Ensemble forecasting for disease outbreak detection

Authors:
Thomas H. Lotze;Galit Shmueli
Affiliations:
University of Maryland, College Park, MD;University of Maryland, College Park, MD
Venue:
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 3
Year:
2008

Citing 0
Cited 1

Interoperability and information brokers in public safety: an approach toward seamless emergency communications

Journal of Theoretical and Applied Electronic Commerce Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe a method to improve detection of disease outbreaks in pre-diagnostic time series data. The method uses multiple forecasters and learns the linear combination to minimize the expected squared error of the next day's forecast. This combination adaptively changes over time. This adaptive ensemble combination is used to generate a disease alert score for each day, using a separate multiday combination method learned from examples of different disease outbreak patterns. These scores are used to generate an alert for the epidemiologist practitioner. Several variants are also proposed and compared. Results from the International Society for Disease Surveillance (ISDS) technical contest are given, evaluating this method on three syndromic series with representative outbreaks.