Appropriate Data Quality Checks Improve the Reliability of Values Predicted from Milk Mid-Infrared Spectra
The use of abnormal milk mid-infrared (MIR) spectrum strongly affects prediction quality, even if the prediction equations used are accurate. So, this record must be detected after or before the prediction process to avoid erroneous spectral extrapolation or the use of poor-quality spectral data by...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Animals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-2615/11/2/533 |
| _version_ | 1797396032417431552 |
|---|---|
| author | Lei Zhang Chunfang Li Frédéric Dehareng Clément Grelet Frédéric Colinet Nicolas Gengler Yves Brostaux Hélène Soyeurt |
| author_facet | Lei Zhang Chunfang Li Frédéric Dehareng Clément Grelet Frédéric Colinet Nicolas Gengler Yves Brostaux Hélène Soyeurt |
| author_sort | Lei Zhang |
| collection | DOAJ |
| description | The use of abnormal milk mid-infrared (MIR) spectrum strongly affects prediction quality, even if the prediction equations used are accurate. So, this record must be detected after or before the prediction process to avoid erroneous spectral extrapolation or the use of poor-quality spectral data by dairy herd improvement (DHI) organizations. For financial or practical reasons, adapting the quality protocol currently used to improve the accuracy of fat and protein contents is unfeasible. This study proposed three different statistical methods that would be easy to implement by DHI organizations to solve this issue: the deletion of 1% of the extreme high and low predictive values (M1), the deletion of records based on the Global-H (GH) distance (M2), and the deletion of records based on the absolute fat residual value (M3). Additionally, the combinations of these three methods were investigated. A total of 346,818 milk samples were analyzed by MIR spectrometry to predict the contents of fat, protein, and fatty acids. Then, the same traits were also predicted externally using their corresponded standardized MIR spectra. The interest in cleaning procedures was assessed by estimating the root mean square differences (RMSDs) between those internal and external predicted phenotypes. All methods allowed for a decrease in the RMSD, with a gain ranging from 0.32% to 41.39%. Based on the obtained results, the “M1 and M2” combination should be preferred to be more parsimonious in the data loss, as it had the higher ratio of RMSD gain to data loss. This method deleted the records based on the 2% extreme predictions and a GH threshold set at 5. However, to ensure the lowest RMSD, the “M2 or M3” combination, considering a GH threshold of 5 and an absolute fat residual difference set at 0.30 g/dL of milk, was the most relevant. Both combinations involved M2 confirming the high interest of calculating the GH distance for all samples to predict. However, if it is impossible to estimate the GH distance due to a lack of relevant information to compute this statistical parameter, the obtained results recommended the use of M1 combined with M3. The limitation used in M3 must be adapted by the DHI, as this will depend on the spectral data and the equation used. The methodology proposed in this study can be generalized for other MIR-based phenotypes. |
| first_indexed | 2024-03-09T00:45:27Z |
| format | Article |
| id | doaj.art-2b07751b24b64f1babb3bee97de4518e |
| institution | Directory Open Access Journal |
| issn | 2076-2615 |
| language | English |
| last_indexed | 2024-03-09T00:45:27Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Animals |
| spelling | doaj.art-2b07751b24b64f1babb3bee97de4518e2023-12-11T17:33:09ZengMDPI AGAnimals2076-26152021-02-0111253310.3390/ani11020533Appropriate Data Quality Checks Improve the Reliability of Values Predicted from Milk Mid-Infrared SpectraLei Zhang0Chunfang Li1Frédéric Dehareng2Clément Grelet3Frédéric Colinet4Nicolas Gengler5Yves Brostaux6Hélène Soyeurt7TERRA Teaching and Research Centre, University of Liège—Gembloux Agro-Bio Tech, 5030 Gembloux, BelgiumHebei Livestock Breeding Station, Shijiazhuang 050000, ChinaValorisation of Agricultural Products Department, Walloon Agricultural Research Centre, 5030 Gembloux, BelgiumValorisation of Agricultural Products Department, Walloon Agricultural Research Centre, 5030 Gembloux, BelgiumTERRA Teaching and Research Centre, University of Liège—Gembloux Agro-Bio Tech, 5030 Gembloux, BelgiumTERRA Teaching and Research Centre, University of Liège—Gembloux Agro-Bio Tech, 5030 Gembloux, BelgiumTERRA Teaching and Research Centre, University of Liège—Gembloux Agro-Bio Tech, 5030 Gembloux, BelgiumTERRA Teaching and Research Centre, University of Liège—Gembloux Agro-Bio Tech, 5030 Gembloux, BelgiumThe use of abnormal milk mid-infrared (MIR) spectrum strongly affects prediction quality, even if the prediction equations used are accurate. So, this record must be detected after or before the prediction process to avoid erroneous spectral extrapolation or the use of poor-quality spectral data by dairy herd improvement (DHI) organizations. For financial or practical reasons, adapting the quality protocol currently used to improve the accuracy of fat and protein contents is unfeasible. This study proposed three different statistical methods that would be easy to implement by DHI organizations to solve this issue: the deletion of 1% of the extreme high and low predictive values (M1), the deletion of records based on the Global-H (GH) distance (M2), and the deletion of records based on the absolute fat residual value (M3). Additionally, the combinations of these three methods were investigated. A total of 346,818 milk samples were analyzed by MIR spectrometry to predict the contents of fat, protein, and fatty acids. Then, the same traits were also predicted externally using their corresponded standardized MIR spectra. The interest in cleaning procedures was assessed by estimating the root mean square differences (RMSDs) between those internal and external predicted phenotypes. All methods allowed for a decrease in the RMSD, with a gain ranging from 0.32% to 41.39%. Based on the obtained results, the “M1 and M2” combination should be preferred to be more parsimonious in the data loss, as it had the higher ratio of RMSD gain to data loss. This method deleted the records based on the 2% extreme predictions and a GH threshold set at 5. However, to ensure the lowest RMSD, the “M2 or M3” combination, considering a GH threshold of 5 and an absolute fat residual difference set at 0.30 g/dL of milk, was the most relevant. Both combinations involved M2 confirming the high interest of calculating the GH distance for all samples to predict. However, if it is impossible to estimate the GH distance due to a lack of relevant information to compute this statistical parameter, the obtained results recommended the use of M1 combined with M3. The limitation used in M3 must be adapted by the DHI, as this will depend on the spectral data and the equation used. The methodology proposed in this study can be generalized for other MIR-based phenotypes.https://www.mdpi.com/2076-2615/11/2/533milk-component predictionmid-infrared spectrumMahalanobis distancequality-assurance systemHolstein cow |
| spellingShingle | Lei Zhang Chunfang Li Frédéric Dehareng Clément Grelet Frédéric Colinet Nicolas Gengler Yves Brostaux Hélène Soyeurt Appropriate Data Quality Checks Improve the Reliability of Values Predicted from Milk Mid-Infrared Spectra Animals milk-component prediction mid-infrared spectrum Mahalanobis distance quality-assurance system Holstein cow |
| title | Appropriate Data Quality Checks Improve the Reliability of Values Predicted from Milk Mid-Infrared Spectra |
| title_full | Appropriate Data Quality Checks Improve the Reliability of Values Predicted from Milk Mid-Infrared Spectra |
| title_fullStr | Appropriate Data Quality Checks Improve the Reliability of Values Predicted from Milk Mid-Infrared Spectra |
| title_full_unstemmed | Appropriate Data Quality Checks Improve the Reliability of Values Predicted from Milk Mid-Infrared Spectra |
| title_short | Appropriate Data Quality Checks Improve the Reliability of Values Predicted from Milk Mid-Infrared Spectra |
| title_sort | appropriate data quality checks improve the reliability of values predicted from milk mid infrared spectra |
| topic | milk-component prediction mid-infrared spectrum Mahalanobis distance quality-assurance system Holstein cow |
| url | https://www.mdpi.com/2076-2615/11/2/533 |
| work_keys_str_mv | AT leizhang appropriatedataqualitychecksimprovethereliabilityofvaluespredictedfrommilkmidinfraredspectra AT chunfangli appropriatedataqualitychecksimprovethereliabilityofvaluespredictedfrommilkmidinfraredspectra AT fredericdehareng appropriatedataqualitychecksimprovethereliabilityofvaluespredictedfrommilkmidinfraredspectra AT clementgrelet appropriatedataqualitychecksimprovethereliabilityofvaluespredictedfrommilkmidinfraredspectra AT fredericcolinet appropriatedataqualitychecksimprovethereliabilityofvaluespredictedfrommilkmidinfraredspectra AT nicolasgengler appropriatedataqualitychecksimprovethereliabilityofvaluespredictedfrommilkmidinfraredspectra AT yvesbrostaux appropriatedataqualitychecksimprovethereliabilityofvaluespredictedfrommilkmidinfraredspectra AT helenesoyeurt appropriatedataqualitychecksimprovethereliabilityofvaluespredictedfrommilkmidinfraredspectra |