A Prospective Real-time Early Warning System to Anticipate Onsets and Peaks of Respiratory Diseases Outbreaks at the State Level in the U.S. A Transfer Learning Approach Leveraging Digital Traces.

Respiratory disease outbreaks burden U.S. healthcare systems with over one million hospital- izations annually, yet current surveillance systems lag 1-2 weeks behind real-time conditions, preventing timely intervention. We developed a machine learning early warning system that com- bines Google search trends with traditional epidemiological data using ensemble voting algorithms to predict the timing of outbreak onsets and peaks across multiple respiratory pathogens. The sys- tem applies anomaly detection and transfer learning to monitor syndromic Influenza-like illnesses (ILI), and hospitalizations caused by respiratory syncytial virus (RSV) or Influenza, simultane- ously, across all 50 US states. During operational real-time deployment from August 2024 through the 2024-2025 season, the system detected 98.0% of outbreak onsets with 5-week average lead time and 97.0% of peaks with 2-week average lead time, achieving positive predictive values that exceed 82%. This framework transforms reactive public health responses into proactive epidemic preparedness by reducing historical timing uncertainty from 10-20 weeks to consistent 2-6 week prediction windows, providing a scalable approach for monitoring both seasonal outbreaks and emerging respiratory threats.