EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Methodology and development of a machine learning probability calculator: Data heterogeneity limits ability to predict recurrence after arthroscopic Bankart repair

Sanne H van Spanning, Lukas P E Verweij, Laurent A M Hendrickx, Laurens J H Allaart, George S Athwal, Thibault Lafosse, Laurent Lafosse, Job N Doornberg, Jacobien H F Oosterhoff, Michel P J van den Bekerom, Geert Alexander Buijze, Machine Learning Consortium

Knee Surgery, Sports Traumatology, Arthroscopy · 2025

DOI: 10.1002/ksa.12443 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Knee Surgery, Sports Traumatology, Arthroscopy, 2025. Verfasst von Sanne H van Spanning und 11 weiteren Autor:innen. Beteiligte Einrichtung: Alps Surgery Institute, Hand, Upper Limb, Peripheral Nerve, Brachial Plexus and Microsurgery Unit, Clinique Générale, Annecy, France. Hauptthemen laut MEDLINE: Machine Learning, Arthroscopy, Shoulder Dislocation, Joint Instability. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This research received no specific grant from any funding agency in the public, commercial or not-for-profit sectors..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

The aim of this study was to develop and train a machine learning (ML) algorithm to create a clinical decision support tool (i.e., ML‐driven probability calculator) to be used in clinical practice to estimate recurrence rates following an arthroscopic Bankart repair (ABR).

Methods

Data from 14 previously published studies were collected. Inclusion criteria were (1) patients treated with ABR without remplissage for traumatic anterior shoulder instability and (2) a minimum of 2 years follow‐up. Risk factors associated with recurrence were identified using bivariate logistic regression analysis. Subsequently, four ML algorithms were developed and internally validated. The predictive performance was assessed using discrimination, calibration and the Brier score.

Results

In total, 5591 patients underwent ABR with a recurrence rate of 15.4% ( n = 862). Age

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningArthroscopyShoulder DislocationJoint InstabilityBankart LesionsHumansRecurrenceAdultMaleFemaleAlgorithmsRisk FactorsRetrospective Studies

Stichwörter der Autor:innen

arthroscopic Bankart repairartificial intelligencedislocationmachine learning algorithmrecurrenceshoulder instability

Autor:innen und Institutionen

  • Alps Surgery Institute, Hand, Upper Limb, Peripheral Nerve, Brachial Plexus and Microsurgery Unit, Clinique Générale, Annecy, France.
  • Amsterdam Shoulder and Elbow Centre of Expertise (ASECE), Amsterdam, The Netherlands.
  • Department of Human Movement Sciences, Faculty of Behavioural and Movement Sciences, Vrije Universiteit Amsterdam, Amsterdam Movement Sciences, Amsterdam, The Netherlands.
  • Department of Orthopedic Surgery, OLVG, Shoulder and Elbow Unit, Amsterdam, The Netherlands.
  • Amsterdam Movement Sciences, Musculoskeletal Health Program, Amsterdam, The Netherlands.
  • Department of Amsterdam UMC, Department of Orthopedic Surgery and Sports Medicine, Location AMC, University of Amsterdam, Amsterdam, The Netherlands.

Förderung

  • This research received no specific grant from any funding agency in the public, commercial or not-for-profit sectors.

Zitieren

APA

van Spanning, S. H., Verweij, L. P. E., Hendrickx, L. A. M., Allaart, L. J. H., Athwal, G. S., Lafosse, T., Lafosse, L., Doornberg, J. N., Oosterhoff, J. H. F., van den Bekerom, M. P. J., Buijze, G. A., & Machine Learning Consortium (2025). Methodology and development of a machine learning probability calculator: Data heterogeneity limits ability to predict recurrence after arthroscopic Bankart repair. Knee Surgery, Sports Traumatology, Arthroscopy. https://doi.org/10.1002/ksa.12443

Vancouver

van Spanning SH, Verweij LPE, Hendrickx LAM, Allaart LJH, Athwal GS, Lafosse T, et al. Methodology and development of a machine learning probability calculator: Data heterogeneity limits ability to predict recurrence after arthroscopic Bankart repair. Knee Surgery, Sports Traumatology, Arthroscopy. 2025. doi:10.1002/ksa.12443

BibTeX
@article{vanSpanning2025,
  author = {van Spanning, Sanne H and Verweij, Lukas P E and Hendrickx, Laurent A M and Allaart, Laurens J H and Athwal, George S and Lafosse, Thibault and Lafosse, Laurent and Doornberg, Job N and Oosterhoff, Jacobien H F and van den Bekerom, Michel P J and Buijze, Geert Alexander and Machine Learning Consortium, Machine Learning Consortium},
  title = {Methodology and development of a machine learning probability calculator: Data heterogeneity limits ability to predict recurrence after arthroscopic Bankart repair},
  journal = {Knee Surgery, Sports Traumatology, Arthroscopy},
  year = {2025},
  doi = {10.1002/ksa.12443}
}
Kostenlos starten →