Classification of light Yorkshire pigs at different production stages using ordinary least squares and machine learning methods
Pig homogeneity and growth are major concerns for the pig industry today. Variability in pigs’ size has a strong impact on profitability as uniformity plays a key role in the overall economic value of pigs produced. This research focused on statistical methods to identify pigs at risk of growth reta...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-01-01
|
| Series: | Animal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1751731123003646 |
| _version_ | 1797355299148922880 |
|---|---|
| author | J. Casellas P. Salgado-López J. Lorente I. Solar Diaz T. Rathje J. Gasa D. Solà-Oriol |
| author_facet | J. Casellas P. Salgado-López J. Lorente I. Solar Diaz T. Rathje J. Gasa D. Solà-Oriol |
| author_sort | J. Casellas |
| collection | DOAJ |
| description | Pig homogeneity and growth are major concerns for the pig industry today. Variability in pigs’ size has a strong impact on profitability as uniformity plays a key role in the overall economic value of pigs produced. This research focused on statistical methods to identify pigs at risk of growth retardation at different stages of production. Data from 125 083 Yorkshire pigs at weaning (18–28 d), 59 533 pigs at the end of the nursery period (70–82 d) and 48 862 pigs at slaughter (155–170 d) were analyzed under three different cut-points (lowest 10, 20 and 30%) to characterize light animals. Records were randomly split into 2:1 training:testing sets, and each training data set was analyzed through an ordinary least squares approach and four machine learning algorithms (decision tree, random forest, and two alternative boosting approaches). A wide range of weighting functions were applied to give increased relevance to lighter pigs. Each resulting classification norm was used to classify light pigs in the testing data set. Both sensitivity and specificity were retained to construct the receiver operating characteristic curve, and the statistical performance of each analytical approach was evaluated by the area under the curve (AUC). In all production stages and cut-points, the random forest machine learning algorithm provided the highest AUC, closely followed by boosting procedures. For weaning BW (WW), factors related to birth BW and litter size accounted for more than 75% of the important prediction factors for light pigs. BW at the end of the nursery period and slaughter BW analyses revealed a similar pattern where WW and BW at the end of the nursery period accounted for more than 40 and 50% of statistical importance among the prediction factors, respectively. Machine learning algorithms are useful tools to easily evaluate the risk factors affecting the efficiency and homogeneity in swine. Since the BW at birth and weaning are key factors, sow nutrition and feeding management during gestation and lactation, along with piglet management during lactation, are identified as important influences on pig weight variability. |
| first_indexed | 2024-03-08T14:09:08Z |
| format | Article |
| id | doaj.art-8fbb6addd0334314a448fdab0b015f2f |
| institution | Directory Open Access Journal |
| issn | 1751-7311 |
| language | English |
| last_indexed | 2024-03-08T14:09:08Z |
| publishDate | 2024-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Animal |
| spelling | doaj.art-8fbb6addd0334314a448fdab0b015f2f2024-01-15T04:21:00ZengElsevierAnimal1751-73112024-01-01181101047Classification of light Yorkshire pigs at different production stages using ordinary least squares and machine learning methodsJ. Casellas0P. Salgado-López1J. Lorente2I. Solar Diaz3T. Rathje4J. Gasa5D. Solà-Oriol6Department of Animal and Food Science, Autonomous University of Barcelona, Bellaterra 08193, SpainAnimal Nutrition and Welfare Service (SNIBA), Department of Animal and Food Science, Autonomous University of Barcelona, Bellaterra 08193, Spain; Corresponding author.Andrimner Genética Aplicada, Calvet 30-32, 3o 2a, 08021, Barcelona, SpainDNA Genetics LLC, Columbus, NE 68601, USADNA Genetics LLC, Columbus, NE 68601, USAAnimal Nutrition and Welfare Service (SNIBA), Department of Animal and Food Science, Autonomous University of Barcelona, Bellaterra 08193, SpainAnimal Nutrition and Welfare Service (SNIBA), Department of Animal and Food Science, Autonomous University of Barcelona, Bellaterra 08193, SpainPig homogeneity and growth are major concerns for the pig industry today. Variability in pigs’ size has a strong impact on profitability as uniformity plays a key role in the overall economic value of pigs produced. This research focused on statistical methods to identify pigs at risk of growth retardation at different stages of production. Data from 125 083 Yorkshire pigs at weaning (18–28 d), 59 533 pigs at the end of the nursery period (70–82 d) and 48 862 pigs at slaughter (155–170 d) were analyzed under three different cut-points (lowest 10, 20 and 30%) to characterize light animals. Records were randomly split into 2:1 training:testing sets, and each training data set was analyzed through an ordinary least squares approach and four machine learning algorithms (decision tree, random forest, and two alternative boosting approaches). A wide range of weighting functions were applied to give increased relevance to lighter pigs. Each resulting classification norm was used to classify light pigs in the testing data set. Both sensitivity and specificity were retained to construct the receiver operating characteristic curve, and the statistical performance of each analytical approach was evaluated by the area under the curve (AUC). In all production stages and cut-points, the random forest machine learning algorithm provided the highest AUC, closely followed by boosting procedures. For weaning BW (WW), factors related to birth BW and litter size accounted for more than 75% of the important prediction factors for light pigs. BW at the end of the nursery period and slaughter BW analyses revealed a similar pattern where WW and BW at the end of the nursery period accounted for more than 40 and 50% of statistical importance among the prediction factors, respectively. Machine learning algorithms are useful tools to easily evaluate the risk factors affecting the efficiency and homogeneity in swine. Since the BW at birth and weaning are key factors, sow nutrition and feeding management during gestation and lactation, along with piglet management during lactation, are identified as important influences on pig weight variability.http://www.sciencedirect.com/science/article/pii/S1751731123003646Area under the curveArtificial intelligenceGrowth retardationLive weightSwine |
| spellingShingle | J. Casellas P. Salgado-López J. Lorente I. Solar Diaz T. Rathje J. Gasa D. Solà-Oriol Classification of light Yorkshire pigs at different production stages using ordinary least squares and machine learning methods Animal Area under the curve Artificial intelligence Growth retardation Live weight Swine |
| title | Classification of light Yorkshire pigs at different production stages using ordinary least squares and machine learning methods |
| title_full | Classification of light Yorkshire pigs at different production stages using ordinary least squares and machine learning methods |
| title_fullStr | Classification of light Yorkshire pigs at different production stages using ordinary least squares and machine learning methods |
| title_full_unstemmed | Classification of light Yorkshire pigs at different production stages using ordinary least squares and machine learning methods |
| title_short | Classification of light Yorkshire pigs at different production stages using ordinary least squares and machine learning methods |
| title_sort | classification of light yorkshire pigs at different production stages using ordinary least squares and machine learning methods |
| topic | Area under the curve Artificial intelligence Growth retardation Live weight Swine |
| url | http://www.sciencedirect.com/science/article/pii/S1751731123003646 |
| work_keys_str_mv | AT jcasellas classificationoflightyorkshirepigsatdifferentproductionstagesusingordinaryleastsquaresandmachinelearningmethods AT psalgadolopez classificationoflightyorkshirepigsatdifferentproductionstagesusingordinaryleastsquaresandmachinelearningmethods AT jlorente classificationoflightyorkshirepigsatdifferentproductionstagesusingordinaryleastsquaresandmachinelearningmethods AT isolardiaz classificationoflightyorkshirepigsatdifferentproductionstagesusingordinaryleastsquaresandmachinelearningmethods AT trathje classificationoflightyorkshirepigsatdifferentproductionstagesusingordinaryleastsquaresandmachinelearningmethods AT jgasa classificationoflightyorkshirepigsatdifferentproductionstagesusingordinaryleastsquaresandmachinelearningmethods AT dsolaoriol classificationoflightyorkshirepigsatdifferentproductionstagesusingordinaryleastsquaresandmachinelearningmethods |