Patients With Femoral Neck Fractures Are at Risk for Conversion to Arthroplasty After Internal Fixation: A Machine-learning Algorithm

被引:5
作者
van de Kuit, Anouk [1 ]
Oosterhoff, Jacobien H. F. [2 ,3 ]
Dijkstra, Hidde [4 ]
Sprague, Sheila [5 ,6 ]
Bzovsky, Sofia [6 ]
Bhandari, Mohit [5 ,6 ]
Swiontkowski, Marc [7 ]
Schemitsch, Emil H. H. [8 ]
IJpma, Frank F. A. [4 ]
Poolman, Rudolf W. W. [9 ]
Doornberg, Job N. N. [1 ,4 ,10 ]
Hendrickx, Laurent A. M. [11 ]
机构
[1] Univ Groningen, Univ Med Ctr Groningen, Dept Orthopaed Surg, Groningen, Netherlands
[2] Harvard Med Sch, Massachusetts Gen Hosp, Dept Orthopaed Surg, Boston, MA USA
[3] Univ Amsterdam, Dept Orthopaed Surg, Amsterdam UMC, Amsterdam, Netherlands
[4] Univ Groningen, Univ Med Ctr Groningen, Dept Trauma Surg, Groningen, Netherlands
[5] McMaster Univ, Dept Hlth Res Methods Evidence & Impact, Hamilton, ON, Canada
[6] McMaster Univ, Dept Surg, Div Orthopaed Surg, Hamilton, ON, Canada
[7] Univ Minnesota, Dept Orthopaed Surg, Minneapolis, MN USA
[8] Western Univ, Dept Surg, London, ON, Canada
[9] Univ Med Ctr Leiden, Leiden Univ, Dept Orthopaed Surg, Leiden, Netherlands
[10] Flinders Univ S Australia, Flinders Med Ctr, Dept Orthopaed & Trauma Surg, Adelaide, SA, Australia
[11] Sint Antonius Ziekenhuis, Dept Surg, Utrecht, Netherlands
基金
加拿大健康研究院; 美国国家卫生研究院;
关键词
PREDICTION MODEL; FOLLOW-UP; REOPERATION; PERFORMANCE; MEDICINE; SURGERY; SCREW;
D O I
10.1097/CORR.0000000000002283
中图分类号
R826.8 [整形外科学]; R782.2 [口腔颌面部整形外科学]; R726.2 [小儿整形外科学]; R62 [整形外科学(修复外科学)];
学科分类号
摘要
Background Femoral neck fractures are common and are frequently treated with internal fixation. A major disadvantage of internal fixation is the substantially high number of conversions to arthroplasty because of nonunion, malunion, avascular necrosis, or implant failure. A clinical prediction model identifying patients at high risk of conversion to arthroplasty may help clinicians in selecting patients who could have benefited from arthroplasty initially. Question/purpose What is the predictive performance of a machine-learning (ML) algorithm to predict conversion to arthroplasty within 24 months after internal fixation in patients with femoral neck fractures? MethodsWe included 875 patients from the Fixation using Alternative Implants for the Treatment of Hip fractures (FAITH) trial. The FAITH trial consisted of patients with low-energy femoral neck fractures who were randomly assigned to receive a sliding hip screw or cancellous screws for internal fixation. Of these patients, 18% (155 of 875) underwent conversion to THA or hemiarthroplasty within the first 24 months. All patients were randomly divided into a training set (80%) and test set (20%). First, we identified 27 potential patient and fracture characteristics that may have been associated with our primary outcome, based on biomechanical rationale and previous studies. Then, random forest algorithms (an ML learning, decision tree-based algorithm that selects variables) identified 10 predictors of conversion: BMI, cardiac disease, Garden classification, use of cardiac medication, use of pulmonary medication, age, lung disease, osteoarthritis, sex, and the level of the fracture line. Based on these variables, five different ML algorithms were trained to identify patterns related to conversion. The predictive performance of these trained ML algorithms was assessed on the training and test sets based on the following performance measures: (1) discrimination (the model's ability to distinguish patients who had conversion from those who did not; expressed with the area under the receiver operating characteristic curve [AUC]), (2) calibration (the plotted estimated versus the observed probabilities; expressed with the calibration curve intercept and slope), and (3) the overall model performance (Brier score: a composite of discrimination and calibration). Results None of the five ML algorithms performed well in predicting conversion to arthroplasty in the training set and the test set; AUCs of the algorithms in the training set ranged from 0.57 to 0.64, slopes of calibration plots ranged from 0.53 to 0.82, calibration intercepts ranged from -0.04 to 0.05, and Brier scores ranged from 0.14 to 0.15. The algorithms were further evaluated in the test set; AUCs ranged from 0.49 to 0.73, calibration slopes ranged from 0.17 to 1.29, calibration intercepts ranged from -1.28 to 0.34, and Brier scores ranged from 0.13 to 0.15. Conclusion The predictive performance of the trained algorithms was poor, despite the use of one of the best datasets available worldwide on this subject. If the current dataset consisted of different variables or more patients, the performance may have been better. Also, various reasons for conversion to arthroplasty were pooled in this study, but the separate prediction of underlying pathology (such as, avascular necrosis or nonunion) may be more precise. Finally, it may be possible that it is inherently difficult to predict conversion to arthroplasty based on preoperative variables alone.Therefore, future studies should aim to include more variables and to differentiate between the various reasons for arthroplasty. Level of Evidence Level III, prognostic study.
引用
收藏
页码:2350 / 2360
页数:11
相关论文
共 55 条
[1]  
[Anonymous], 2017, LANCET, V389, P1519, DOI DOI 10.1016/S0140-6736(17)30066-1
[2]   External Validation of Deep Learning Algorithm for Detecting and Visualizing Femoral Neck Fracture Including Displaced and Non-displaced Fracture on Plain X-ray [J].
Bae, Junwon ;
Yu, Sangjoon ;
Oh, Jaehoon ;
Kim, Tae Hyun ;
Chung, Jae Ho ;
Byun, Hayoung ;
Yoon, Myeong Seong ;
Ahn, Chiwon ;
Lee, Dong Keon .
JOURNAL OF DIGITAL IMAGING, 2021, 34 (05) :1099-1109
[3]   Internal fixation compared with arthroplasty for displaced fractures of the femoral neck - A meta-analysis [J].
Bhandari, M ;
Devereaux, PJ ;
Swiontkowski, MF ;
Tornetta, P ;
Obremskey, W ;
Koval, KJ ;
Nork, S ;
Sprague, S ;
Schemitsch, EH ;
Guyatt, GH .
JOURNAL OF BONE AND JOINT SURGERY-AMERICAN VOLUME, 2003, 85A (09) :1673-1681
[4]   A Machine Learning Algorithm to Identify Patients with Tibial Shaft Fractures at Risk for Infection After Operative Treatment [J].
Bhandari, Mohit ;
Bulstra, Anne Eva J. ;
Bzovsky, Sofia ;
Doornberg, Job N. ;
Goslings, J. Carel ;
Hendrickx, Laurent A. M. ;
Jaarsma, Ruurd L. ;
Jeray, Kyle J. ;
Kerkhoffs, Gino M. M. J. ;
Petrisor, Brad ;
Ring, David ;
Schemitsch, Emil H. ;
Swiontkowski, Marc ;
Sanders, David ;
Sprague, Sheila ;
Tornetta, Paul, III ;
Walter, Stephen D. ;
Bhandari, Mohit ;
Guyatt, Gordon ;
Sanders, David W. ;
Schemitsch, Emil H. ;
Swiontkowski, Marc ;
Tornetta, Paul, III ;
Walter, Stephen ;
Sprague, Sheila ;
Heels-Ansdell, Diane ;
Buckingham, Lisa ;
Leece, Pamela ;
Viveiros, Helena ;
Mignott, Tashay ;
Ansell, Natalie ;
Sidorkewicz, Natalie ;
Agel, Julie ;
Bombardier, Claire ;
Berlin, Jesse A. ;
Bosse, Michael ;
Browner, Bruce ;
Gillespie, Brenda ;
Jones, Alan ;
O'Brien, Peter ;
Poolman, Rudolf ;
Macleod, Mark D. ;
Carey, Timothy ;
Leitch, Kellie ;
Bailey, Stuart ;
Gurr, Kevin ;
Konito, Ken ;
Bartha, Charlene ;
Low, Isolina ;
MacBean, Leila V. .
JOURNAL OF BONE AND JOINT SURGERY-AMERICAN VOLUME, 2021, 103 (06) :532-540
[5]   Infographic. Can even experienced orthopaedic surgeons predict who will benefit from surgery when patients present with degenerative meniscal tears? A survey of 194 orthopaedic surgeons who made 3880 predictions [J].
Bloembergen, Coen H. ;
van de Graaf, Victor A. ;
Virgile, Adam ;
Willigenburg, Niene W. ;
Noorduyn, Julia C. A. ;
Saris, Daniel B. F. ;
Harris, Ian ;
Poolman, Rudolf W. .
BRITISH JOURNAL OF SPORTS MEDICINE, 2020, 54 (09) :556-557
[6]   Displaced femoral neck fracture:: comparison of primary total hip replacement with secondary replacement after failed internal fixation -: A 2-year follow-up of 84 patients [J].
Blomfeldt, Richard ;
Tornkvist, Hans ;
Ponzer, Sari ;
Soderqvist, Anita ;
Tidermark, Jan .
ACTA ORTHOPAEDICA, 2006, 77 (04) :638-643
[7]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32
[8]   Machine Learning and Prediction in Medicine - Beyond the Peak of Inflated Expectations [J].
Chen, Jonathan H. ;
Asch, Steven M. .
NEW ENGLAND JOURNAL OF MEDICINE, 2017, 376 (26) :2507-2509
[9]  
Collins GS, 2015, ANN INTERN MED, V162, P55, DOI [10.7326/M14-0697, 10.1136/bmj.g7594, 10.1016/j.jclinepi.2014.11.010, 10.1038/bjc.2014.639, 10.1002/bjs.9736, 10.1016/j.eururo.2014.11.025, 10.1186/s12916-014-0241-z, 10.7326/M14-0698]
[10]   INTRODUCTION TO NEURAL NETWORKS [J].
CROSS, SS ;
HARRISON, RF ;
KENNEDY, RL .
LANCET, 1995, 346 (8982) :1075-1079