How Much Will AI Help in the Next Pandemic?

It's been dubbed "Disease X" - the next global pandemic, which some experts predict is pretty much bound to happen. Over the next decade, according to certain forecasts, there's a one in four chance of another outbreak on the scale of Covid-19. It could be influenza or coronavirus - or something completely new. Covid-19, of course, infected and killed millions of people worldwide, so it's a frightening prospect.

Innovative AI Early Warning Systems

Researchers at the University of California, Irvine (UCI) and the University of California, Los Angeles (UCLA) are working on an AI-driven early warning system aimed at predicting potential pandemics by analyzing social media activity. This initiative is part of the US National Science Foundation's Predictive Intelligence for Pandemic Prevention grant programme, which focuses on the identification, modeling, prediction, tracking, and mitigation of future pandemics.

• The system utilizes a database of 2.3 billion US Twitter posts collected since 2015 to track public health trends.
• Under the leadership of Prof Chen Li, UCI's Department of Computer Science is advancing this research by analyzing real-time data from social media.
• The AI tool is designed to:
  1. Identify significant tweets related to public health.
  2. Train algorithms to recognize early signals of a potential pandemic.
  3. Forecast future outbreaks and assess the outcomes of various public health strategies.
• It aims to assist public health departments and hospitals in evaluating the effectiveness of interventions on virus transmission.

Despite its promise, the tool faces challenges, particularly related to data accessibility. For instance, the reliance on X, previously known as Twitter, raises concerns in regions where this platform is not available. Prof Chen acknowledges that data availability beyond the US is limited, and the team is exploring ways to address potential biases as they expand their efforts globally.

Advanced Variant Prediction with EVEScape

Another noteworthy AI tool under development is EVEScape, created collaboratively by Harvard Medical School and the University of Oxford. This tool forecasts new variants of the coronavirus and provides a bimonthly ranking of emerging variants.

• EVEScape has demonstrated its capability to accurately predict adaptations in other viruses, including HIV and influenza.
• Nikki Thadani, a former postdoctoral research fellow involved in its development, notes that its early use in a pandemic could benefit:
  1. Vaccine developers.
  2. Researchers working on therapeutic options, such as antibodies.

AI in Antibody Discovery

AstraZeneca's vice president of data science and AI R&D, Jim Wetherall, reveals that the company employs AI to enhance the efficiency of new antibody discovery, crucial for vaccine development. Antibodies play an essential role in the body's immune response to pathogens.

• AstraZeneca's approach allows the company to:
  1. Generate and screen a vast library of antibodies.
  2. Focus on the most promising candidates for laboratory testing.
• This process significantly reduces the timeline for identifying viable antibody leads from three months to just three days.
• Such advancements are vital for pandemic readiness, as the rapid mutation of viruses necessitates quicker identification of targets.

Leveraging AI for Epidemic Readiness

The Coalition for Epidemic Preparedness Innovations (CEPI), headquartered in Oslo and a funder of EVEScape, views AI as instrumental in enhancing preparedness and response strategies for epidemics and pandemics. Dr. In-Kyu Yoon, director of programmes and innovative technology at CEPI, emphasizes the importance of comprehensive readiness.

• He stresses the role of AI in accelerating the preparation process, but also notes the need for further development in the field.
• Dr. Yoon cautions that AI's effectiveness is directly tied to the quality of input data, asserting that appropriate application is essential to augment pandemic preparedness.

At the World Health Organization (WHO), Dr. Philip AbdelMalik underscores the necessity of human involvement in maximizing the potential of AI. He identifies AI's ability to monitor discussions around specific symptoms and detect emerging threats before formal government announcements.

• Despite recognizing AI's benefits, he highlights several challenges:
  1. AI cannot make decisions independently.
  2. Ethical concerns regarding AI use and equitable representation must be addressed.
• Dr. AbdelMalik warns against relying on flawed data, reiterating the adage, "garbage in, garbage out."

Conclusion

Overall, experts believe we’re in a better position for the next pandemic, partly because of the progress made in AI. “I think this pandemic was kind of a wake-up call to a lot of people who think about this space,” says Nikki Thadani. “Our model [AI tool EVEScape], and a lot of other efforts to really refine how we think about epidemiology, and how we think about leveraging the sort of data that you can have before a pandemic, and then integrating it with the data that's coming in through a pandemic, that does make me feel better about our ability to handle pandemics in the future.”

But, she says, there's a long way to go both on more of the fundamental biology and modelling she has worked in, but in epidemiology and public health more broadly, to help make us more prepared for future pandemics. “We're much better off now than we were three years ago,” says Dr. AbdelMalik. “However, there’s something more important than technology to help us when the next pandemic hits, and that’s trust. Technology to me is not our limiting factor. I think we really have to work on relationships, on information sharing and building trust. We keep saying that, everybody's saying that, but are we actually doing it?”