Google AI model tops CDC review for predicting flu hospital admissions
The CDC’s review puts Google’s model at the front of flu demand forecasting for the 2025-26 season.
The CDC’s end-of-season review named a Google AI flu forecasting model as the strongest predictor of U.S. flu-related hospital admissions for the 2025-26 season. That matters for teams building public-health or operations software because the agency uses FluSight forecasts to estimate near-term hospital demand across states. The review covered 39 eligible models, and Google’s model matched observed admissions most closely. Google said the model was built with Empirical Research Assistance, an AI system for generating optimization algorithms, and that ERA’s underlying technology is now available to trusted testers.
Why it matters
For public-health planners, the result shows which model best tracked real hospital admissions in a field of 39. Because the CDC uses FluSight forecasts to estimate near-term hospital demand across states, the ranking points to where decision-makers may place more weight when they are trying to gauge pressure on hospitals.
Keep or strike?
Does this story matter, or is it hype? Mark it before you see what everyone else did.
Sources
- Google Blog