دورية أكاديمية
Machine learning approach as an early warning system to prevent foodborne Salmonella outbreaks in northwestern Italy.
| العنوان: | Machine learning approach as an early warning system to prevent foodborne Salmonella outbreaks in northwestern Italy. |
|---|---|
| المؤلفون: | Garcia-Vozmediano A; Istituto Zooprofilattico Sperimentale del Piemonte, Liguria e Valle d'Aosta, Via Bologna 148, 10154, Turin, Italy. aitor.garciavozmediano@izsto.it., Maurella C; Istituto Zooprofilattico Sperimentale del Piemonte, Liguria e Valle d'Aosta, Via Bologna 148, 10154, Turin, Italy., Ceballos LA; Istituto Zooprofilattico Sperimentale del Piemonte, Liguria e Valle d'Aosta, Via Bologna 148, 10154, Turin, Italy., Crescio E; Tecnológico de Monterrey, Av. Eugenio Garza Sada 2501 Sur, Tecnológico, 64849, Monterrey, N.L., México., Meo R; Department of Computer Science, University of Turin, Corso Svizzera 185, 10149, Turin, Italy., Martelli W; Istituto Zooprofilattico Sperimentale del Piemonte, Liguria e Valle d'Aosta, Via Bologna 148, 10154, Turin, Italy., Pitti M; Istituto Zooprofilattico Sperimentale del Piemonte, Liguria e Valle d'Aosta, Via Bologna 148, 10154, Turin, Italy., Lombardi D; Piedmont Regional Service for the Epidemiology of Infectious Diseases (SeREMI), Via Venezia 6, 15121, Alessandria, Italy., Meloni D; Istituto Zooprofilattico Sperimentale del Piemonte, Liguria e Valle d'Aosta, Via Bologna 148, 10154, Turin, Italy., Pasqualini C; Piedmont Regional Service for the Epidemiology of Infectious Diseases (SeREMI), Via Venezia 6, 15121, Alessandria, Italy., Ru G; Istituto Zooprofilattico Sperimentale del Piemonte, Liguria e Valle d'Aosta, Via Bologna 148, 10154, Turin, Italy. |
| المصدر: | Veterinary research [Vet Res] 2024 Jun 05; Vol. 55 (1), pp. 72. Date of Electronic Publication: 2024 Jun 05. |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: BioMed Central Country of Publication: England NLM ID: 9309551 Publication Model: Electronic Cited Medium: Internet ISSN: 1297-9716 (Electronic) Linking ISSN: 09284249 NLM ISO Abbreviation: Vet Res Subsets: MEDLINE |
| أسماء مطبوعة: | Publication: 2011- : London : BioMed Central Original Publication: Paris : Editions Scientifiques Elsevier ; INRA, c1993- |
| مواضيع طبية MeSH: | Machine Learning* , Disease Outbreaks*/veterinary , Disease Outbreaks*/prevention & control , Salmonella Food Poisoning*/prevention & control , Salmonella Food Poisoning*/epidemiology, Italy/epidemiology ; Humans ; Animals ; Salmonella/physiology ; Food Microbiology ; Foodborne Diseases/prevention & control ; Foodborne Diseases/epidemiology ; Foodborne Diseases/microbiology ; Prevalence ; Salmonella Infections/epidemiology ; Salmonella Infections/prevention & control |
| مستخلص: | Salmonellosis, one of the most common foodborne infections in Europe, is monitored by food safety surveillance programmes, resulting in the generation of extensive databases. By leveraging tree-based machine learning (ML) algorithms, we exploited data from food safety audits to predict spatiotemporal patterns of salmonellosis in northwestern Italy. Data on human cases confirmed in 2015-2018 (n = 1969) and food surveillance data collected in 2014-2018 were used to develop ML algorithms. We integrated the monthly municipal human incidence with 27 potential predictors, including the observed prevalence of Salmonella in food. We applied the tree regression, random forest and gradient boosting algorithms considering different scenarios and evaluated their predictivity in terms of the mean absolute percentage error (MAPE) and R 2 . Using a similar dataset from the year 2019, spatiotemporal predictions and their relative sensitivities and specificities were obtained. Random forest and gradient boosting (R 2 = 0.55, MAPE = 7.5%) outperformed the tree regression algorithm (R 2 = 0.42, MAPE = 8.8%). Salmonella prevalence in food; spatial features; and monitoring efforts in ready-to-eat milk, fruits and vegetables, and pig meat products contributed the most to the models' predictivity, reducing the variance by 90.5%. Conversely, the number of positive samples obtained for specific food matrices minimally influenced the predictions (2.9%). Spatiotemporal predictions for 2019 showed sensitivity and specificity levels of 46.5% (due to the lack of some infection hotspots) and 78.5%, respectively. This study demonstrates the added value of integrating data from human and veterinary health services to develop predictive models of human salmonellosis occurrence, providing early warnings useful for mitigating foodborne disease impacts on public health. (© 2024. The Author(s).) |
| References: | J R Soc Interface. 2019 Feb 28;16(151):20180624. (PMID: 30958197) Trends Microbiol. 2018 Feb;26(2):102-118. (PMID: 29097090) J Biomed Inform. 2021 Jan;113:103655. (PMID: 33309898) Epidemiol Infect. 2015 Oct;143(13):2786-94. (PMID: 25672399) Front Microbiol. 2019 Aug 06;10:1722. (PMID: 31447800) Lancet Digit Health. 2019 May;1(1):e13-e14. (PMID: 33323236) Trials. 2021 Aug 16;22(1):537. (PMID: 34399832) BMC Public Health. 2013 Sep 23;13:875. (PMID: 24060206) Foodborne Pathog Dis. 2021 Aug;18(8):590-598. (PMID: 33902323) Int J Infect Dis. 2016 Dec;53:15-20. (PMID: 27777092) Prev Vet Med. 2011 Sep 1;101(3-4):148-56. (PMID: 20832879) Euro Surveill. 2019 Aug;24(34):. (PMID: 31456559) Epidemiol Infect. 2013 Oct;141(10):2011-21. (PMID: 23659675) N Engl J Med. 2016 Sep 29;375(13):1216-9. (PMID: 27682033) J Infect Dis. 2016 Dec 1;214(suppl_4):S375-S379. (PMID: 28830113) Acta Med Acad. 2020 Dec;49(3):255-264. (PMID: 33781069) Proc Biol Sci. 2020 Feb 12;287(1920):20192882. (PMID: 32019444) Emerg Infect Dis. 2011 Jan;17(1):7-15. (PMID: 21192848) Annu Rev Public Health. 2017 Mar 20;38:57-79. (PMID: 27992726) Epidemiology. 2020 May;31(3):327-333. (PMID: 32079833) EFSA J. 2022 Dec 13;20(12):e07666. (PMID: 36524203) BMC Public Health. 2014 Feb 11;14:147. (PMID: 24517715) Neural Comput Appl. 2020;32(9):4417-4451. (PMID: 32205918) Comput Struct Biotechnol J. 2020 Jun 25;18:1704-1721. (PMID: 32670510) Global Health. 2005 Apr 22;1(1):4. (PMID: 15847691) PLoS One. 2021 Jul 27;16(7):e0254301. (PMID: 34314433) Pathogens. 2022 Jun 16;11(6):. (PMID: 35745545) Appl Environ Microbiol. 2019 Jul 1;85(14):. (PMID: 31053586) Int J Environ Res Public Health. 2018 Aug 13;15(8):. (PMID: 30104555) Front Vet Sci. 2021 Mar 12;8:633977. (PMID: 33778039) Epidemiol Infect. 2018 Mar;146(4):423-429. (PMID: 29409557) NPJ Digit Med. 2018 May 8;1:18. (PMID: 31304302) NPJ Digit Med. 2018 Nov 6;1:36. (PMID: 31304318) Epidemiol Infect. 2023 Feb 27;151:e46. (PMID: 36843485) |
| معلومات مُعتمدة: | IZS PLV 07/20 RC Ministero della Salute |
| فهرسة مساهمة: | Keywords: Supervised learning; decision tree algorithms; disease surveillance; food products; salmonellosis; transdisciplinarity |
| تواريخ الأحداث: | Date Created: 20240605 Date Completed: 20240606 Latest Revision: 20240608 |
| رمز التحديث: | 20240608 |
| مُعرف محوري في PubMed: | PMC11154984 |
| DOI: | 10.1186/s13567-024-01323-9 |
| PMID: | 38840261 |
| قاعدة البيانات: | MEDLINE |
Find this article in full text from Springer Verlag. 
Full Text Finder | تدمد: | 1297-9716 |
|---|---|
| DOI: | 10.1186/s13567-024-01323-9 |