Early detection of norovirus outbreak using machine learning methods in South Korea

Sieun Lee, Eunhae Cho, Geunsoo Jang, Sangil Kim and Giphil Cho

PLOS ONE, 2022, vol. 17, issue 11, 1-12

Abstract: Background: The norovirus is a major cause of acute gastroenteritis at all ages but particularly has a high chance of affecting children under the age of five. Given that the outbreak of norovirus in Korea is seasonal, it is important to try and predict the start and end of norovirus outbreaks. Methods: We predicted weekly norovirus warnings using six machine learning algorithms using test data from 2017 to 2018 and training data from 2009 to 2016. In addition, we proposed a novel method for the early detection of norovirus using a calculated norovirus risk index. Further, feature importance was calculated to evaluate the contribution of the estimated weekly norovirus warnings. Results: The long short-term memory machine learning (LSTM) algorithm proved to be the best algorithm for predicting weekly norovirus warnings, with 97.2% and 92.5% accuracy in the training and test data, respectively. The LSTM algorithm predicted the observed start and end weeks of the early detection of norovirus within a 3-week range. Conclusions: The results of this study show that early detection can provide important insights for the preparation and control of norovirus outbreaks by the government. Our method provides indicators of high-risk weeks. In particular, last norovirus detection rate, minimum temperature, and day length, play critical roles in estimating weekly norovirus warnings.

Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0277671 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 77671&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0277671

DOI: 10.1371/journal.pone.0277671

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().