EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Evaluation of Machine Learning Models for TT-POCUS Based Prognostic Prediction of Did-Not-Finish and First-Treatment Failure Cattle Diagnosed with Bovine Respiratory Disease

Bewertung von Machine-Learning-Modellen für TT-POCUS-basierte Prognose von Did-Not-Finish und First-Treatment-Failure bei Rindern mit bovinem respiratorischem Syndrom

Hayden E. Kunnary, Brad J. White, Luis F. B. B. Feitoza, Robert L. Larson, Jordana A. R. Zimmermann, Tyler J. Spore

Veterinary Sciences · 06.11.2026 · 13 (11) · 1199

DOI: 10.3390/vetsci13111199 ↗

Auf einen Blick

Eine prospektive Kohortenstudie prüfte, ob TT-POCUS-Variablen Prognosemodelle für DNF und FTF bei Rindern mit BRD verbessern. Die besten AUC lagen bei 0,71, 0,80 und 0,84.

Fragestellung

Wie gut sagen Machine-Learning-Modelle mit TT-POCUS-Variablen DNF und FTF bei Rindern mit BRD voraus?

Methode

Prospektive Kohorten-Observationsstudie; TT-POCUS bei Studieneinschluss; 6 überwachte Machine-Learning-Algorithmen mit TT-POCUS- und Demografiedaten.

Ergebnisse

1422 First-treatment-Rinder und 150 chronic cattle. Für FTF hatte logistische Regression die höchste AUC (0,71). Für DNF bei First-treatment-Rindern: AUC 0,80; bei chronic cattle: Perceptron, AUC 0,84.

Schlussfolgerung der Autor:innen

TT-POCUS-abgeleitete Variablen lieferten relevante prognostische Informationen und könnten Behandlungsentscheidungen, den antimikrobiellen Einsatz und das Tierwohl unterstützen.

Kernaussagen

  • TT-POCUS wurde zur Prognose bei BRD-Rindern eingesetzt
  • Beste AUC: 0,71 für FTF, 0,80 für DNF, 0,84 bei chronic cattle
  • Logistische Regression und Perceptron erzielten die besten AUCs

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 06.11.2026. Verfasst von Hayden E. Kunnary und 5 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beef Cattle Institute Internal Grant.

Auf einen BlickAbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bovine respiratory disease remains the leading cause of morbidity and mortality in feedyard cattle and is associated with substantial economic and animal welfare consequences. Prognostic tools remain limited, but combining objective diagnostic measures with predictive modeling may improve clinical decision-making. This study evaluated the performance of machine learning models incorporating targeted thoracic point-of-care ultrasound (TT-POCUS)-derived variables to predict did-not-finish (DNF) and first-treatment failure (FTF) outcomes in feedyard cattle diagnosed with bovine respiratory disease (BRD). First-treatment cattle were evaluated for both FTF and DNF outcomes, whereas chronic cattle were evaluated for DNF outcomes following enrollment. A prospective cohort observational study was conducted in cattle receiving either first treatment or chronic treatment for BRD. TT-POCUS examinations were performed at enrollment to assess pulmonary abnormalities, including lung consolidation, pleural irregularities, B-lines, and lesion scores. A total of 1422 first-treatment cattle and 150 chronic cattle were enrolled. Six supervised machine learning algorithms were trained using TT-POCUS variables and demographic data. For FTF prediction, logistic regression demonstrated the highest AUC (0.71). For first-treatment DNF, logistic regression again achieved the highest AUC (0.80). In chronic cattle, the perceptron model demonstrated the highest AUC (0.84). Overall, TT-POCUS-derived variables provided meaningful prognostic information and may support improved treatment decisions, antimicrobial stewardship, and animal welfare in feedyard cattle.

Förderung

  • Beef Cattle Institute Internal Grant

Zitieren

APA

Kunnary, H. E., White, B. J., Feitoza, L. F. B. B., Larson, R. L., Zimmermann, J. A. R., & Spore, T. J. (2026). Evaluation of Machine Learning Models for TT-POCUS Based Prognostic Prediction of Did-Not-Finish and First-Treatment Failure Cattle Diagnosed with Bovine Respiratory Disease. Veterinary Sciences, 13(11), 1199. https://doi.org/10.3390/vetsci13111199

Vancouver

Kunnary HE, White BJ, Feitoza LFBB, Larson RL, Zimmermann JAR, Spore TJ. Evaluation of Machine Learning Models for TT-POCUS Based Prognostic Prediction of Did-Not-Finish and First-Treatment Failure Cattle Diagnosed with Bovine Respiratory Disease. Veterinary Sciences. 2026;13(11):1199. doi:10.3390/vetsci13111199

BibTeX
@article{Kunnary2026,
  author = {Kunnary, Hayden E. and White, Brad J. and Feitoza, Luis F. B. B. and Larson, Robert L. and Zimmermann, Jordana A. R. and Spore, Tyler J.},
  title = {Evaluation of Machine Learning Models for TT-POCUS Based Prognostic Prediction of Did-Not-Finish and First-Treatment Failure Cattle Diagnosed with Bovine Respiratory Disease},
  journal = {Veterinary Sciences},
  year = {2026},
  volume = {13},
  number = {11},
  pages = {1199},
  doi = {10.3390/vetsci13111199}
}
Kostenlos starten →