they transmit within and among populations, and of the strategies that can be used to prevent, control and mitigate their spread 11. Mathematical, computational and statistical modelling is an essential component of this interdisciplinary field, and quantitative models are used to inform public health policies and responses at local and global scales 11. Although much attention has been paid to the application of AI to problems in human health, such as patient diagnosis 12 , individual-level disease risk prediction 13 and decision support for doctors 14 , there have been fewer demonstrations of the

Citation

Kraemer, M. U. G., Tsui, L.-H., Chang, S. Y., Lytras, S., Khurana, M. P., Vanderslott, S., Bajaj, S., Scheidwasser, N., Curran-Sebastian, J. L., Semenova, E., Zhang, M., Unwin, H. J. T., Watson, O. J., Mills, C., Dasgupta, A., Ferretti, L., Scarpino, S. V., Koua, E., Morgan, O., Tegally, H., …Bhatt, S. (2025). Artificial intelligence for modelling infectious disease epidemics. Nature, 638(8051), 623-635. https://doi.org/10.1038/s41586-024-08564-w

• Journal Article Type: Article
• Acceptance Date: Dec 20, 2024
• Online Publication Date: Feb 19, 2025
• Publication Date: Feb 20, 2025
• Deposit Date: Apr 2, 2025
• Publicly Available Date: Aug 20, 2025
• Journal: Nature
• Print ISSN: 0028-0836
• Electronic ISSN: 1476-4687
• Publisher: Nature Research
• Peer Reviewed: Not Peer Reviewed
• Volume: 638
• Issue: 8051
• Pages: 623-635
• DOI: https://doi.org/10.1038/s41586-024-08564-w
• Additional Information: Received: 8 July 2024; Accepted: 20 December 2024; First Online: 19 February 2025; : S. Bhatt is a paid member of the Academic Council of the Schmidt Science Fellows programme outside the scope of this work. This affiliation is unrelated to the submitted work, and the programme does not stand to benefit from this publication. M.A.S. receives grants from the US National Institutes of Health within the scope of this work, and grants and contracts from the US Food and Drug Administration, the US Department of Veterans Affairs, and Johnson and Johnson, all outside the scope of this work. C.F. is a member of two committees that advise the UK Department of Health on emerging epidemics, namely NERVTAG and SPI-M. The other authors declare no competing interests.