Predictors of adverse events after percutaneous pedicle screws fixation in patients with single-segment thoracolumbar burst fractures

Abstract

Background Percutaneous pedicle screw fixation (PPSF) is the primary approach for single-segment thoracolumbar burst fractures (TLBF). The healing angle at the thoracolumbar junction is one of the most significant criteria for evaluating the efficacy of PPSF. Therefore, the purpose of this study was to analyze the predictors associated with the poor postoperative alignment of the thoracolumbar region from routine variables using a support vector machine (SVM) model. Methods We retrospectively analyzed patients with TLBF operated at our academic institute between March 1, 2014 and December 31, 2019. Stepwise logistic regression analysis was performed to assess potential statistical differences between all clinical and radiological variables and the adverse events. Based on multivariate logistic results, a series of independent risk factors were fed into the SVM model. Meanwhile, the feature importance of radiologic outcome for each parameter was explored. The predictive performance of the SVM classifier was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy (ACC) and confusion matrices with 10-fold cross-validation, respectively. Results In the recruited 150 TLBFs, unfavorable radiological outcomes were observed in 53 patients (35.33%). The relationship between osteoporosis (p = 0.036), preoperative Cobb angle (p = 0.001), immediate postoperative Cobb angle (p = 0.029), surgically corrected Cobb angle (p = 0.001), intervertebral disc injury (Score 2 p = 0.001, Score 3 p = 0.001), interpedicular distance (IPD) (p = 0.001), vertebral body compression rate (VBCR) (p = 0.010) and adverse events was confirmed by univariate regression. Thereafter, independent risk factors including preoperative Cobb angle, the disc status and IPD and independent protective factors surgical correction angle were identified by multivariable logistic regression. The established SVM classifier demonstrated favorable predictive performance with the best AUC = 0.93, average AUC = 0.88, and average ACC = 0.87. The variables associated with radiological outcomes, in order of correlation strength, were intervertebral disc injury (42%), surgically corrected Cobb angle (25%), preoperative Cobb angle (18%), and IPD (15%). The confusion matrix reveals the classification results of the discriminant analysis. Conclusions Critical radiographic indicators and surgical purposes were confirmed to be associated with an unfavorable radiographic outcome of TLBF. This SVM model demonstrated good predictive ability for endpoints in terms of adverse events in patients after PPSF surgery.

Predicting factors for extremity fracture among border-fall patients using machine learning computing

“…We will compare different ML classifiers such as logistic regression (LR) which fits better for dichotomous data [ 43 , 44 ], K nearest-neighbor (KNN) [ 45 , 46 ], Linear Discriminant Analysis (LDA) [ 45 , 47 , 48 ], support vector machine (SVM) [ [49] , [50] , [51] ], and CNN [ 40 , 41 ] to determine if there is a better predictive ML model.…”

Using Artificial Intelligence to Predict the Development of Kyphosis Disease: A Systematic Review

“…The main advantage of using artificial intelligence to predict the development of kyphosis disease is its ability to predict the development of kyphosis using radiological parameters that are not traditionally used to predict the development of kyphosis; for example, Dong et al [23] demonstrated that a support vector model was able to identify multiple variables associated with the development of postoperative kyphosis disease in patients who underwent percutaneous pedicle screw fixation after thoracolumbar burst fracture with favorable predictive performance, and the identified variables included intervertebral disc injury, surgically corrected Cobb angle, preoperative Cobb angle, and intervertebral distance. Predicting the development of postoperative kyphosis disease is difficult, and these are not parameters traditionally used to predict the development of postoperative kyphosis disease, so it is very advantageous that artificial intelligence can identify relevant variables and utilize these variables to predict the development of kyphosis disease.…”

Evaluation of minimally invasive percutaneous transpedicular screw fixation as an evolving modality for the treatment of thoracolumbar fractures

“…Case selection is a critical factor in opting for MIPS fixation to avoid the risk of a postoperative deformity or lifelong kyphosis [10]. Literature consensuses suggest that conservative treatment is not advisable in type A3 burst fractures [AO-Magerl classification] [3], young active individuals avoiding prolonged work absence, obesity, polytrauma, and previous deep venous thrombosis (DVT) patients.…”