EUVIMEDEUVIMED entdecken
ValidierungsstudieMultizentrische Studie

Predicting return to sport after multiligament knee injuries using machine learning: development and internal validation of a clinical algorithm

Carlos Suarez-Ahedo, Francisco Endara-Urresta, Carlos Peñaherrera-Carrillo, Alejandro Barros-Castro

The Knee · 2025

DOI: 10.1016/j.knee.2025.10.003 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift The Knee, 2025. Verfasst von Carlos Suarez-Ahedo und 3 weiteren Autor:innen. Beteiligte Einrichtung: Adult Hip and Knee Reconstruction Department. National Rehabilitation Institute of Mexico. Mexico City, Mexico. Electronic address: drsuarezahedo@gma…. Hauptthemen laut MEDLINE: Machine Learning, Return to Sport, Knee Injuries, Algorithms. Die Arbeit nennt 24 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: To develop and internally validate a machine learning-based predictive model to estimate the probability of return to sport (RTS) at 12 months after surgical reconstruction of multiligament knee injuries (MLKIs), and to identify the most influential clinical predictors. METHODS: Patients who underwent MLKIs reconstruction between 2012 and 2022 across three tertiary care centers were included. Inclusion criteria comprised reconstruction of ≥2 ligaments, age 18-50, and ≥12 months of follow-up. The primary outcome was RTS at 12 months. Predictive variables included demographic, clinical, surgical, and functional data. Four models were compared: logistic regression, support vector machine (SVM), random forest, and XGBoost. Model performance was assessed via 10-fold cross-validation using AUC-ROC, accuracy, sensitivity, specificity, F1-score, and Brier score. SHAP analysis was used to interpret feature importance. RESULTS: Among 220 patients, 60.9 % achieved RTS at 12 months. Machine learning models demonstrated strong predictive performance, with XGBoost yielding the highest accuracy (AUC = 0.84). Key predictors for RTS included a higher preinjury Tegner score, younger patient age, shorter time to surgery (

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningReturn to SportKnee InjuriesAlgorithmsLigaments, ArticularHumansMaleFemaleAdultMiddle AgedYoung AdultAdolescentRetrospective Studies

Stichwörter der Autor:innen

Functional outcomeMachine learningMultiligament knee injuryPredictive modelingSHAP analysisSports medicine

Autor:innen und Institutionen

  • Adult Hip and Knee Reconstruction Department. National Rehabilitation Institute of Mexico. Mexico City, Mexico. Electronic address: drsuarezahedo@gmail.com.
  • Specialist in Orthopedics and Traumatology. Arhtros Clinic. Quito-Ecuador, Ecuador. Electronic address: fren9123@hotmail.com.
  • Specialist in Orthopedics and Traumatology. Fellow in Adult Hip and Knee Reconstruction. National Rehabilitation Institute of Mexico. Mexico City, Mexico. Electronic address: carlospenaherrerac@gmail.com.
  • Resident in Orthopedics and Traumatology. Metropolitan Hospital. International University of Ecuador. Quito-Ecuador, Ecuador. Electronic address: alejandroxbc27@gmail.com.

Zitieren

APA

Suarez-Ahedo, C., Endara-Urresta, F., Peñaherrera-Carrillo, C., & Barros-Castro, A. (2025). Predicting return to sport after multiligament knee injuries using machine learning: development and internal validation of a clinical algorithm. The Knee. https://doi.org/10.1016/j.knee.2025.10.003

Vancouver

Suarez-Ahedo C, Endara-Urresta F, Peñaherrera-Carrillo C, Barros-Castro A. Predicting return to sport after multiligament knee injuries using machine learning: development and internal validation of a clinical algorithm. The Knee. 2025. doi:10.1016/j.knee.2025.10.003

BibTeX
@article{SuarezAhedo2025,
  author = {Suarez-Ahedo, Carlos and Endara-Urresta, Francisco and Peñaherrera-Carrillo, Carlos and Barros-Castro, Alejandro},
  title = {Predicting return to sport after multiligament knee injuries using machine learning: development and internal validation of a clinical algorithm},
  journal = {The Knee},
  year = {2025},
  doi = {10.1016/j.knee.2025.10.003}
}
Kostenlos starten →