Google's science AI ranks #1 in CDC evaluation (blog.google)

Google's AI has achieved a significant milestone by ranking first in a CDC evaluation for predicting flu-related hospitalizations during the 2025-26 season. This outcome, highlighted by the CDC's FluSight initiative, underscores the effectiveness of machine learning in public health forecasting. FluSight combines predictions from various sources, and Google's model emerged as the most accurate among 39 competitors, demonstrating an impressive alignment with actual hospital admission data. This achievement is crucial for the AI/ML community as it validates the potential of AI combined with human expertise to enhance disease forecasting capabilities globally. The forecasts were generated using an innovative tool called Empirical Research Assistance (ERA), which employs optimization algorithms across diverse scientific domains. By showcasing these methodologies in prestigious publications like “Nature,” Google is paving the way for broader applications of AI in healthcare, urging further exploration and development in predictive modeling for disease management and resource allocation.