EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning Analysis of a Harmonized Multi-Experiment Dataset Suggests Phase-Dependent Predictability of Weight Gain in Salmonella-Challenged Pigs

Machine-Learning-Analyse eines harmonisierten Multi-Experiment-Datensatzes legt phasenabhängige Vorhersagbarkeit der Gewichtszunahme bei mit Salmonella belasteten Schweinen nahe

Gabriela Miotto Galli, Marcio Valk, Ines Andretta, Alícia Zem Fraga, Marcos Kipper, Ismael França, Pedro Righetti Arnaut, Graziela Alves da Cunha Valini, Luciano Hauschild

Veterinary Sciences · 26.10.2026 · 13 (11) · 1139

DOI: 10.3390/vetsci13111139 ↗

Auf einen Blick

Bei 230 Mastschweinen mit Salmonella-Typhimurium-Challenge war die Gewichtszunahme in der akuten Phase schlecht, in der chronischen Phase deutlich besser vorhersagbar.

Fragestellung

Wie gut lässt sich die Gewichtszunahme in der akuten und chronischen Phase nach Salmonella-Typhimurium-Challenge aus Basisdaten vorhersagen?

Methode

Zusammenführung von Daten aus 4 Experimenten mit 230 Schweinen; Vergleich mehrerer Modelle mit individueller fünf-facher Kreuzvalidierung.

Ergebnisse

Akutphase: RWG7 n = 132, cross-validated R2 0,078 bis 0,186. Chronische Phase: RWG7–28 n = 131, Linear Model R2 0,419 und Elastic Net R2 0,420. Random Forest und XGBoost zeigten In-sample-Überanpassung.

Einschränkungen

Experiment-held-out oder externe Validierung fehlte; Ergebnisse sind explorativ und hypothesengenerierend.

Schlussfolgerung der Autor:innen

Die akute Phase ließ sich aus Basisinformationen nur schlecht vorhersagen, die chronische Phase zeigte ein stärkeres internes Vorhersagesignal.

Kernaussagen

  • Akutphase: geringe Vorhersagbarkeit der RWG7
  • Chronische Phase: höhere Vorhersagbarkeit der RWG7–28
  • Random Forest und XGBoost wirkten überangepasst

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift Veterinary Sciences, online erschienen am 26.10.2026. Verfasst von Gabriela Miotto Galli und 8 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: São Paulo Research Foundation, Brazilian National Council for Scientific and Technological Development.

Auf einen BlickAbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study aimed to evaluate the internal predictability of weight gain using an integrated dataset derived from four experiments conducted with growing–finishing pigs subjected to a common Salmonella Typhimurium challenge protocol. Individual-animal data from 230 pigs were harmonized into a database containing growth performance, body composition, serum biochemical measurements, and experiment-level information. Relative weight gain, calculated relative to body weight at the beginning of each evaluation period, was evaluated separately during the acute phase, from days 0 to 7 post-challenge (RWG7; n = 132), and the chronic phase, from days 7 to 28 post-challenge (RWG7–28; n = 131). Linear Model, Elastic Net, Random Forest, XGBoost, Generalized Additive Models, and Support Vector Machine were compared using individual-level five-fold cross-validation, in which pigs from the same source experiment could occur in both training and validation folds. Single regression trees were additionally fitted as exploratory tools. During the acute phase, cross-validated R2 values ranged from 0.078 to 0.186, indicating that the available baseline variables explained only a limited proportion of the variation in RWG7. Predictive performance was higher during the chronic phase, particularly for the Linear Model and Elastic Net, which showed essentially equivalent cross-validated performance, with R2 values of 0.419 and 0.420, respectively. Random Forest and XGBoost achieved high in-sample performance but substantially lower out-of-fold performance, suggesting overfitting structures within the integrated dataset. Body weight, body composition, biochemical variables, and the source experiment contributed to model predictions, indicating that the predictive signal incorporated information related to both individual physiological status and between-experiment heterogeneity. Overall, acute-phase growth performance was poorly predicted from baseline information, whereas chronic-phase growth showed a stronger internal predictive signal. This comparison reflects differences in the predictor information available at the beginning of each phase, as chronic-phase models additionally incorporated body weight and relative weight gain measured on day 7. These results should be interpreted as exploratory and hypothesis-generating because experiment-held-out or external validation is required before extrapolation to independent experimental or commercial populations.

Förderung

  • São Paulo Research Foundation
  • Brazilian National Council for Scientific and Technological Development

Zitieren

APA

Galli, G. M., Valk, M., Andretta, I., Fraga, A. Z., Kipper, M., França, I., Arnaut, P. R., Valini, G. A. D. C., & Hauschild, L. (2026). Machine Learning Analysis of a Harmonized Multi-Experiment Dataset Suggests Phase-Dependent Predictability of Weight Gain in Salmonella-Challenged Pigs. Veterinary Sciences, 13(11), 1139. https://doi.org/10.3390/vetsci13111139

Vancouver

Galli GM, Valk M, Andretta I, Fraga AZ, Kipper M, França I, et al. Machine Learning Analysis of a Harmonized Multi-Experiment Dataset Suggests Phase-Dependent Predictability of Weight Gain in Salmonella-Challenged Pigs. Veterinary Sciences. 2026;13(11):1139. doi:10.3390/vetsci13111139

BibTeX
@article{Galli2026,
  author = {Galli, Gabriela Miotto and Valk, Marcio and Andretta, Ines and Fraga, Alícia Zem and Kipper, Marcos and França, Ismael and Arnaut, Pedro Righetti and Valini, Graziela Alves da Cunha and Hauschild, Luciano},
  title = {Machine Learning Analysis of a Harmonized Multi-Experiment Dataset Suggests Phase-Dependent Predictability of Weight Gain in Salmonella-Challenged Pigs},
  journal = {Veterinary Sciences},
  year = {2026},
  volume = {13},
  number = {11},
  pages = {1139},
  doi = {10.3390/vetsci13111139}
}
Kostenlos starten →