RESUMO
STUDY DESIGN: Retrospective study. OBJECTIVES: Our objective is to create comprehensible machine learning (ML) models that can forecast bone cement leakage in percutaneous vertebral augmentation (PVA) for individuals with osteoporotic vertebral compression fracture (OVCF) while also identifying the associated risk factors. METHODS: We incorporated data from patients (n = 425) which underwent PVA. To predict cement leakage, we devised six models based on a variety of parameters. Evaluate and juxtapose the predictive performances relied on measures of discrimination, calibration, and clinical utility. SHapley Additive exPlanations (SHAP) methodology was used to interpret model and evaluate the risk factors associated with cement leakage. RESULTS: The occurrence rate of cement leakage was established at 50.4%. A binary logistic regression analysis identified cortical disruption (OR 6.880, 95% CI 4.209-11.246), the basivertebral foramen sign (OR 2.142, 95% CI 1.303-3.521), the fracture type (OR 1.683, 95% CI 1.083-2.617), and the volume of bone cement (OR 1.198, 95% CI 1.070-1.341) as independent predictors of cement leakage. The XGBoost model outperformed all others in predicting cement leakage in the testing set, with AUC of .8819, accuracy of .8025, recall score of .7872, F1 score of .8315, and a precision score of .881. Several important factors related to cement leakage were drawn based on the analysis of SHAP values and their clinical significance. CONCLUSION: The ML based predictive model demonstrated significant accuracy in forecasting bone cement leakage for patients with OVCF undergoing PVA. When combined with SHAP, ML facilitated a personalized prediction and offered a visual interpretation of feature importance.
RESUMO
OBJECTIVE: The purpose of the present study was to compare the clinical outcomes and complications between the mini-open Wiltse approach with pedicle screw fixation (MWPSF) and percutaneous pedicle screw fixation (PPSF) in treating neurologically intact thoracolumbar fractures. METHODS: We comprehensively searched PubMed, Web of Science, Embase, and the Cochrane Library and performed a systematic review and meta-analysis of all randomized controlled trials and retrospective comparative studies assessing these important indexes of the 2 methods using Review Manager, version 5.4. The clinical outcomes are presented as the risk difference for dichotomous outcomes and the mean difference for continuous outcomes with the 95% confidence intervals. Heterogeneity was assessed using the χ2 test and I2 statistics. The study was registered with PROSPERO (CRD 42021290078). RESULTS: Two randomized controlled trials and six retrospective cohort studies were included in the present analysis. The percutaneous approach was associated with less intraoperative blood loss compared with the mini-open Wiltse approach. No significant differences were found in the total length of the incisions, hospitalization time, postoperative visual analog scale scores, postoperative Oswestry disability index, postoperative Cobb angle, postoperative Cobb angle correction, postoperative Cobb angle correction loss, accuracy rate of pedicle screw placement, and postoperative complications between MWPSF and PPSF. However, the incidence of facet joint violation was significantly higher in the PPSF group. In addition, MWPSF was associated with a shorter operative time, shorter intraoperative fluoroscopy time, lower hospitalization costs, better postoperative vertebral body angle and percentage of vertebral body height compared with PPSF. CONCLUSIONS: Both MWPSF and PPSF are safe and effective treatments of neurologically intact thoracolumbar fractures. Nevertheless, our results have indicated that MWPSF might be the better choice, because it has a shorter learning curve and decreased facet joint violation, operative time, hospitalization costs, and radiation exposure. In addition, MWPSF was associated with better improvement of the postoperative vertebral body angle and percentage of vertebral body height.