Quantifying the determinants of outbreak detection performance through simulation and machine learning - PubMed (original) (raw)
Quantifying the determinants of outbreak detection performance through simulation and machine learning
Nastaran Jafarpour et al. J Biomed Inform. 2015 Feb.
Free article
Abstract
Objective: To develop a probabilistic model for discovering and quantifying determinants of outbreak detection and to use the model to predict detection performance for new outbreaks.
Materials and methods: We used an existing software platform to simulate waterborne disease outbreaks of varying duration and magnitude. The simulated data were overlaid on real data from visits to emergency department in Montreal for gastroenteritis. We analyzed the combined data using biosurveillance algorithms, varying their parameters over a wide range. We then applied structure and parameter learning algorithms to the resulting data set to build a Bayesian network model for predicting detection performance as a function of outbreak characteristics and surveillance system parameters. We evaluated the predictions of this model through 5-fold cross-validation.
Results: The model predicted performance metrics of commonly used outbreak detection methods with an accuracy greater than 0.80. The model also quantified the influence of different outbreak characteristics and parameters of biosurveillance algorithms on detection performance in practically relevant surveillance scenarios. In addition to identifying characteristics expected a priori to have a strong influence on detection performance, such as the alerting threshold and the peak size of the outbreak, the model suggested an important role for other algorithm features, such as adjustment for weekly patterns.
Conclusion: We developed a model that accurately predicts how characteristics of disease outbreaks and detection methods will influence on detection. This model can be used to compare the performance of detection methods under different surveillance scenarios, to gain insight into which characteristics of outbreaks and biosurveillance algorithms drive detection performance, and to guide the configuration of surveillance systems.
Keywords: Bayesian networks; Disease outbreak detection; Outbreak simulation; Predicting performance; Public health informatics; Surveillance.
Copyright © 2014 Elsevier Inc. All rights reserved.
Similar articles
- A new prior for bayesian anomaly detection: application to biosurveillance.
Shen Y, Cooper GF. Shen Y, et al. Methods Inf Med. 2010;49(1):44-53. doi: 10.3414/ME09-01-0008. Epub 2009 Dec 21. Methods Inf Med. 2010. PMID: 20027381 - Bio-ALIRT biosurveillance detection algorithm evaluation.
Siegrist D, Pavlin J. Siegrist D, et al. MMWR Suppl. 2004 Sep 24;53:152-8. MMWR Suppl. 2004. PMID: 15714645 - Using GIS to create synthetic disease outbreaks.
Watkins RE, Eagleson S, Beckett S, Garner G, Veenendaal B, Wright G, Plant AJ. Watkins RE, et al. BMC Med Inform Decis Mak. 2007 Feb 14;7:4. doi: 10.1186/1472-6947-7-4. BMC Med Inform Decis Mak. 2007. PMID: 17300714 Free PMC article. - Outbreak detection through automated surveillance: a review of the determinants of detection.
Buckeridge DL. Buckeridge DL. J Biomed Inform. 2007 Aug;40(4):370-9. doi: 10.1016/j.jbi.2006.09.003. Epub 2006 Oct 5. J Biomed Inform. 2007. PMID: 17095301 Review. - Outbreak detection algorithms based on generalized linear model: a review with new practical examples.
Zareie B, Poorolajal J, Roshani A, Karami M. Zareie B, et al. BMC Med Res Methodol. 2023 Oct 14;23(1):235. doi: 10.1186/s12874-023-02050-z. BMC Med Res Methodol. 2023. PMID: 37838735 Free PMC article. Review.
Cited by
- Using decision fusion methods to improve outbreak detection in disease surveillance.
Texier G, Allodji RS, Diop L, Meynard JB, Pellegrin L, Chaudet H. Texier G, et al. BMC Med Inform Decis Mak. 2019 Mar 5;19(1):38. doi: 10.1186/s12911-019-0774-3. BMC Med Inform Decis Mak. 2019. PMID: 30837003 Free PMC article. - Some Innovative Approaches for Public Health and Epidemiology Informatics.
Toubiana L, Griffon N. Toubiana L, et al. Yearb Med Inform. 2016 Nov 10;(1):247-250. doi: 10.15265/IY-2016-047. Yearb Med Inform. 2016. PMID: 27830258 Free PMC article. - Characterizing the Effects of Extreme Cold Using Real-time Syndromic Surveillance, Ontario, Canada, 2010-2016.
VanStone N, van Dijk A, Chisamore T, Mosley B, Hall G, Belanger P, Michael Moore K. VanStone N, et al. Public Health Rep. 2017 Jul/Aug;132(1_suppl):48S-52S. doi: 10.1177/0033354917708354. Public Health Rep. 2017. PMID: 28692396 Free PMC article. - Public Health, Population Health, and Epidemiology Informatics: Recent Research and Trends in the United States.
Massoudi BL, Chester KG. Massoudi BL, et al. Yearb Med Inform. 2017 Aug;26(1):241-247. doi: 10.15265/IY-2017-035. Epub 2017 Sep 11. Yearb Med Inform. 2017. PMID: 29063572 Free PMC article. Review. - Machine learning based efficient prediction of positive cases of waterborne diseases.
Hussain M, Cifci MA, Sehar T, Nabi S, Cheikhrouhou O, Maqsood H, Ibrahim M, Mohammad F. Hussain M, et al. BMC Med Inform Decis Mak. 2023 Jan 18;23(1):11. doi: 10.1186/s12911-022-02092-1. BMC Med Inform Decis Mak. 2023. PMID: 36653779 Free PMC article.