首页|Affiliated Hospital of Guangdong Medical University Reports Findings in Arthropl asty (Prediction of intraoperative press-fit stability of the acetabular cup in total hip arthroplasty using radiomics-based machine learning models)
Affiliated Hospital of Guangdong Medical University Reports Findings in Arthropl asty (Prediction of intraoperative press-fit stability of the acetabular cup in total hip arthroplasty using radiomics-based machine learning models)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
New research on Surgery-Arthroplasty is the subject of a report. According to news reporting originating in Guangdon g, People's Republic of China, by NewsRx journalists, research stated, "Preopera tive prediction of the acetabular cup press-fit stability in total hip arthropla sty is necessary for clinical decision-making. This study aims to establish and validate machine learning models to investigate the feasibility of predicting th e intraoperative press-fit stability of the acetabular cup in total hip arthropl asty (THA)." The news reporters obtained a quote from the research from the Affiliated Hospit al of Guangdong Medical University, "226 patients who underwent primary THA from 2018 to 2022 in our hospital were retrospectively enrolled. Patients were divid ed into press-fit stable or unstable groups according to the intraoperative pull -out test of the implanted cup. Then, they were randomly assigned to the trainin g or test cohort in an 8:2 ratio. We used 3Dslicer software to segment the regio n of interest (ROI) of the patient's bilateral hip X-ray to extract radiomics fe atures. The least absolute shrinkage and selection operator (LASSO) regression w as used in our feature selection. Finally, four machine learning models were emp loyed in this study, including support vector machine (SVM), random forest (RF), logistic regression (LR), and XGBoost (XGB). Decision curve analysis (DCA), and receiver operating characteristic (ROC) curves of the models were plotted. The area under the curve (AUC), diagnostic accuracy, sensitivity, and specificity we re calculated as well. The AUCs of the four models were compared using the DeLon g test. Twenty-seven valuable radiomics features were determined by dimensionali ty reduction and selection. Regarding to the DeLong test, the AUC of the XGB mod el was significantly different from those of the other three models. (p <0.05). Among all models, the XGB model exhibited the best performance with an A UC of 0.823 (95 % CI: 0.711-0.919) in the test cohort and showed o ptimal clinical efficacy according to the DCA."
GuangdongPeople's Republic of ChinaAsiaArthroplastyCyborgsEmerging TechnologiesHealth and MedicineMachine LearningOrthopedic ProceduresSurgery
NETL
NSTL
