EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Predicting classes of β-hydroxybutyrate concentrations in blood of dairy cows from milk mid-infrared spectra: Application of a weighted discriminant model addressing class imbalance

M Lesnoff, C Grelet, V Wolf, L Millot, A Köck, J Leblois, B Bapst, M A Crowe, T Larsen, D C Wathes, C P Ferris, K L Ingvartsen und 7 weitere

JDS Communications · 2026-11 · 7 (6) · 896-901

DOI: 10.3168/jdsc.2026-1074 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JDS Communications, 2026-11. Verfasst von M Lesnoff und 18 weiteren Autor:innen. Beteiligte Einrichtung: SELMET, Université Montpellier, CIRAD, INRAE, Institut Agro, Montpellier, France, 34398. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Seventh Framework Programme, Bundesministerium für Ernährung und Landwirtschaft, Interreg.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Monitoring biomarkers in milk or blood is widely used to assess dairy cow health and to detect diseases such as (sub)clinical ketosis. Blood BHB is a key indicator of metabolic imbalance, and its prediction from milk Fourier-transform mid-infrared (FT-MIR) spectra has been extensively explored. However, most of the predictive models applied in spectrometry fail to achieve acceptable accuracy because of the highly skewed distribution of BHB concentrations (many blood samples have low concentrations, but a few have high concentrations). Imbalanced distributions complicate both quantitative and class modeling. Thus, the objective of this work was to undertake discrete predictions of BHB (low versus high level) by implementing a specific weighting in a usual discrimination algorithm to overcome the class imbalance between healthy cows and those suffering from hyperketonemia. The threshold of 1.2 mmol/L was used to distinguish low from high BHB, that is, absence or presence of hyperketonemia. The cleaned dataset combined 4,221 records comprising milk FT-MIR spectra and blood BHB content that were collected across 10 countries between 2013 and 2024, and in multiple breeds, and numerous research projects. Milk MIR spectra (selected wavenumber regions, second derivative Savitzky-Golay preprocessing) served as predictors. A replicated external herd validation strategy was implemented. The weighted model outperformed the standard model, achieving average intraclass error rates of around 18% on external test sets. It reached 82% accuracy, 83% sensitivity, and 81% specificity, with these results comparable to or better than previously published discriminant models, despite using only raw MIR spectra. These findings demonstrate that the use of weighting within discriminant methods is a valid option for the class prediction of asymmetrically distributed health biomarkers.

Autor:innen und Institutionen

  • SELMET, Université Montpellier, CIRAD, INRAE, Institut Agro, Montpellier, France, 34398.
  • CIRAD, UMR SELMET, Montpellier, France, 34398.
  • ChemHouse Research Group, Montpellier, France, 34398.
  • Walloon Agricultural Research Center (CRA-W), Gembloux, Belgium, 5030.
  • CEL25-90, Roulans, France, 25640.
  • ZuchtData, Vienna, Austria, A-1200.

Förderung

  • Seventh Framework Programme
  • Bundesministerium für Ernährung und Landwirtschaft
  • Interreg
  • Waalse Gewest

Zitieren

APA

Lesnoff, M., Grelet, C., Wolf, V., Millot, L., Köck, A., Leblois, J., Bapst, B., Crowe, M. A., Larsen, T., Wathes, D. C., Ferris, C. P., Ingvartsen, K. L., Marchitelli, C., Becker, F., Hummel, J., Gelé, M., Soyeurt, H., Gengler, N., & Dehareng, F. (2026). Predicting classes of β-hydroxybutyrate concentrations in blood of dairy cows from milk mid-infrared spectra: Application of a weighted discriminant model addressing class imbalance. JDS Communications, 7(6), 896-901. https://doi.org/10.3168/jdsc.2026-1074

Vancouver

Lesnoff M, Grelet C, Wolf V, Millot L, Köck A, Leblois J, et al. Predicting classes of β-hydroxybutyrate concentrations in blood of dairy cows from milk mid-infrared spectra: Application of a weighted discriminant model addressing class imbalance. JDS Communications. 2026;7(6):896-901. doi:10.3168/jdsc.2026-1074

BibTeX
@article{Lesnoff2026,
  author = {Lesnoff, M and Grelet, C and Wolf, V and Millot, L and Köck, A and Leblois, J and Bapst, B and Crowe, M A and Larsen, T and Wathes, D C and Ferris, C P and Ingvartsen, K L and Marchitelli, C and Becker, F and Hummel, J and Gelé, M and Soyeurt, H and Gengler, N and Dehareng, F},
  title = {Predicting classes of β-hydroxybutyrate concentrations in blood of dairy cows from milk mid-infrared spectra: Application of a weighted discriminant model addressing class imbalance},
  journal = {JDS Communications},
  year = {2026},
  volume = {7},
  number = {6},
  pages = {896--901},
  doi = {10.3168/jdsc.2026-1074}
}
Kostenlos starten →