Back

A framework for classifying disease trends applied to influenza-associated hospital admissions in the United States

Mathis, S. M.; Biggerstaff, M.; Budd, A.; O'Halloran, A.; Bozio, C.; Borchering, R. K.

2025-04-16 epidemiology
10.1101/2025.04.11.25324947 medRxiv
Show abstract

We built a framework for categorizing week-to-week increases or decreases in seasonal influenza hospitalizations aiding data interpretation in the context of past seasons. Using Influenza Hospitalization Surveillance Network (FluSurv-NET) data, we established thresholds for weekly hospitalization rate differences and applied them to the 2022/23 and 2023/24 influenza seasons from the National Healthcare Safety Network. While the number of weeks categorized as stable was consistent across seasons, more large increases and decreases were observed in 2022/23. This metric captures hospitalization rate changes and contextualizes the current season relative to past influenza trends, facilitating trend assessment.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.