Comparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows

Abstract Bovine mastitis is one of the most important economic and health issues in dairy farms. Data collection during routine recording procedures and access to large datasets have shed the light on the possibility to use trained machine learning algorithms to predict the udder health status of co...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Tania Bobbo, Stefano Biffani, Cristian Taccioli, Mauro Penasa, Martino Cassandro
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/f92da889623c4b0d91bf3a497f495f1f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f92da889623c4b0d91bf3a497f495f1f
record_format	dspace
spelling	oai:doaj.org-article:f92da889623c4b0d91bf3a497f495f1f2021-12-02T18:18:32ZComparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows10.1038/s41598-021-93056-42045-2322https://doaj.org/article/f92da889623c4b0d91bf3a497f495f1f2021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-93056-4https://doaj.org/toc/2045-2322Abstract Bovine mastitis is one of the most important economic and health issues in dairy farms. Data collection during routine recording procedures and access to large datasets have shed the light on the possibility to use trained machine learning algorithms to predict the udder health status of cows. In this study, we compared eight different machine learning methods (Linear Discriminant Analysis, Generalized Linear Model with logit link function, Naïve Bayes, Classification and Regression Trees, k-Nearest Neighbors, Support Vector Machines, Random Forest and Neural Network) to predict udder health status of cows based on somatic cell counts. Prediction accuracies of all methods were above 75%. According to different metrics, Neural Network, Random Forest and linear methods had the best performance in predicting udder health classes at a given test-day (healthy or mastitic according to somatic cell count below or above a predefined threshold of 200,000 cells/mL) based on the cow’s milk traits recorded at previous test-day. Our findings suggest machine learning algorithms as a promising tool to improve decision making for farmers. Machine learning analysis would improve the surveillance methods and help farmers to identify in advance those cows that would possibly have high somatic cell count in the subsequent test-day.Tania BobboStefano BiffaniCristian TaccioliMauro PenasaMartino CassandroNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Tania Bobbo Stefano Biffani Cristian Taccioli Mauro Penasa Martino Cassandro Comparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows
description	Abstract Bovine mastitis is one of the most important economic and health issues in dairy farms. Data collection during routine recording procedures and access to large datasets have shed the light on the possibility to use trained machine learning algorithms to predict the udder health status of cows. In this study, we compared eight different machine learning methods (Linear Discriminant Analysis, Generalized Linear Model with logit link function, Naïve Bayes, Classification and Regression Trees, k-Nearest Neighbors, Support Vector Machines, Random Forest and Neural Network) to predict udder health status of cows based on somatic cell counts. Prediction accuracies of all methods were above 75%. According to different metrics, Neural Network, Random Forest and linear methods had the best performance in predicting udder health classes at a given test-day (healthy or mastitic according to somatic cell count below or above a predefined threshold of 200,000 cells/mL) based on the cow’s milk traits recorded at previous test-day. Our findings suggest machine learning algorithms as a promising tool to improve decision making for farmers. Machine learning analysis would improve the surveillance methods and help farmers to identify in advance those cows that would possibly have high somatic cell count in the subsequent test-day.
format	article
author	Tania Bobbo Stefano Biffani Cristian Taccioli Mauro Penasa Martino Cassandro
author_facet	Tania Bobbo Stefano Biffani Cristian Taccioli Mauro Penasa Martino Cassandro
author_sort	Tania Bobbo
title	Comparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows
title_short	Comparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows
title_full	Comparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows
title_fullStr	Comparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows
title_full_unstemmed	Comparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows
title_sort	comparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/f92da889623c4b0d91bf3a497f495f1f
work_keys_str_mv	AT taniabobbo comparisonofmachinelearningmethodstopredictudderhealthstatusbasedonsomaticcellcountsindairycows AT stefanobiffani comparisonofmachinelearningmethodstopredictudderhealthstatusbasedonsomaticcellcountsindairycows AT cristiantaccioli comparisonofmachinelearningmethodstopredictudderhealthstatusbasedonsomaticcellcountsindairycows AT mauropenasa comparisonofmachinelearningmethodstopredictudderhealthstatusbasedonsomaticcellcountsindairycows AT martinocassandro comparisonofmachinelearningmethodstopredictudderhealthstatusbasedonsomaticcellcountsindairycows
_version_	1718378310597083136

Comparison of machine learning methods to predict udder health status based on somatic cell counts in dairy cows

Ejemplares similares