Predicting Prolonged Wound Drainage after Hemiarthroplasty for Hip Fractures: A Stacked Machine Learning Study.
Drainage fluid
Hemiarthroplasty
Hip fracture
Machine learning
Stacking
Journal
Clinics in orthopedic surgery
ISSN: 2005-4408
Titre abrégé: Clin Orthop Surg
Pays: Korea (South)
ID NLM: 101505087
Informations de publication
Date de publication:
Dec 2023
Dec 2023
Historique:
received:
08
06
2022
revised:
24
09
2022
accepted:
27
09
2022
medline:
5
12
2023
pubmed:
4
12
2023
entrez:
4
12
2023
Statut:
ppublish
Résumé
Prolonged wound drainage (PWD) is one of the most important reasons that increase the risk of early periprosthetic joint infection after arthroplasty. It is very important to evaluate the risk factors for PWD in the surgical field after arthroplasty surgery. This can be accomplished using machine learning or artificial intelligence methods. Our aim in this study was to compare machine learning methods in predicting possible PWD. The study was carried out on clinical, laboratory, and radiological data of 313 patients who underwent hemiarthroplasty (HA) for proximal femur fractures. We preprocessed the dataset and trained and tested machine learning methods using cross validation. We compared various machine learning algorithms (linear discriminant analysis, decision tree, k-nearest neighbors, gradient boosting machine, and logistic regression [LR]) based on performance measures. We also combined the most successful algorithms with a metaclassifier. To help understand the relationship between risk factors, we provided a risk factor severity ranking. To estimate the risk of PWD, classification was performed with first-level classifiers and then integrated as a LR-based meta-learner stacking method. More performance improvements were achieved with the stacking method. We found that the stacking method was superior to other methods in PWD classification. We determined that the volume of fluid collected from the drain, morbid obesity class, blood transfusion, and body mass index score were the four most important risk factors according to stacking.
Sections du résumé
Background
UNASSIGNED
Prolonged wound drainage (PWD) is one of the most important reasons that increase the risk of early periprosthetic joint infection after arthroplasty. It is very important to evaluate the risk factors for PWD in the surgical field after arthroplasty surgery. This can be accomplished using machine learning or artificial intelligence methods. Our aim in this study was to compare machine learning methods in predicting possible PWD.
Methods
UNASSIGNED
The study was carried out on clinical, laboratory, and radiological data of 313 patients who underwent hemiarthroplasty (HA) for proximal femur fractures. We preprocessed the dataset and trained and tested machine learning methods using cross validation. We compared various machine learning algorithms (linear discriminant analysis, decision tree, k-nearest neighbors, gradient boosting machine, and logistic regression [LR]) based on performance measures. We also combined the most successful algorithms with a metaclassifier. To help understand the relationship between risk factors, we provided a risk factor severity ranking.
Results
UNASSIGNED
To estimate the risk of PWD, classification was performed with first-level classifiers and then integrated as a LR-based meta-learner stacking method. More performance improvements were achieved with the stacking method.
Conclusions
UNASSIGNED
We found that the stacking method was superior to other methods in PWD classification. We determined that the volume of fluid collected from the drain, morbid obesity class, blood transfusion, and body mass index score were the four most important risk factors according to stacking.
Identifiants
pubmed: 38045590
doi: 10.4055/cios22181
pmc: PMC10689231
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
894-901Informations de copyright
Copyright © 2023 by The Korean Orthopaedic Association.
Déclaration de conflit d'intérêts
CONFLICT OF INTEREST: No potential conflict of interest relevant to this article was reported.
Références
Arch Phys Med Rehabil. 2021 Mar;102(3):386-394
pubmed: 32949551
Injury. 2021 Apr;52(4):918-925
pubmed: 33059924
J Am Med Dir Assoc. 2021 Feb;22(2):291-296
pubmed: 33132014
Acta Orthop. 2009 Oct;80(5):520-4
pubmed: 19916682
J Bone Joint Surg Am. 2007 Jan;89(1):33-8
pubmed: 17200307
J Arthroplasty. 2010 Feb;25(2):244-8
pubmed: 19056215
Clin Orthop Surg. 2018 Mar;10(1):14-19
pubmed: 29564042
Front Neurorobot. 2013 Dec 04;7:21
pubmed: 24409142
Wound Repair Regen. 2011 Sep-Oct;19(5):588-96
pubmed: 22092797
PLoS One. 2011;6(8):e23224
pubmed: 21853091
J Orthop Trauma. 2019 Jul;33(7):324-330
pubmed: 30730360
Int Orthop. 2020 Sep;44(9):1823-1831
pubmed: 32728927
J Biomech. 2021 Mar 30;118:110190
pubmed: 33581443