Ensemble Forecasting for Disease Outbreak Detection
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.
Cite
Text
Lotze and Shmueli. "Ensemble Forecasting for Disease Outbreak Detection." AAAI Conference on Artificial Intelligence, 2008.Markdown
[Lotze and Shmueli. "Ensemble Forecasting for Disease Outbreak Detection." AAAI Conference on Artificial Intelligence, 2008.](https://mlanthology.org/aaai/2008/lotze2008aaai-ensemble/)BibTeX
@inproceedings{lotze2008aaai-ensemble,
title = {{Ensemble Forecasting for Disease Outbreak Detection}},
author = {Lotze, Thomas H. and Shmueli, Galit},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2008},
pages = {1470-1471},
url = {https://mlanthology.org/aaai/2008/lotze2008aaai-ensemble/}
}