Comparison of Machine Learning Tree-Based Algorithms to Predict Future Paratuberculosis ELISA Results Using Repeat Milk Tests
Machine learning algorithms have been applied to various animal husbandry and veterinary-related problems; however, its use in Johne’s disease diagnosis and control is still in its infancy. The following proof-of-concept study explores the application of tree-based (decision trees and random forest)...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-04-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/14/7/1113 |
| _version_ | 1797212930316435456 |
|---|---|
| author | Jamie Imada Juan Carlos Arango-Sabogal Cathy Bauman Steven Roche David Kelton |
| author_facet | Jamie Imada Juan Carlos Arango-Sabogal Cathy Bauman Steven Roche David Kelton |
| author_sort | Jamie Imada |
| collection | DOAJ |
| description | Machine learning algorithms have been applied to various animal husbandry and veterinary-related problems; however, its use in Johne’s disease diagnosis and control is still in its infancy. The following proof-of-concept study explores the application of tree-based (decision trees and random forest) algorithms to analyze repeat milk testing data from 1197 Canadian dairy cows and the algorithms’ ability to predict future Johne’s test results. The random forest models using milk component testing results alongside past Johne’s results demonstrated a good predictive performance for a future Johne’s ELISA result with a dichotomous outcome (positive vs. negative). The final random forest model yielded a kappa of 0.626, a roc AUC of 0.915, a sensitivity of 72%, and a specificity of 98%. The positive predictive and negative predictive values were 0.81 and 0.97, respectively. The decision tree models provided an interpretable alternative to the random forest algorithms with a slight decrease in model sensitivity. The results of this research suggest a promising avenue for future targeted Johne’s testing schemes. Further research is needed to validate these techniques in real-world settings and explore their incorporation in prevention and control programs. |
| first_indexed | 2024-04-24T10:50:12Z |
| format | Article |
| id | doaj.art-a841b76dfb5a40318aecbff2b23d3b00 |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-04-24T10:50:12Z |
| publishDate | 2024-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-a841b76dfb5a40318aecbff2b23d3b002024-04-12T13:14:25ZengMDPI AGAnimals2076-26152024-04-01147111310.3390/ani14071113Comparison of Machine Learning Tree-Based Algorithms to Predict Future Paratuberculosis ELISA Results Using Repeat Milk TestsJamie Imada0Juan Carlos Arango-Sabogal1Cathy Bauman2Steven Roche3David Kelton4Department of Population Medicine, University of Guelph, Guelph, ON N1G 2W1, CanadaDépartement de Pathologie et Microbiologie, Faculté de Médecine Vétérinaire, Université de Montréal, Saint-Hyacinthe, QC J2S 2M2, CanadaDepartment of Population Medicine, University of Guelph, Guelph, ON N1G 2W1, CanadaDepartment of Population Medicine, University of Guelph, Guelph, ON N1G 2W1, CanadaDepartment of Population Medicine, University of Guelph, Guelph, ON N1G 2W1, CanadaMachine learning algorithms have been applied to various animal husbandry and veterinary-related problems; however, its use in Johne’s disease diagnosis and control is still in its infancy. The following proof-of-concept study explores the application of tree-based (decision trees and random forest) algorithms to analyze repeat milk testing data from 1197 Canadian dairy cows and the algorithms’ ability to predict future Johne’s test results. The random forest models using milk component testing results alongside past Johne’s results demonstrated a good predictive performance for a future Johne’s ELISA result with a dichotomous outcome (positive vs. negative). The final random forest model yielded a kappa of 0.626, a roc AUC of 0.915, a sensitivity of 72%, and a specificity of 98%. The positive predictive and negative predictive values were 0.81 and 0.97, respectively. The decision tree models provided an interpretable alternative to the random forest algorithms with a slight decrease in model sensitivity. The results of this research suggest a promising avenue for future targeted Johne’s testing schemes. Further research is needed to validate these techniques in real-world settings and explore their incorporation in prevention and control programs.https://www.mdpi.com/2076-2615/14/7/1113paratuberculosisJohne’s diseasedisease controlmachine learningrandom forestdecision tree |
| spellingShingle | Jamie Imada Juan Carlos Arango-Sabogal Cathy Bauman Steven Roche David Kelton Comparison of Machine Learning Tree-Based Algorithms to Predict Future Paratuberculosis ELISA Results Using Repeat Milk Tests Animals paratuberculosis Johne’s disease disease control machine learning random forest decision tree |
| title | Comparison of Machine Learning Tree-Based Algorithms to Predict Future Paratuberculosis ELISA Results Using Repeat Milk Tests |
| title_full | Comparison of Machine Learning Tree-Based Algorithms to Predict Future Paratuberculosis ELISA Results Using Repeat Milk Tests |
| title_fullStr | Comparison of Machine Learning Tree-Based Algorithms to Predict Future Paratuberculosis ELISA Results Using Repeat Milk Tests |
| title_full_unstemmed | Comparison of Machine Learning Tree-Based Algorithms to Predict Future Paratuberculosis ELISA Results Using Repeat Milk Tests |
| title_short | Comparison of Machine Learning Tree-Based Algorithms to Predict Future Paratuberculosis ELISA Results Using Repeat Milk Tests |
| title_sort | comparison of machine learning tree based algorithms to predict future paratuberculosis elisa results using repeat milk tests |
| topic | paratuberculosis Johne’s disease disease control machine learning random forest decision tree |
| url | https://www.mdpi.com/2076-2615/14/7/1113 |
| work_keys_str_mv | AT jamieimada comparisonofmachinelearningtreebasedalgorithmstopredictfutureparatuberculosiselisaresultsusingrepeatmilktests AT juancarlosarangosabogal comparisonofmachinelearningtreebasedalgorithmstopredictfutureparatuberculosiselisaresultsusingrepeatmilktests AT cathybauman comparisonofmachinelearningtreebasedalgorithmstopredictfutureparatuberculosiselisaresultsusingrepeatmilktests AT stevenroche comparisonofmachinelearningtreebasedalgorithmstopredictfutureparatuberculosiselisaresultsusingrepeatmilktests AT davidkelton comparisonofmachinelearningtreebasedalgorithmstopredictfutureparatuberculosiselisaresultsusingrepeatmilktests |