1. Evaluation and analysis of risk factors for adverse events of the fractured vertebra post-percutaneous kyphoplasty: a retrospective cohort study using multiple machine learning models.
- Author
-
Zhao, YingLun, Bo, Li, Chen, XueMing, Wang, YanHui, Cui, LiBin, Xin, Yuan, Liang, Liu, Chao, Kong, and Lu, ShiBao
- Subjects
- *
KYPHOPLASTY , *RISK assessment , *STATISTICAL correlation , *PREDICTION models , *ADIPOSE tissues , *MULTIPLE regression analysis , *COMPUTED tomography , *COMPRESSION fractures , *VERTEBRAL fractures , *RETROSPECTIVE studies , *DESCRIPTIVE statistics , *BACK muscles , *BONE fractures , *SURGICAL complications , *ODDS ratio , *MEDICAL records , *ACQUISITION of data , *RESEARCH , *THEORY , *OSTEOPOROSIS , *MACHINE learning , *COMPARATIVE studies , *CONFIDENCE intervals , *SPINE , *SPINE diseases , *DISEASE risk factors - Abstract
Background: Adverse events of the fractured vertebra (AEFV) post-percutaneous kyphoplasty (PKP) can lead to recurrent pain and neurological damage, which considerably affect the prognosis of patients and the quality of life. This study aimed to analyze the risk factors of AEFV and develop and select the optimal risk prediction model for AEFV to provide guidance for the prevention of this condition and enhancement of clinical outcomes. Methods: This work included 383 patients with primary osteoporotic vertebral compression fracture (OVCF) who underwent PKP. The patients were grouped based on the occurrence of AEFV postsurgery, and data were collected. Group comparisons and correlation analysis were conducted to identify potential risk factors, which were then included in the five prediction models. The performance indicators served as basis for the selection of the best model. Results: Multivariate logistic regression analysis revealed the following independent risk factors for AEFV: kissing spine (odds ratio (OR) = 8.47, 95% confidence interval (CI) 1.46–49.02), high paravertebral muscle fat infiltration grade (OR = 29.19, 95% CI 4.83–176.04), vertebral body computed tomography value (OR = 0.02, 95% CI 0.003–0.13, P < 0.001), and large Cobb change (OR = 5.31, 95% CI 1.77–15.77). The support vector machine (SVM) model exhibited the best performance in the prediction of the risk of AEFV. Conclusion: Four independent risk factors were identified of AEFV, and five risk prediction models that can aid clinicians in the accurate identification of high-risk patients and prediction of the occurrence of AEFV were developed. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF