Forecasting the monthly incidence rate of brucellosis in west of Iran using time series and data mining from 2010 to 2019.
Journal
PloS one
ISSN: 1932-6203
Titre abrégé: PLoS One
Pays: United States
ID NLM: 101285081
Informations de publication
Date de publication:
2020
2020
Historique:
received:
21
01
2020
accepted:
23
04
2020
entrez:
13
5
2020
pubmed:
13
5
2020
medline:
31
7
2020
Statut:
epublish
Résumé
The identification of statistical models for the accurate forecast and timely determination of the outbreak of infectious diseases is very important for the healthcare system. Thus, this study was conducted to assess and compare the performance of four machine-learning methods in modeling and forecasting brucellosis time series data based on climatic parameters. In this cohort study, human brucellosis cases and climatic parameters were analyzed on a monthly basis for the Qazvin province-located in northwestern Iran- over a period of 9 years (2010-2018). The data were classified into two subsets of education (80%) and testing (20%). Artificial neural network methods (radial basis function and multilayer perceptron), support vector machine and random forest were fitted to each set. Performance analysis of the models were done using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Root Error (MARE), and R2 criteria. The incidence rate of the brucellosis in Qazvin province was 27.43 per 100,000 during 2010-2019. Based on our results, the values of the RMSE (0.22), MAE (0.175), MARE (0.007) criteria were smaller for the multilayer perceptron neural network than their values in the other three models. Moreover, the R2 (0.99) value was bigger in this model. Therefore, the multilayer perceptron neural network exhibited better performance in forecasting the studied data. The average wind speed and mean temperature were the most effective climatic parameters in the incidence of this disease. The multilayer perceptron neural network can be used as an effective method in detecting the behavioral trend of brucellosis over time. Nevertheless, further studies focusing on the application and comparison of these methods are needed to detect the most appropriate forecast method for this disease.
Sections du résumé
BACKGROUND
The identification of statistical models for the accurate forecast and timely determination of the outbreak of infectious diseases is very important for the healthcare system. Thus, this study was conducted to assess and compare the performance of four machine-learning methods in modeling and forecasting brucellosis time series data based on climatic parameters.
METHODS
In this cohort study, human brucellosis cases and climatic parameters were analyzed on a monthly basis for the Qazvin province-located in northwestern Iran- over a period of 9 years (2010-2018). The data were classified into two subsets of education (80%) and testing (20%). Artificial neural network methods (radial basis function and multilayer perceptron), support vector machine and random forest were fitted to each set. Performance analysis of the models were done using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Root Error (MARE), and R2 criteria.
RESULTS
The incidence rate of the brucellosis in Qazvin province was 27.43 per 100,000 during 2010-2019. Based on our results, the values of the RMSE (0.22), MAE (0.175), MARE (0.007) criteria were smaller for the multilayer perceptron neural network than their values in the other three models. Moreover, the R2 (0.99) value was bigger in this model. Therefore, the multilayer perceptron neural network exhibited better performance in forecasting the studied data. The average wind speed and mean temperature were the most effective climatic parameters in the incidence of this disease.
CONCLUSIONS
The multilayer perceptron neural network can be used as an effective method in detecting the behavioral trend of brucellosis over time. Nevertheless, further studies focusing on the application and comparison of these methods are needed to detect the most appropriate forecast method for this disease.
Identifiants
pubmed: 32396582
doi: 10.1371/journal.pone.0232910
pii: PONE-D-20-00374
pmc: PMC7217463
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e0232910Déclaration de conflit d'intérêts
The authors have declared that no competing interests exist.
Références
Rev Esp Salud Publica. 2000 Jan-Feb;74(1):45-53
pubmed: 10832390
Scand J Infect Dis. 2014 Aug;46(8):573-7
pubmed: 24934986
PLoS One. 2016 Feb 22;11(2):e0149401
pubmed: 26901682
PLoS One. 2014 Feb 05;9(2):e88075
pubmed: 24505382
Int J Infect Dis. 2008 Mar;12(2):157-61
pubmed: 17698385
Am J Med Sci. 1994 Jan;307(1):64-75
pubmed: 8291510
J Clin Virol. 2006 Feb;35(2):147-53
pubmed: 16055371
BMC Res Notes. 2019 Jun 24;12(1):353
pubmed: 31234938
Vet Microbiol. 2002 Dec 20;90(1-4):111-34
pubmed: 12414138
South Med J. 2007 Nov;100(11):1074
pubmed: 17984735
Iran J Public Health. 2012;41(11):102-3
pubmed: 23304684
Emerg Infect Dis. 2008 Dec;14(12):1916-8
pubmed: 19046520
Healthc Inform Res. 2013 Sep;19(3):177-85
pubmed: 24175116
Public Health. 2012 Dec;126(12):1058-62
pubmed: 22884862
Lancet Infect Dis. 2006 Feb;6(2):91-9
pubmed: 16439329
J Med Syst. 2017 Apr;41(4):51
pubmed: 28214992
Methods Inf Med. 2000 Dec;39(4-5):303-10
pubmed: 11191698
Biosci Trends. 2017 Jul 24;11(3):292-296
pubmed: 28484187
Epidemiol Infect. 2012 Apr;140(4):602-7
pubmed: 21676348
Jpn J Infect Dis. 2007 Nov;60(6):362-6
pubmed: 18032835
World J Gastroenterol. 2004 Dec 15;10(24):3579-82
pubmed: 15534910
Emerg Infect Dis. 2002 Jul;8(7):672-8
pubmed: 12095433
Presse Med. 2001 Sep 29;30(27):1339-43
pubmed: 11675922
Zoonoses Public Health. 2019 Nov;66(7):759-772
pubmed: 31305019
Microb Pathog. 2017 Aug;109:239-247
pubmed: 28602839
Vet Microbiol. 2002 Dec 20;90(1-4):81-110
pubmed: 12414137
Int J Clin Pract. 2003 Jan-Feb;57(1):20-4
pubmed: 12587937
Osong Public Health Res Perspect. 2016 Jun;7(3):157-67
pubmed: 27413646
Aten Primaria. 1997 Apr 15;19(6):290-5
pubmed: 9264667
Stat Med. 2001 Oct 30;20(20):3051-69
pubmed: 11590632
J Res Health Sci. 2012 Dec 13;12(2):105-8
pubmed: 23241521
Prilozi. 2010;31(1):33-54
pubmed: 20703182