A Machine Learning Algorithm to Identify Patients at Risk of Unplanned Subsequent Surgery After Intramedullary Nailing for Tibial Shaft Fractures.
Journal
Journal of orthopaedic trauma
ISSN: 1531-2291
Titre abrégé: J Orthop Trauma
Pays: United States
ID NLM: 8807705
Informations de publication
Date de publication:
01 Oct 2021
01 Oct 2021
Historique:
accepted:
25
01
2021
entrez:
17
9
2021
pubmed:
18
9
2021
medline:
26
10
2021
Statut:
ppublish
Résumé
In the SPRINT trial, 18% of patients with a tibial shaft fracture (TSF) treated with intramedullary nailing (IMN) had one or more unplanned subsequent surgical procedures. It is clinically relevant for surgeon and patient to anticipate unplanned secondary procedures, other than operations that can be readily expected such as reconstructive procedures for soft tissue defects. Therefore, the objective of this study was to develop a machine learning (ML) prediction model using the SPRINT data that can give individual patients and their care team an estimate of their particular probability of an unplanned second surgery. Patients from the SPRINT trial with unilateral TSFs were randomly divided into a training set (80%) and test set (20%). Five ML algorithms were trained in recognizing patterns associated with subsequent surgery in the training set based on a subset of variables identified by random forest algorithms. Performance of each ML algorithm was evaluated and compared based on (1) area under the ROC curve, (2) calibration slope and intercept, and (3) the Brier score. Total data set comprised 1198 patients, of whom 214 patients (18%) underwent subsequent surgery. Seven variables were used to train ML algorithms: (1) Gustilo-Anderson classification, (2) Tscherne classification, (3) fracture location, (4) fracture gap, (5) polytrauma, (6) injury mechanism, and (7) OTA/AO classification. The best-performing ML algorithm had an area under the ROC curve, calibration slope, calibration intercept, and the Brier score of 0.766, 0.954, -0.002, and 0.120 in the training set and 0.773, 0.922, 0, and 0.119 in the test set, respectively. An ML algorithm was developed to predict the probability of subsequent surgery after IMN for TSFs. This ML algorithm may assist surgeons to inform patients about the probability of subsequent surgery and might help to identify patients who need a different perioperative plan or a more intensive approach. Prognostic Level II. See Instructions for Authors for a complete description of levels of evidence.
Identifiants
pubmed: 34533505
doi: 10.1097/BOT.0000000000002070
pii: 00005131-202110000-00015
doi:
Types de publication
Journal Article
Randomized Controlled Trial
Langues
eng
Sous-ensembles de citation
IM
Pagination
e381-e388Informations de copyright
Copyright © 2021 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
The authors report no conflict of interest.
Références
Stavrou PZ, Ciriello V, Theocharakis S, et al. Prevalence and risk factors for re-interventions following reamed intramedullary tibia nailing. Injury. 2016;47(suppl 7):S49–S52.
Ricci WM, Gallagher B, Brandt A, et al. Is after-hours orthopaedic surgery associated with adverse outcomes? A prospective comparative study. J Bone Joint Surg Am. 2009;91:2067–2072.
Hernández-Vaquero D, Suárez-Vázquez A, Iglesias-Fernández S, et al. Dynamisation and early weight-bearing in tibial reamed intramedullary nailing: its safety and effect on fracture union. Injury. 2012;43(suppl 2):S63–S67.
Bhandari M, Tornetta P III, Sprague S, et al. Predictors of reoperation following operative management of fractures of the tibial shaft. J Orthop Trauma. 2003;17:353–361.
Stiell IG, Greenberg GH, McKnight RD, et al. A study to develop clinical decision rules for the use of radiography in acute ankle injuries. Ann Emerg Med. 1992;21:384–390.
Appelboam A, Reuben AD, Benger JR, et al. Elbow extension test to rule out elbow fracture: multicentre, prospective validation and observational study of diagnostic accuracy in adults and children. BMJ. 2008;337:a2428.
Walenkamp MMJ, Bentohami A, Slaar A, et al. The Amsterdam wrist rules: the multicenter prospective derivation and external validation of a clinical decision rule for the use of radiography in acute wrist trauma. BMC Musculoskelet Disord. 2015;16:389.
Bongers MER, Thio QCBS, Karhade AV, et al. Does the SORG algorithm predict 5-year survival in patients with chondrosarcoma? An external validation. Clin Orthop Relat Res. 2019;477:2296–2303.
Shah AA, Karhade AV, Bono CM, et al. Development of a machine learning algorithm for prediction of failure of nonoperative management in spinal epidural abscess. Spine J. 2019;19:1657–1665.
Ogink PT, Karhade AV, Thio QCBS, et al. Predicting Discharge Placement after Elective Surgery for Lumbar Spinal Stenosis Using Machine Learning Methods. Eur Spine J. 2019;28:1433–1440.
Karhade AV, Thio QCBS, Ogink PT, et al. Predicting 90-day and 1-year mortality in spinal metastatic disease: development and internal validation. Neurosurgery. 2019;85:E671–E681.
Thio QCBS, Karhade AV, Ogink PT, et al. Can machine-learning techniques Be used for 5-year survival prediction of patients with chondrosarcoma? Clin Orthop Relat Res. 2018;476:2040–2048.
Staartjes VE, de Wispelaere MP, Vandertop WP, et al. Deep learning-based preoperative predictive analytics for patient-reported outcomes following lumbar diskectomy: feasibility of center-specific modeling. Spine J. 2019;19:853–861.
Bertsimas D, Dunn J, Velmahos GC, et al. Surgical risk is not linear: derivation and validation of a novel, user-friendly, and machine-learning-based predictive OpTimal trees in emergency surgery risk (POTTER) calculator. Ann Surg. 2018;268:574–583.
Study to Prospectively Evaluate Reamed Intramedullary Nails in Patients with Tibial Fractures Investigators, Bhandari M, Guyatt G, et al. Randomized trial of reamed and unreamed intramedullary nailing of tibial shaft fractures. J Bone Joint Surg. Am. 2008;90:2567–2578.
Luo W, Phung D, Tran T, et al. Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view. J Med Internet Res. 2016;18:e323.
Moons KGM, Altman DG, Reitsma JB, et al. Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med. 2015;162:W1–W73.
WHO | WHO Data Policy. 2018. Available at: https://www.who.int/publishing/datapolicy/en/. Accessed August 7, 2019.
SPRINT Investigators, Bhandari M, Guyatt G, et al. Study to prospectively evaluate reamed intramedually nails in patients with tibial fractures (S.P.R.I.N.T.): study rationale and design. BMC Musculoskelet Disord. 2008;9:91.
Schemitsch EH, Bhandari M, Guyatt G, et al. Prognostic factors for predicting outcomes after intramedullary nailing of the tibia. J Bone Joint Surg Am. 2012;94:1786–1793.
Stekhoven DJ, Bühlmann P. MissForest—non-parametric missing value imputation for mixed-type data. Bioinformatics. 2012;28:112–118.
Kursa MB, Rudnicki WR, Others. Feature selection with the Boruta package. J Stat Softw. 2010;36:1–13.
Wolpert DH. The lack of A priori distinctions between learning algorithms. Neural Comput. 1996;8:1341–1390.
Maroco J, Silva D, Rodrigues A, et al. Data mining methods in the prediction of Dementia: a real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests. BMC Res Notes. 2011;4:299.
Wainer J. Comparison of 14 Different Families of Classification Algorithms on 115 Binary Datasets [Internet]. arXiv [cs.LG]. Available at: http://arxiv.org/abs/1606.00930. Accessed June 2, 2016.
Fernández-Delgado M, Cernadas E, Barro S. Do we need hundreds of classifiers to solve real world classification problems? J Mach. 2014;15:3133–3181.
Karhade AV, Thio QCBS, Ogink PT, et al. Development of machine learning algorithms for prediction of 30-day mortality after surgery for spinal metastasis. Neurosurg [Internet]. 2018. 10.1093/neuros/nyy469.
doi: 10.1093/neuros/nyy469
Steyerberg EW, Vergouwe Y. Towards better clinical prediction models: seven steps for development and an ABCD for validation. Eur Heart J. 2014;35:1925–1931.
Steyerberg EW. Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating. New York, NY: Springer Science & Business Media; 2008.
Hosmer DW, Lemeshow S, Sturdivant RX, et al. Applied Logistic Regression. New York, NY: John Wiley & Sons; 2013.
Vergouwe Y, Steyerberg EW, Eijkemans MJC, et al. Validity of prognostic models: when is a model clinically useful?. Semin Urol Oncol. 2002;20:96–107.
Gaston MS, Simpson AHRW. Inhibition of fracture healing. J Bone Joint Surg Br. 2007;89:1553–1560.
O'Halloran K, Coale M, Costales T, et al. Will my tibial fracture heal? Predicting nonunion at the time of definitive fixation based on commonly available variables. Clin Orthop Relat Res. 2016;474:1385–1395.
Chrastil J, Sampson C, Jones KB, et al. Postoperative opioid administration inhibits bone healing in an animal model. Clin Orthop Relat Res. 2013;471:4076–4081.
Harris I, Lyons M. Reoperation rate in diaphyseal tibia fractures. ANZ J Surg. 2005;75:1041–1044.
Sarmiento A, Sharpe FE, Ebramzadeh E, et al. Factors influencing the outcome of closed tibial fractures treated with functional bracing. Clin Orthop Relat Res. 1995:8–24.
Fong K, Truong V, Foote CJ, et al. Predictors of nonunion and reoperation in patients with fractures of the tibia: an observational study. BMC Musculoskelet Disord. 2013;14:103.
Audigé L, Griffin D, Bhandari M, et al. Path analysis of factors for delayed healing and nonunion in 416 operatively treated tibial shaft fractures. Clin Orthop Relat Res. 2005;438:221–232.
Sanders DW, Bhandari M, Guyatt G, et al. Critical-sized defect in the tibia: is it critical? Results from the SPRINT trial. J Orthop Trauma. 2014;28:632–635.
Karhade AV, Ogink PT, Thio QCBS, et al. Machine learning for prediction of sustained opioid prescription after anterior cervical discectomy and fusion. Spine J. 2019;19:976–983.
Karhade AV, Ogink P, Thio Q, et al. Development of machine learning algorithms for prediction of discharge disposition after elective inpatient surgery for lumbar degenerative disc disorders. Neurosurg Focus. 2018;45:E6.
Ouyang FS, Guo BL, Ouyang LZ, et al. Comparison between linear and nonlinear machine-learning algorithms for the classification of thyroid nodules. Eur J Radiol. 2019;113:251–257.