EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine learning and quantitative computed tomography radiomics prediction of postoperative functional recovery in paraplegic dogs

Daniel Low iD, Scott Rutherford iD

Veterinary Surgery · 2025

DOI: 10.1111/vsu.70016 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Veterinary Surgery, 2025. Verfasst von Daniel Low und 1 weiteren Autor:innen. Beteiligte Einrichtung: Frank. Pet Surgeons, Leeds, UK. Hauptthemen laut MEDLINE: Dog Diseases, Paraplegia, Machine Learning, Tomography, X-Ray Computed. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: IVC Evidensia.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

To develop a computed tomography (CT)‐radiomics‐based machine‐learning algorithm for prediction of functional recovery in paraplegic dogs with acute intervertebral disc extrusion (IVDE). Study design Multivariable prediction model development. Sample population Paraplegic dogs with acute IVDE: 128 deep‐pain positive and 86 deep‐pain negative (DPN).

Methods

Radiomics features from noncontrast CT were combined with deep‐pain perception in an extreme gradient algorithm using an 80:20 train–test split. Model performance was assessed on the independent test set (Test full ) and on the test set of DPN dogs (Test DPN ). Deep‐pain perception alone served as the control.

Results

Recovery of ambulation was recorded in 165/214 dogs (77.1%) after decompressive surgery. The model had an area under the receiver operating characteristic curve (AUC) of .9118 (95% CI: .8366–.9872), accuracy of 86.1% (95% CI: 74.4%–95.4%), sensitivity of 82.4% (95% CI: 68.6%–93.9%), and specificity of 100.0% (95% CI: 100.0%–100.0%) on Test full , and an AUC of .7692 (95% CI: .6250–.9000), accuracy of 72.7% (95% CI: 50.0%–90.9%), sensitivity of 53.8% (95% CI: 25.0%–80.0%), and specificity of 100.0% (95% CI: 100.0%–100.0%) on Test DPN . Deep‐pain perception had an AUC of .8088 (95% CI: .7273–.8871), accuracy of 69.8% (95% CI: 55.8%–83.7%), sensitivity of 61.8% (95% CI: 45.5%–77.4%), and specificity of 100.0% (95% CI: 100.0%–100.0%), which was different from that of the model ( p = .02).

Conclusion

Noncontrast CT‐based radiomics provided prognostic information in dogs with severe spinal cord injury secondary to acute intervertebral disc extrusion. The model outperformed deep‐pain perception alone in identifying dogs that recovered ambulation following decompressive surgery. Clinical significance Radiomics features from noncontrast CT, when integrated into a multimodal machine‐learning algorithm, may be useful as an assistive tool for surgical decision making.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Dog DiseasesParaplegiaMachine LearningTomography, X-Ray ComputedIntervertebral Disc DisplacementAnimalsDogsMaleFemaleRecovery of FunctionDecompression, SurgicalRadiomics

Autor:innen und Institutionen

  • Frank. Pet Surgeons, Leeds, UK.
  • Swift Referrals, Wetherby, UK.

ORCID-Profile: Daniel Low, Scott Rutherford

Förderung

  • IVC Evidensia

Zitieren

APA

Low, D., & Rutherford, S. (2025). Machine learning and quantitative computed tomography radiomics prediction of postoperative functional recovery in paraplegic dogs. Veterinary Surgery. https://doi.org/10.1111/vsu.70016

Vancouver

Low D, Rutherford S. Machine learning and quantitative computed tomography radiomics prediction of postoperative functional recovery in paraplegic dogs. Veterinary Surgery. 2025. doi:10.1111/vsu.70016

BibTeX
@article{Low2025,
  author = {Low, Daniel and Rutherford, Scott},
  title = {Machine learning and quantitative computed tomography radiomics prediction of postoperative functional recovery in paraplegic dogs},
  journal = {Veterinary Surgery},
  year = {2025},
  doi = {10.1111/vsu.70016}
}
Kostenlos starten →