Related Experiment Video
Updated: Jan 15, 2026
Technical Detail for Robot Assisted Pancreaticoduodenectomy
Published on: September 28, 2019
Machine learning model based on preoperative MRI and clinical data for predicting pancreatic fistula after
Piao Yan1, Kuinan Tong2, Zhenhao Liu3
1Department of Radiology, Beijing Friendship Hospital, Capital Medical University, No. 95, Yong'an Road, Xicheng District, Beijing, 100050, China.
Objective:
To establish and validate a machine learning model using preoperative multi-sequence MRI radiomic features and clinical data to predict pancreatic fistula after pancreaticoduodenectomy (PD).
Methods:
We retrospectively analyzed 139 patients who underwent PD, dividing them into a training group (n = 97) and a test group (n = 42) through stratified sampling in a 7:3 ratio. Regions of interest (ROI) were delineated on non-enhanced T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), high b-value diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC) maps, and dynamic contrast-enhanced (DCE) images; radiomic features were subsequently extracted. The most significant radiomic features were selected using the t-test and least absolute shrinkage and selection operator with cross-validation (LASSO-CV). We identified clinical risk factors for clinically relevant postoperative pancreatic fistula (CR-POPF) using univariate logistic regression. Ten distinct machine learning algorithms were used to develop radiomics and clinical models, which were then integrated via weighted voting. Model performance was evaluated using receiver operating characteristic (ROC) curves and calibration curves.
Results:
Eight radiomic features and one clinical feature (BMI) were selected for model construction. Among the ten machine learning algorithms, the Random Forest (RF) algorithm yielded the optimal radiomics model, achieving an AUC of 0.702, an F1-score of 0.571, and an accuracy of 0.857 in the test set. The K-Nearest Neighbors (KNN) algorithm produced the optimal clinical model, with corresponding values of 0.846, 0.640, and 0.786. Finally, the integrated model, developed using a weighted voting strategy, demonstrated superior comprehensive performance with an AUC of 0.899, showing excellent discrimination and calibration.
Conclusion:
The machine learning model using preoperative multi-sequence MRI radiomic features showed moderate predictive value for CR-POPF risk, which was significantly enhanced by integrating BMI.
Insights
This study developed a machine learning model using MRI radiomic features to predict pancreatic fistula after pancreaticoduodenectomy. Integrating BMI significantly improved the model's predictive power for clinically relevant postoperative pancreatic fistula (CR-POPF).
Area of Science:
- Radiology
- Oncology
- Data Science
Background:
- Pancreatic fistula is a major complication after pancreaticoduodenectomy (PD).
- Accurate prediction of postoperative pancreatic fistula (POPF) is crucial for patient management.
- Machine learning and radiomics offer potential for predicting POPF.
Purpose of the Study:
- To develop and validate a machine learning model for predicting clinically relevant postoperative pancreatic fistula (CR-POPF).
- To utilize preoperative multi-sequence MRI radiomic features and clinical data for prediction.
- To assess the added value of integrating clinical data with radiomic features.
Main Methods:
- Retrospective analysis of 139 patients undergoing PD.
- Extraction of radiomic features from multi-sequence MRI (T1WI, T2WI, DWI, ADC, DCE).
- Development and integration of machine learning models (Random Forest, KNN) with radiomic and clinical (BMI) features, validated using ROC curves.
Main Results:
- Eight radiomic features and BMI were selected for model construction.
- The integrated model achieved an AUC of 0.899, demonstrating superior predictive performance.
- The Random Forest radiomics model and KNN clinical model showed promising individual results.
Conclusions:
- Preoperative MRI radiomic features have moderate predictive value for CR-POPF.
- Integrating BMI with radiomic features significantly enhances CR-POPF prediction accuracy.
- The developed integrated machine learning model shows excellent discrimination and calibration for CR-POPF risk.
