Annals of surgical oncology · 2025
Machine Learning Model for Predicting Pheochromocytomas/Paragangliomas Surgery Difficulty: A Retrospective Cohort Study.
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.
Zhang Yubing, Guo Qikun, Li Shurong, Zhang Zhiqiang, Xiang Fangzheng, Su Wenhui, Wu Yukun, Yu Jiajie, Xie Yun, Luo Cheng, Zheng Fufu
Аннотация
OBJECTIVE: We aimed to develop a machine learning (ML) model to preoperatively predict surgical difficulty for pheochromocytomas and paragangliomas (PPGLs) using clinical and radiomic features.
METHODS: In this study, 212 patients with pathologically confirmed PPGLs were retrospectively enrolled and divided into training (n = 148) and validation cohorts (n = 64). Seven ML models (Classification and Regression Tree, K-Nearest Neighbors, Least Absolute Shrinkage and Selection Operator, Naïve Bayes, Random Forest, Support Vector Machine (SVM), and Extreme Gradient Boosting) were trained using clinical parameters alone or combined with radiomics. Model performance was evaluated and compared through accuracy, sensitivity, specificity, F1 score, area under the curve (AUC), calibration curves, and decision curve analysis. Through comprehensive assessment, the optimal integrated model (clinical + radiomics) was identified and its predictive efficacy was subsequently compared with that of the clinical parameter model. Finally, SHapley Additive exPlanations (SHAP) was applied to enhance the interpretability of the optimal model by visualizing feature contributions.
RESULTS: Among all integrated models, the SVM model exhibited the most prominent performance, achieving AUC values of 0.96 in the training cohort and 0.85 in the validation cohort, while demonstrating statistically significant superiority over the clinical parameter model (p < 0.05). The SHAP analysis revealed that radiomic signature (Rad score) exerted the most substantial influence on the predictive outcomes, with age, body mass index, maximum tumor diameter, and preoperative heart rate also demonstrating statistically significant contributions to the model predictions.
CONCLUSION: The SVM model integrating clinical and radiomic features effectively predicts PPGL surgical difficulty, aiding preoperative risk stratification and personalized surgical planning to reduce operative risks.
METHODS: In this study, 212 patients with pathologically confirmed PPGLs were retrospectively enrolled and divided into training (n = 148) and validation cohorts (n = 64). Seven ML models (Classification and Regression Tree, K-Nearest Neighbors, Least Absolute Shrinkage and Selection Operator, Naïve Bayes, Random Forest, Support Vector Machine (SVM), and Extreme Gradient Boosting) were trained using clinical parameters alone or combined with radiomics. Model performance was evaluated and compared through accuracy, sensitivity, specificity, F1 score, area under the curve (AUC), calibration curves, and decision curve analysis. Through comprehensive assessment, the optimal integrated model (clinical + radiomics) was identified and its predictive efficacy was subsequently compared with that of the clinical parameter model. Finally, SHapley Additive exPlanations (SHAP) was applied to enhance the interpretability of the optimal model by visualizing feature contributions.
RESULTS: Among all integrated models, the SVM model exhibited the most prominent performance, achieving AUC values of 0.96 in the training cohort and 0.85 in the validation cohort, while demonstrating statistically significant superiority over the clinical parameter model (p < 0.05). The SHAP analysis revealed that radiomic signature (Rad score) exerted the most substantial influence on the predictive outcomes, with age, body mass index, maximum tumor diameter, and preoperative heart rate also demonstrating statistically significant contributions to the model predictions.
CONCLUSION: The SVM model integrating clinical and radiomic features effectively predicts PPGL surgical difficulty, aiding preoperative risk stratification and personalized surgical planning to reduce operative risks.