Stijn R. J. Mennes

Stijn R. J. Mennes

Auto-generated profile, based on publicly available information

Stijn R. J. Mennes

Shoulder and Elbow Unit, Department of Orthopaedic and Trauma Surgery, OLVG Hospital, Amsterdam, the Netherlands

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 January 2026 in Clinical Orthopaedics and Related Research
Verified
Journal Article
Closed access
SMStijn R. J. Mennes
Stijn R. J. Mennes
SESebastian Engbers
Sebastian Engbers
BGBjarty L. Garcia
Bjarty L. Garcia
RSReinier W. A. Spek
Reinier W. A. Spek
RMRoelina Munnik-Hagewoud
Roelina Munnik-Hagewoud
MBMichel P. J. van Den Bekerom
Michel P. J. van Den Bekerom
Background: Proximal humerus fractures (PHFs) in patients ≥ 65 years of age are associated with increased risk of death in the months after injury. Controversy exists regarding the preferred treatment strategy in these patients, and operative treatment is associated with high complication and reoperation rates. Machine learning (ML)–driven probability calculators for mortality prediction therefore may be valuable during shared decision-making for surgeons and patients. Questions/purposes: (1) To develop ML algorithms to predict 1-year mortality in patients ≥ 65 years of age. (2) To externally validate all algorithms on a geographically distinct patient population. (3) To create an easy-to-use, online calculator that can be used by surgeons at the point of care to enable more informed decision-making. Methods: This study identified 5114 potentially eligible patients age ≥ 65 years who presented to our two hospitals in Holland (one is a Level 1 trauma center and one is a Level 2 trauma center) between January 2016 and December 2023. Of those, we considered 3488 patients eligible because they were ≥ 65 years of age and had a first-time PHF. Based on that, 86% (2999) were included for the analysis. A further 10% (334) were excluded because of misdiagnosis, bilateral PHFs, or a history of previous PHFs. Finally, 4% (155) had an irretrievable mortality status or had incomplete data sets. Data on 24 potential factors associated with increased mortality after PHFs were collected. Surgical or nonoperative treatment were not included as the aim was to predict 1-year mortality at the moment a PHF was sustained, before a treatment choice had been made. Therefore, excluding treatment modalities does not limit the intended use as a pretreatment risk estimation model. Four ML algorithms were developed: logistic regression, extreme gradient boosting machine (XGBoost), random forest, and LightGBM. The ML algorithms were trained and internally validated on patients from the first hospital (59% [1768 of 2999]) and externally validated on a geographically distinct group of patients from the second hospital (41% [1231 of 2999]). The mean ± SD age in the training cohort was 77 ± 8 years, and it was 76 ± 8 years in the external validation set; 79% (2383 of 2999) of patients were female. The overall 1-year mortality rate was 11% (325 of 2999). Performance was assessed with discrimination and calibration curves, and overall performance was assessed using the Brier score. Discrimination was assessed with the c-statistic: the area under the receiver operating characteristic curve. The c-statistic ranges from 0.50 to 1.0, with 1.0 indicating perfect discriminating ability. Calibration was assessed by plotting the agreement between the observed outcome and predicted probability, and the intercept and slope were determined. The plot’s intercept indicates whether predictions were too high (intercept < 0) or too low (intercept > 0). The slope reflects either overfitting (predictions too extreme, slope > 1) or underfitting (predictions not extreme enough, slope < 1). An ideal prediction model has a calibration curve with an intercept of 0 and a slope of 1. The Brier score reflects the overall performance, a composite of discrimination and calibration. A score of 0 reflects perfect prediction and 1 indicates the worst prediction. Negative and positive predictive values were also assessed. For internal validation, fivefold cross-validation was performed to prevent data leakage, and 1000-fold bootstrapping was used to ensure robust results and account for optimism. Cross-validation entails dividing the training set into subsets (five), and the models are subsequently trained on four sets. The fifth, unseen set is used for internal validation and prevents overestimated model performance. For external validation, performance was assessed using only 1000-fold bootstrapping to ensure robust results and correct for optimism. Results: Algorithms performed similarly with c-statistics (discriminative ability), ranging from 0.80 to 0.81 (95% confidence interval [CI] 0.72 to 0.86) in internal validation and 0.83 to 0.85 (95% CI 0.81 to 0.86) in external validation. C-statistics exceeding 0.80 are considered a strong performance for mortality prediction models in geriatric trauma populations. Logistic regression was chosen as the best model from among those evaluated because of adequate calibration and interpretability. The strong calibration ensures that the model is not subject to overfitting or underfitting and does not predict too high or low. Logistic regression is interpretable as it needs fewer predictors and provides comprehensible coefficients. The negative predictive value was 0.91 (95% CI 0.90 to 0.92), the positive predictive value 0.66 (95% CI 0.54 to 0.81), and the factors most strongly associated with mortality were hemiplegia, prefracture residence in a healthcare institution, and heart failure. Conclusion: This study developed and externally validated an ML-driven prediction model that accurately provides the 1-year mortality risk for an individual patient. This tool for prognosis estimation can be used by physicians during shared decision-making and patient counseling, as it enhances the informed consent process by providing patients and families with realistic expectations when considering treatment options for PHFs. The prediction tool was incorporated into a freely available web application and can be accessed through https://bjarty.shinyapps.io/mortality_app/. Level of Evidence: Level III, therapeutic study.

15 January 2026 in JSES International
Verified
Journal Article
Open access
SMStijn R.J. Mennes
Stijn R.J. Mennes
ISIgor J. Shirinskiy
Igor J. Shirinskiy
CKCharmaine E.M. Kool
Charmaine E.M. Kool
ETEric D. Tutuhatunewa
Eric D. Tutuhatunewa
RBRonald L.A.W. Bleys
Ronald L.A.W. Bleys
LKLaura M. Kok
Laura M. Kok
It is not clear whether cortical fibular allografts or cancellous femoral allografts provide similar stability for augmentation of locking plate fixation of proximal humerus fractures. Therefore, this study aimed to assess and compare biomechanical properties of augmented locking plate fixation with 1) a cortical fibular allograft and 2) a cancellous femoral allograft. Twenty-two fresh frozen humeri were randomly allocated to undergo unstable three-part fracture creation, locking plate fixation, and augmentation with cortical fibular or cancellous femoral allografts. All constructs were tested with cyclic loading (5 N to 532.5 N) for 1000 cycles at 1 Hz. Subsequently, constructs were loaded to 1700 N. Loss of humeral head height (HHH), ultimate failure loads, mode of failure, and stiffness were assessed. Twenty humeri were included in the analysis. No failure occurred during cyclic loading. During load-to-failure testing, four (40.0%) fibula-augmented constructs and six (60.0%) femoral-augmented constructs failed. During cyclic loading, median loss of HHH was 2.00 (interquartile range [IQR], 1.12-3.50) for fibular grafts and 2.75 (IQR, 2.00-3.00) femoral grafts (P = .40). Median loss of HHH during failure tests was 9.50 (IQR, 7.88-15.50) for fibular grafts and 9.50 (IQR, 8.50-10.90) for femoral grafts (P = .68). The stiffness for fibular grafts was 174 (IQR, 106-186) and 157 for femoral grafts (IQR, 134-192) (P = .97). There is no significant difference in biomechanical stability between cortical fibular allograft augmentation and cancellous hip allograft augmentation for locking plate fixation in proximal humerus fractures. Both techniques may equally prevent loss of reduction and early screw protrusion. Cancellous femoral allografts may yield advantages considering costs, availability, and future revision surgery with arthroplasty when compared to cortical fibular allografts.

22 August 2026 in JSES Reviews, Reports, and Techniques
Verified
Journal Article
Open access
SMStijn R.J. Mennes
Stijn R.J. Mennes
HKHuub H. de Klerk
Huub H. de Klerk
RSReinier W.A. Spek
Reinier W.A. Spek
NCNeal C. Chen
Neal C. Chen
RLRoss K. Leighton
Ross K. Leighton
JWJ.W. White
J.W. White

4 November 2026 in Injury
Verified
Journal Article
Closed access
NTNeeltje M. Trouwborst
Neeltje M. Trouwborst
KDKaj Ten Duis
Kaj Ten Duis
HAHamed Ayoobi
Hamed Ayoobi
NANick Assink
Nick Assink
JDJob N. Doornberg
Job N. Doornberg
FIFrank F.A. Ijpma
Frank F.A. Ijpma

14 August 2026 in JSES International
Verified
Journal Article
Open access
SMStijn R.J. Mennes
Stijn R.J. Mennes
AMAnne M.L. Meesters
Anne M.L. Meesters
MBMichel P.J. van Den Bekerom
Michel P.J. van Den Bekerom
RJRuurd L. Jaarsma
Ruurd L. Jaarsma
JDJob N. Doornberg
Job N. Doornberg
NANick Assink
Nick Assink
Corrective osteotomies for malunions after proximal humerus fractures are reserved for selected cases. These procedures are technically demanding, and surgical planning based on two-dimensional imaging, with free-hand operative correction, may lead to surgical inaccuracy. Three-dimensional (3D) pre-operative planning combined with patient-specific surgical guides and surgical simulation can overcome this issue. This study introduces 3D patient-specific guides for corrective osteotomies in proximal humeral malunions and determines the accuracy of achieved correction in human cadaveric shoulders with 2 innovative surgical techniques. Seven reversed corrective osteotomies were planned and performed on 4 Thiel-embalmed human specimens using 7 different respective 3D patient-specific cutting and reduction guides. Computed tomography scans were used to create 3D segmentations of all specimens. Subsequently, virtual surgical plans of osteotomies were created, and 3D-printed patient-specific cutting and reposition guides were designed and produced. Three humeri underwent an "extracapsular" corrective osteotomy, and 4 humeri underwent correction using a novel "humeral head-tuberosity separation" technique. Accuracy was assessed for valgus angulation and rotation by comparing pre-operative planning with post-operative results quantified with computed tomography scans. The overall median difference between pre-operative planning and post-operative results was 5.2° (min-max: 2.9°-8.5°) for rotation and 3.4° (min-max: 2.4°-5.8°) for valgus angulation. For the "extracapsular" method, the median difference was 5.2° (min-max: 2.9°-7.0°) for rotation and 3.9° (min-max: 3.2°-5.8°) for valgus angulation. The median differences in rotation and valgus angulation for the "humeral head-tuberosity separation" corrections were 6.3° (min-max: 3.6°-8.5°) and 3.1° (min-max: 2.4°-3.6°), respectively. The application of 3D surgical planning and patient-specific guides is feasible for corrective osteotomies of malunited proximal humerus and resulted in reconstructions with less than 10° deviation from pre-operative planning, demonstrating acceptable technical accuracy and supporting the potential of this approach for future clinical application. The extracapsular osteotomy technique may serve as a solution for malunions with an intact anatomic relationship between the humeral head and greater tuberosity, whereas the novel osteotomy may be a solution for severe malunions with disrupted anatomy between the humeral head, greater tuberosity, and surgical neck. Future studies need to evaluate the use of the proposed techniques in patients with actual proximal humeral malunions.

17 July 2026 in Journal of Shoulder and Elbow Surgery
Verified
Journal Article
Open access
SMStijn R.J. Mennes
Stijn R.J. Mennes
RSReinier W.A. Spek
Reinier W.A. Spek
XZXingyuan Zhang
Xingyuan Zhang
XQXuyin Qi
Xuyin Qi
ZLZhibin Liao
Zhibin Liao
YZYang Zhao
Yang Zhao
Agreement between surgeons on classification, characterization and choice of treatment for proximal humerus fractures (PHFs) is poor, leading to subjective surgical decision-making and poor inter-surgeon reliability. Machine Learning for classification and characterization of PHFs on radiographs performed insufficiently. More detailed three-dimensional (3D) configuration of PHFs on Computed Tomography (CT) scans may improve performance. This study aimed to 1) develop and internally validate a Convolutional Neural Network (CNN) on CT-scans, 2) externally validate the model, and 3) compare characterization performance with orthopedic surgeons. A 3D DenseNet was trained and internally validated on 581 Australian PHF patients with CT-scans, and externally validated geographically on 122 Dutch patients. Ground truth was established through multirater consensus. Fractures were classified as: a) none- to minimally displaced; b) two-part; c) multipart; or d) glenohumeral dislocation, and characterized on: a) greater tuberosity (GT) displacement ≥1 cm; b) varus malalignment (neck-shaft angle ≤100°); c) shaft translation; and d) articular involvement. All fractures were annotated with a bounding cube. The algorithm's performance was assessed with accuracy, area under the receiver operating characteristic curve, sensitivity, specificity, and negative and positive predictive values. Diagnostic accuracy for fracture classification was 78.6% (AUC's 0.87-0.99). The DenseNet could accurately characterize GT displacement (accuracy 80.3%, AUC 0.88), varus malalignment (accuracy 87.2%, AUC 0.91) but performance for subclasses of shaft translation (accuracy substantial translation 16.7%) and articular involvement (accuracy head-split 0%) was insufficient. The DenseNet was on par with orthopedic surgeons for GT displacement and varus angulation, and achieved higher overall accuracy than surgeons on shaft translation and articular involvement (p<0.001). Notably, algorithm performance in some subclasses (substantial and entire shaft translation, head-splits) was worse. This open-source CNN accurately classified and characterized PHFs for GT displacement and varus malalignment on CT-scans. AI performance for shaft translation and articular involvement was better than surgeons, but had insufficient areas under the curve. Performance of PHF classification and characterization of greater tuberosity displacement and varus angulation is strong and ready for prospective evaluation. For articular involvement and shaft translation, adding more data is needed to improve model performance. The code is available through https://github.com/Richardqiyi/classification-and-characterisation-of-PHFs. Basic Science Study, Computer Modeling using Machine Learning.