Computational surveillance of pneumonia and influenza mortality in the United States using FluView uses epidemic thresholds to identify high mortality rates but is limited by statistical issues such as seasonality and autocorrelation. We used time series anomaly detection to improve recognition of high mortality rates. Results suggest that anomaly detection can complement mortality reporting.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7588519PMC
http://dx.doi.org/10.3201/eid2611.200706DOI Listing

Publication Analysis

Top Keywords

anomaly detection
12
surveillance pneumonia
8
pneumonia influenza
8
influenza mortality
8
high mortality
8
mortality rates
8
mortality
5
thresholds versus
4
versus anomaly
4
detection surveillance
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!