Related Experiment Video
Updated: Jul 6, 2025
Technical Detail for Robot Assisted Pancreaticoduodenectomy
Published on: September 28, 2019
Machine learning approach to predict postpancreatectomy hemorrhage following pancreaticoduodenectomy: a retrospective
Shinichi Ikuta1, Masataka Fujikawa2, Takayoshi Nakajima2
1Department of Surgery, Meiwa Hospital, 4-31 Agenaruo, Nishinomiya, Hyogo, 663-8186, Japan. g2s1002@gmail.com.
Background:
Postpancreatectomy hemorrhage (PPH) is a rare yet dreaded complication following pancreaticoduodenectomy (PD). This retrospective study aimed to explore a machine learning (ML) model for predicting PPH in PD patients.
Methods:
A total of 284 patients who underwent open PD at our institute were included in the analysis. To address the issue of imbalanced data, the adaptive synthetic sampling (ADASYN) technique was employed. The best-performing ML model was selected using the PyCaret library in Python and evaluated based on recall, precision, and F1 score metrics. In addition to assessing the model's performance on the test data, bootstrap validation (n = 1000) with the original dataset was conducted.
Results:
PPH occurred in 11 patients (3.9%), with a median onset time of 22 days postoperatively. These minority cases were oversampled to 85 using ADASYN. The extra trees classifier demonstrated superior performance with recall, precision, and F1 score of 0.967, 0.914, and 0.937, respectively. Both validation using the test data and bootstrap resampling consistently demonstrated recall, precision, and F1 score exceeding 0.9. The model identified the peak value of C-reactive protein during the first 7 postoperative days as the most significant feature, followed by the preoperative neutrophil-to-lymphocyte ratio.
Conclusions:
This study highlights the potential of the ML approach to predict PPH occurrence following PD. Vigilance and early interventions guided by such model predictions could positively impact outcomes for high-risk patients.
Insights
This study developed a machine learning model to predict postpancreatectomy hemorrhage (PPH) after pancreaticoduodenectomy (PD). The model achieved high accuracy, identifying key predictive factors for early intervention in high-risk patients.
Area of Science:
- Surgical Oncology
- Medical Informatics
- Predictive Analytics
Background:
- Postpancreatectomy hemorrhage (PPH) is a severe complication after pancreaticoduodenectomy (PD).
- Predicting PPH is crucial for improving patient outcomes.
- Machine learning (ML) offers a potential solution for PPH prediction.
Purpose of the Study:
- To develop and evaluate a machine learning model for predicting PPH in patients undergoing PD.
- To identify significant predictors of PPH.
Main Methods:
- Retrospective analysis of 284 patients undergoing open PD.
- Utilized adaptive synthetic sampling (ADASYN) for imbalanced data.
- Employed PyCaret library for ML model selection and evaluation (recall, precision, F1 score).
- Validated model performance using test data and bootstrap resampling (n=1000).
Main Results:
- PPH occurred in 3.9% of patients, with a median onset of 22 days.
- The Extra Trees Classifier achieved high performance (recall 0.967, precision 0.914, F1 0.937).
- Model validation confirmed consistent performance exceeding 0.9 for key metrics.
- Peak C-reactive protein (first 7 days) and preoperative neutrophil-to-lymphocyte ratio were key predictors.
Conclusions:
- Machine learning models show promise for predicting PPH after PD.
- Early identification of high-risk patients can guide interventions and improve outcomes.
