Could AI Help Predict the Next Pandemic?
Artificial intelligence can monitor disease outbreaks and could help prepare us for future pandemics.
Complete the form below to unlock access to ALL audio articles.
The COVID-19 pandemic highlighted the speed at which infectious diseases can spread — and the importance of an equally agile and robust array of tools to predict, monitor and control their proliferation. New and long-standing artificial intelligence (AI) tools were deployed during the pandemic to help fill this role.
Lessons learned from this period have shown that AI can be successfully utilized in early-warning systems for infection, outbreak detection, epidemiological forecasting and resource allocation. With new pathogens of concern and new strains of old viruses a constant threat, building on these AI-powered tools and incorporating them into public health is a key priority.
This article outlines examples of where AI has been utilized to predict disease outbreaks and how AI models could help inform future strategies for controlling the spread of infectious diseases to prevent possible pandemics.
AI’s contribution to pandemic preparedness
In August 2024, the World Health Organization (WHO) updated its list of pathogens that could spark the next pandemic, which grew to include more than 30 pathogens. The microorganisms were selected based on available evidence showing them to be highly transmissible and virulent, with limited access to vaccines and treatments. While some pathogens on the list may never cause an epidemic, the growing number of pathogens of concern highlights the need for new tools to help predict and control the spread of infectious diseases.
Recognizing the utility of AI in preparing for future pandemics, the US Centers for Disease Control and Prevention (CDC) Center for Forecasting and Outbreak Analytics launched Insight Net in 2023. The US network hopes to transform the analytic capacities for infectious disease outbreaks by combining machine learning and AI with the best available technologies and academic research. Similarly, the WHO Hub for Pandemic and Epidemic Intelligence is working towards implementing AI in surveillance programs.
A key lesson from the COVID-19 pandemic was that effective preparedness relies on monitoring known pathogens and anticipating viral mutations that can evade host immune responses. To address this, researchers at Harvard Medical School (HMS) and the University of Oxford have developed an AI tool named EVEscape.
To build the tool, the researchers took their existing generative model EVE – which can predict mutations in viral proteins that won’t interfere with the virus’s function – and added biological and structural details about the virus. Together, this data allows EVEscape to predict the variants most likely to occur as a virus evolves.
In a study, published in the journal Nature, the researchers demonstrated that EVEscape is as accurate as high-throughput experimental scans at anticipating variations for SARS-CoV-2 and is generalizable to other viruses including influenza, HIV and understudied viruses with pandemic potential.
The researchers continue to utilize EVEscape to predict future variants of SARS-CoV-2 and publish a biweekly variant report. They are now working on broadening this work to include other pathogens with pandemic potential.
“We want to know if we can anticipate the variation in viruses and forecast new variants — because if we can, that’s going to be extremely important for designing vaccines and therapies,” said Debora Marks, professor of systems biology at the Blavatnik Institute at HMS.
Disease surveillance in disaster contexts
In addition to predicting how diseases may evolve, AI can also help track and contain epidemics. Early-warning systems for disease surveillance have greatly benefited from incorporating AI algorithms that can analyze text for signals of infectious disease events with high accuracy and at unprecedented speeds.
A study, published in the journal Emerging Infectious Disease, utilized open-source data from EPIWATCH – an AI early-warning system – to analyze the effects of the Russia-Ukraine war on infectious disease epidemiology.
Conflict situations can increase the risk of epidemics, and disruptions to public health surveillance create extra challenges in tracking them. In the study, researchers demonstrated the value of using AI-powered open-source intelligence to gather information about unfolding epidemics in a conflict zone where formal surveillance was reduced.
The researchers analyzed patterns of infectious diseases and syndromes before (November 1, 2021–February 23, 2022) and during (February 24–July 31, 2022) the conflict. Case numbers for the most frequently reported diseases were compared with numbers from formal sources.
The researchers found increases in overall infectious disease reports. In addition, compared with formal surveillance, the researchers were able to extract more complete case data for the eight most reported infectious diseases.
While the study has some limitations, such as the lack of data from smaller regions in Ukraine, it demonstrates how open-source health intelligence systems can be valuable for making real-time public health decisions during disasters.
Informing strategies against future pandemics
AI-driven approaches complement human-curated ones, providing new insights to help health professionals make more informed decisions during outbreaks. A team of engineers at the University of Houston recently developed an AI tool to identify hotspots of infection linked to air traffic. This model could help policymakers decide on air traffic controls during pandemics. The study was published in the journal Scientific Reports.
To explore how air traffic impacts the spread of disease, the researchers developed a graph neural network (GNN)-based framework called Dynamic Weighted GraphSAGE. “The uniqueness of this work is that the graph can accommodate dynamic weights, reflecting aviation pattern changes over time. We also used directed graphs to accurately capture the directionality and asymmetry of flight traffic between regions,” lead researcher and associate professor at the University of Houston Dr. Hien Van Nguyen, told Technology Networks. “These unique features make our GNN very suitable for modeling the spatial and temporal changes in air traffic, and from this, we can predict the spreading of infectious disease cases via air travel.”
The researcher’s analysis found that air traffic significantly drove COVID-19 infection during the pandemic. By performing sensitivity analysis on the model, the researchers could observe changes in the spreading patterns. From this analysis, they found that Western Europe, the Middle East and North America were regions with the highest sensitivity to these changes and therefore concluded they had a disproportionately large impact on the spread of the virus.
“This highlights the importance of looking at air travel patterns to potentially curb the spreading of airborne diseases,” said Nguyen. “In the past, governments have tried this, but I believe our model provides a more systematic, data-driven way to decide how much air traffic we want to cut and to predict how that would likely impact the spreading pattern of disease.”
“The model we’ve developed can be used as a data-driven tool for policymakers to evaluate the effectiveness of travel restrictions on the spread of airborne diseases,” said Nguyen.
The next steps for this research will be to verify the model on other types of infectious diseases with different spreading rates and other properties that might impact spreading predictions. “Various infectious diseases can be applicable here because our framework is not restricted. It has no assumptions related to COVID-19, and we can apply this model to influenza or any airborne disease influenced by human travel migration patterns,” explained Nguyen. “In the future, we could potentially use this framework for early warning, not just predicting the spread of a disease but to detect spikes and unusual patterns.”
Insights from the study were used to search through restriction policies on air traffic for controlling the pandemic, which identified policies and strategies that reduced predicted global COVID cases effectively with lesser air traffic reductions.
Nguyen concluded, “We can apply the tool for other interventions such as where to increase health infrastructure, and where to deploy resources to anticipate the increased number of patients. So, in addition to helping with decisions on air travel, we can identify high-impact regions and quantify the potential outcomes of strategies aimed at helping these regions.”
Future outlooks for AI in infectious disease monitoring
AI has become an established technology in many areas of medicine. Emerging technologies such as quantum computing, biosensors, augmented intelligence and large language models are all predicted to play an increasing role in infectious disease surveillance in the future.
While AI continues to improve surveillance infrastructures, limitations such as the prevalence of databases that underrepresent select populations and the potential for predictions that aren’t generalizable still need to be overcome. In addition, data privacy is a significant concern regarding using AI in infectious disease surveillance. As models incorporate data streams from sources such as wearable health technology, connected health devices and smartphones that may be linked to open social media, approaches to preserve privacy will be a priority.
AI will likely continue to improve disease surveillance infrastructure, but future pandemics remain a possibility. Experiences with AI during the COVID-19 pandemic have shown its utility in this space, however, it still cannot replace the collective intelligence required to prevent emerging infectious diseases. Pandemic preparedness continues to require the combined efforts of collaborative surveillance networks.
