Academic radiology · 2024
Predicting Secondary Vertebral Compression Fracture After Vertebral Augmentation via CT-Based Machine Learning Radiomics-Clinical Model.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Wang Xiaokun, Ye Wu, Gu Yao, Gao Yu, Wang Haofan, Zhou Yitong, Pan Dishui, Ge Xuhui, Liu Wei, Cai Weihua
Аннотация
RATIONALE AND OBJECTIVES: Secondary vertebral compression fractures (SVCF) are very common in patients after vertebral augmentation (VA). The aim of this study was to establish a radiomic-based model to predict SVCF and specify appropriate treatment strategies.
MATERIALS AND METHODS: Patients diagnosed with osteoporotic vertebral compression fracture (OVCF) and undergoing VA surgery at our center between 2017 and 2021 were subject to a retrospective analysis. Radiological features of the T6-L5 vertebrae were derived from CT images. Clustering analysis, t-test, and LASSO (least absolute shrinkage and selection operator) regression were used to identify the optimization characteristics. A radiological signature model was constructed through the best combination of 13 machine learning algorithms. Radiomics signature was integrated with clinical characteristics into a nomogram for clinical applications. The model reliability was assessed by receiver operating characteristic (ROC) curve, calibration curve, clinical decision analysis (DCA), log-rank test, and confusion matrix.
RESULTS: A total of 470 eligible patients (81 with SVCF and 389 without) were identified in the clinical cohort. Eight radiomics features were identified and incorporated into machine learning, and "XGBoost" model showed the best performance. Final logistic nomogram included radiomics signature (P < 0.001), bone cement volume (P = 0.034), and T-scores of L1-L4 (P = 0.001), and showed satisfactory prediction capability in training set (0.986, 95%CI 0.969-1.000) and verification set (0.884, 95%CI 0.823-0.946).
CONCLUSION: Our radiomics-clinical model based on machine learning showed potential to prospectively predict SVCF after VA and provide precise treatment strategies.
MATERIALS AND METHODS: Patients diagnosed with osteoporotic vertebral compression fracture (OVCF) and undergoing VA surgery at our center between 2017 and 2021 were subject to a retrospective analysis. Radiological features of the T6-L5 vertebrae were derived from CT images. Clustering analysis, t-test, and LASSO (least absolute shrinkage and selection operator) regression were used to identify the optimization characteristics. A radiological signature model was constructed through the best combination of 13 machine learning algorithms. Radiomics signature was integrated with clinical characteristics into a nomogram for clinical applications. The model reliability was assessed by receiver operating characteristic (ROC) curve, calibration curve, clinical decision analysis (DCA), log-rank test, and confusion matrix.
RESULTS: A total of 470 eligible patients (81 with SVCF and 389 without) were identified in the clinical cohort. Eight radiomics features were identified and incorporated into machine learning, and "XGBoost" model showed the best performance. Final logistic nomogram included radiomics signature (P < 0.001), bone cement volume (P = 0.034), and T-scores of L1-L4 (P = 0.001), and showed satisfactory prediction capability in training set (0.986, 95%CI 0.969-1.000) and verification set (0.884, 95%CI 0.823-0.946).
CONCLUSION: Our radiomics-clinical model based on machine learning showed potential to prospectively predict SVCF after VA and provide precise treatment strategies.