Development and Validation of a Nomogram for New Vertebral Compression Fractures in Postmenopausal Female Patients Undergoing Percutaneous Kyphoplasty Surgery

Abstract

Abstract Background: Postmenopausal women face a heightened risk of developing new vertebral compression fractures (NVCF) after experiencing osteoporotic vertebral compression fractures (OVCF) and undergoing percutaneous kyphoplasty (PKP). This study aims to develop and validate a novel Nomogram visual model capable of accurately predicting the occurrence of NVCF following PKP. The objective is to optimize treatment strategies and minimize the occurrence of new fractures. Methods: A retrospective study was conducted on postmenopausal women diagnosed with OVCF who underwent PKP at the Affiliated Hospital of Shandong University of Traditional Chinese Medicine between January 2016 and January 2021. Patient data, including basic information, surgical details, imaging records, and laboratory test results, were collected. The patients were categorized into two groups based on the occurrence of NVCF: a new fracture group and a no new fracture group. Feature selection was performed using LASSO regression, and a Nomogram diagram was constructed. The model's differentiation, calibration, and clinical applicability were evaluated through receiver operating characteristic curve (ROC) analysis, calibration curves, and decision curve analysis (DCA). Results: In this study, a total of 357 patients were included. The results of LASSO regression analysis indicated that cement leakage, poor cement diffusion, and endplate fracture were identified as independent predictors of NVCF. The development and verification of the Nomogram demonstrated its predictive ability and clinical applicability. Conclusions: The study utilized LASSO regression to identify three independent predictors and developed a predictive model for predicting the occurrence of NVCF in postmenopausal women. The developed model effectively predicts the occurrence of NVCF in this population.