Comparing early outbreak detection algorithms based on their optimized parameter values

Xiaoli Wang, Dajun Zeng, Holly Seale, Su Li, He Cheng, Rongsheng Luan, Xiong He, Xinghuo Pang, Xiangfeng Dou, Quanyi Wang

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Background: Many researchers have evaluated the performance of outbreak detection algorithms with recommended parameter values. However, the influence of parameter values on algorithm performance is often ignored. Methods: Based on reported case counts of bacillary dysentery from 2005 to 2007 in Beijing, semi-synthetic datasets containing outbreak signals were simulated to evaluate the performance of five outbreak detection algorithms. Parameters' values were optimized prior to the evaluation. Results: Differences in performances were observed as parameter values changed. Of the five algorithms, space-time permutation scan statistics had a specificity of 99.9% and a detection time of less than half a day. The exponential weighted moving average exhibited the shortest detection time of 0.1 day, while the modified C1, C2 and C3 exhibited a detection time of close to one day. Conclusion: The performance of these algorithms has a correlation to their parameter values, which may affect the performance evaluation.

Original languageEnglish (US)
Pages (from-to)97-103
Number of pages7
JournalJournal of Biomedical Informatics
Volume43
Issue number1
DOIs
StatePublished - Feb 2010
Externally publishedYes

Fingerprint

Disease Outbreaks
Bacillary Dysentery
Research Personnel
Statistics

Keywords

  • Evaluation
  • Outbreak detection algorithms
  • Outbreak simulation
  • Parameter values

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Comparing early outbreak detection algorithms based on their optimized parameter values. / Wang, Xiaoli; Zeng, Dajun; Seale, Holly; Li, Su; Cheng, He; Luan, Rongsheng; He, Xiong; Pang, Xinghuo; Dou, Xiangfeng; Wang, Quanyi.

In: Journal of Biomedical Informatics, Vol. 43, No. 1, 02.2010, p. 97-103.

Research output: Contribution to journalArticle

Wang, X, Zeng, D, Seale, H, Li, S, Cheng, H, Luan, R, He, X, Pang, X, Dou, X & Wang, Q 2010, 'Comparing early outbreak detection algorithms based on their optimized parameter values', Journal of Biomedical Informatics, vol. 43, no. 1, pp. 97-103. https://doi.org/10.1016/j.jbi.2009.08.003
Wang, Xiaoli ; Zeng, Dajun ; Seale, Holly ; Li, Su ; Cheng, He ; Luan, Rongsheng ; He, Xiong ; Pang, Xinghuo ; Dou, Xiangfeng ; Wang, Quanyi. / Comparing early outbreak detection algorithms based on their optimized parameter values. In: Journal of Biomedical Informatics. 2010 ; Vol. 43, No. 1. pp. 97-103.
@article{92adcdaba5e4410991733c2c3e4b05af,
title = "Comparing early outbreak detection algorithms based on their optimized parameter values",
abstract = "Background: Many researchers have evaluated the performance of outbreak detection algorithms with recommended parameter values. However, the influence of parameter values on algorithm performance is often ignored. Methods: Based on reported case counts of bacillary dysentery from 2005 to 2007 in Beijing, semi-synthetic datasets containing outbreak signals were simulated to evaluate the performance of five outbreak detection algorithms. Parameters' values were optimized prior to the evaluation. Results: Differences in performances were observed as parameter values changed. Of the five algorithms, space-time permutation scan statistics had a specificity of 99.9{\%} and a detection time of less than half a day. The exponential weighted moving average exhibited the shortest detection time of 0.1 day, while the modified C1, C2 and C3 exhibited a detection time of close to one day. Conclusion: The performance of these algorithms has a correlation to their parameter values, which may affect the performance evaluation.",
keywords = "Evaluation, Outbreak detection algorithms, Outbreak simulation, Parameter values",
author = "Xiaoli Wang and Dajun Zeng and Holly Seale and Su Li and He Cheng and Rongsheng Luan and Xiong He and Xinghuo Pang and Xiangfeng Dou and Quanyi Wang",
year = "2010",
month = "2",
doi = "10.1016/j.jbi.2009.08.003",
language = "English (US)",
volume = "43",
pages = "97--103",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",
number = "1",

}

TY - JOUR

T1 - Comparing early outbreak detection algorithms based on their optimized parameter values

AU - Wang, Xiaoli

AU - Zeng, Dajun

AU - Seale, Holly

AU - Li, Su

AU - Cheng, He

AU - Luan, Rongsheng

AU - He, Xiong

AU - Pang, Xinghuo

AU - Dou, Xiangfeng

AU - Wang, Quanyi

PY - 2010/2

Y1 - 2010/2

N2 - Background: Many researchers have evaluated the performance of outbreak detection algorithms with recommended parameter values. However, the influence of parameter values on algorithm performance is often ignored. Methods: Based on reported case counts of bacillary dysentery from 2005 to 2007 in Beijing, semi-synthetic datasets containing outbreak signals were simulated to evaluate the performance of five outbreak detection algorithms. Parameters' values were optimized prior to the evaluation. Results: Differences in performances were observed as parameter values changed. Of the five algorithms, space-time permutation scan statistics had a specificity of 99.9% and a detection time of less than half a day. The exponential weighted moving average exhibited the shortest detection time of 0.1 day, while the modified C1, C2 and C3 exhibited a detection time of close to one day. Conclusion: The performance of these algorithms has a correlation to their parameter values, which may affect the performance evaluation.

AB - Background: Many researchers have evaluated the performance of outbreak detection algorithms with recommended parameter values. However, the influence of parameter values on algorithm performance is often ignored. Methods: Based on reported case counts of bacillary dysentery from 2005 to 2007 in Beijing, semi-synthetic datasets containing outbreak signals were simulated to evaluate the performance of five outbreak detection algorithms. Parameters' values were optimized prior to the evaluation. Results: Differences in performances were observed as parameter values changed. Of the five algorithms, space-time permutation scan statistics had a specificity of 99.9% and a detection time of less than half a day. The exponential weighted moving average exhibited the shortest detection time of 0.1 day, while the modified C1, C2 and C3 exhibited a detection time of close to one day. Conclusion: The performance of these algorithms has a correlation to their parameter values, which may affect the performance evaluation.

KW - Evaluation

KW - Outbreak detection algorithms

KW - Outbreak simulation

KW - Parameter values

UR - http://www.scopus.com/inward/record.url?scp=74649084204&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=74649084204&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2009.08.003

DO - 10.1016/j.jbi.2009.08.003

M3 - Article

VL - 43

SP - 97

EP - 103

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

IS - 1

ER -