Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Apr;33(4):1488-1499.
doi: 10.1002/ksa.12443. Epub 2024 Sep 26.

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

Sanne H van Spanning  1   2   3   4 , Lukas P E Verweij  3   5   6 , Laurent A M Hendrickx  6   7 , Laurens J H Allaart  1   2   3 , George S Athwal  8 , Thibault Lafosse  1 , Laurent Lafosse  1 , Job N Doornberg  7   9 , Jacobien H F Oosterhoff  10 , Michel P J van den Bekerom  3   4   5 , Geert Alexander Buijze  1   6   11 ; Machine Learning Consortium
Collaborators, Affiliations

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

Sanne H van Spanning et al. Knee Surg Sports Traumatol Arthrosc. 2025 Apr.

Abstract

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 <35 years, participation in contact and collision sports, bony Bankart lesions and full-thickness rotator cuff tears increased the risk of recurrence (all p < 0.05). A single shoulder dislocation (compared to multiple dislocations) lowered the risk of recurrence (p < 0.05). Due to the unavailability of certain variables in some patients, a portion of the patient data had to be excluded before pooling the data set to create the algorithm. A total of 797 patients were included providing information on risk factors associated with recurrence. The discrimination (area under the receiver operating curve) ranged between 0.54 and 0.57 for prediction of recurrence.

Conclusion: ML was not able to predict the recurrence following ABR with the current available predictors. Despite a global coordinated effort, the heterogeneity of clinical data limited the predictive capabilities of the algorithm, emphasizing the need for standardized data collection methods in future studies.

Level of evidence: Level IV, retrospective cohort study.

Keywords: arthroscopic Bankart repair; artificial intelligence; dislocation; machine learning algorithm; recurrence; shoulder instability.

PubMed Disclaimer

Conflict of interest statement

Dr. Laurens J. H. Allaart reports personal fees from Stryker, ConMed, Exatech, PercisionOS, Parvizi Surgical Innovation and Reach Orthopedics and has a patent pending to Exatech, ConMed and Stryker. Dr. Geert Alexander Buijze reports grants from SECEC, Vivalto Sante, personal fees from Depuy‐Synthes. Dr. Michel P. J. van den Bekerom reports grants for clinical and research fellowships supported by Smith and Nephew. Dr. Laurent Lafosse reports personal fees from Stryker, Smith and Nephew, Depuy. Dr. Thibault Lafosse reports personal fees from Stryker, Smith and Nephew, Depuy. The other authors have nothing to disclose. None of the fees above were related to the current study.

References

    1. Alkaduhimi, H. , Connelly, J.W. , van Deurzen, D.F.P. , Eygendaal, D. & van den Bekerom, M.P.J. (2021) High variability of the definition of recurrent glenohumeral instability: an analysis of the current literature by a systematic review. Arthroscopy, Sports Medicine, and Rehabilitation, 3, e951–e966. Available from: 10.1016/j.asmr.2021.02.002 - DOI - PMC - PubMed
    1. Austin, P.C. & Steyerberg, E.W. (2017) Events per variable (EPV) and the relative performance of different strategies for estimating the out‐of‐sample validity of logistic regression models. Statistical Methods in Medical Research, 26, 796–808. Available from: 10.1177/0962280214558972 - DOI - PMC - PubMed
    1. Balg, F. & Boileau, P. (2007) The instability severity index score. A simple pre‐operative score to select patients for arthroscopic or open shoulder stabilisation. The Journal of Bone and Joint Surgery. British Volume, 89, 1470–1477. Available from: 10.1302/0301-620X.89B11.18962 - DOI - PubMed
    1. Breiman, L. (2001) Random forests. Machine Learning, 45, 5–32. Available from: 10.1023/A:1010933404324 - DOI
    1. Collins, G.S. , Moons, K.G.M. , Dhiman, P. , Riley, R.D. , Beam, A.L. , Van Calster, B. , et al. (2024) TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ, 385, e078378. Available from: 10.1136/bmj-2023-078378 - DOI - PMC - PubMed