Establishment and validation of a predictive model for the progression of pancreatic cystic lesions based on clinical and CT radiological features
10.3760/cma.j.cn115667-20230902-00017
- VernacularTitle:基于临床和CT影像学特征的胰腺囊性病变进展预测模型的建立及验证
- Author:
Wenyi DENG
1
;
Feiyang XIE
;
Li MAO
;
Xiuli LI
;
Zhaoyong SUN
;
Kai XU
;
Liang ZHU
;
Zhengyu JIN
;
Xiao LI
;
Huadan XUE
Author Information
1. 中国医学科学院北京协和医学院 北京协和医院放射科,北京 100730
- Keywords:
Pancreatic cystic neoplasm;
Machine learning;
Progressive disease;
Computed tomography
- From:
Chinese Journal of Pancreatology
2024;24(1):23-28
- CountryChina
- Language:Chinese
-
Abstract:
Objective:To construct a machine-learning model for predicting the progression of pancreatic cystic lesions (PCLs) based on clinical and CT features, and to evaluate its predictive performance in internal/external testing cohorts.Methods:Baseline clinical and radiological data of 200 PCLs in 177 patients undergoing abdominal thin slice enhanced CT examination at Peking Union Medical College Hospital from July 2014 to December 2022 were retrospectively collected. PCLs were divided into progressive and non-progressive groups according to whether the signs indicated for surgery by the guidelines of the European study group on PCLs were present during three-year follow-up. 200 PCLs were randomly divided into training (150 PCLs) and internal testing cohorts (50 PCLs) at the ratio of 1∶3. 15 PCLs in 14 patients at Jinling Affiliated Hospital of Medical School of Nanjing University from October 2011 to May 2020 were enrolled as external testing cohort. The clinical and CT radiological features were recorded. Multiple feature selection methods and machine-learning models were implemented and combined to identify the optimal machine-learning model based on the 10-fold cross-validation method. Receiver operating characteristics (ROC) curve was drawn and area under curve (AUC) was calculated. The model with the highest AUC was determined as the optimal model. The optimal model's predictive performance was evaluated on testing cohort by calculating AUC, sensitivity, specificity and accuracy. Permutation importance was used to assess the importance of optimal model features. Calibration curves of the optimal model were established to evaluate the model's clinical applicability by Hosmer-Lemeshow test.Results:In training and internal testing cohorts, the progressive and non-progressive groups were significantly different on history of pancreatitis, lesions size, main pancreatic duct diameter and dilation, thick cyst wall, presence of septation and thick septation (all P value <0.05) In internal testing cohort, the two groups were significantly different on gender, lesion calcification and pancreatic atrophy (all P value <0.05). In external testing cohort, the two groups were significantly different on lesions size and pancreatic duct dilation (both P<0.05). The support vector machine (SVM) model based on five features selected by F test (lesion size, thick cyst wall, history of pancreatitis, main pancreatic duct diameter and dilation) achieved the highest AUC of 0.899 during cross-validation. SVM model for predicting the progression of PCLs demonstrated an AUC of 0.909, sensitivity of 82.4%, specificity of 72.7%, and accuracy of 76.0% in the internal testing cohort, and 0.944, 100%, 77.8%, and 86.7% in the external testing cohort. Calibration curved showed that the predicted probability by the model was comparable to the real progression of PCLs. Hosmer-Lemeshow goodness-of-fit test affirmed the model's consistency with actual PCLs progression in testing cohorts. Conclusions:The SVM model based on clinical and CT features can help doctors predict the PCLs progression within three-year follow-up, thus achieving efficient patient management and rational allocation of medical resource.