Development and validation of a machine learning–based model for predicting textbook outcome after minimally invasive pancreaticoduodenectomy
- 1General Surgery, Cancer Center, Department of Gastrointestinal and Pancreatic Surgery, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital, Hangzhou Medical College), Hangzhou, Zhejiang 310014 China
- 2Department of Nursing, Zhejiang Provincial People’s Hospital (Affiliated People’s Hospital, Hangzhou Medical College, Hangzhou, China
Abstract
Background: Textbook Outcome (TO) has been proposed as a composite indicator reflecting overall surgical quality. With the expanding use of minimally invasive pancreaticoduodenectomy (MIPD), including laparoscopic and robotic-assisted approaches, reliable prediction of TO achievement has become essential. This study aimed to identify independent predictors of TO after MIPD and to develop an interpretable machine learning (ML)–based prediction model.
Methods: We retrospectively analyzed 411 consecutive patients who underwent MIPD at Zhejiang Provincial People’s Hospital between 2017 and 2023. Clinical, operative, and pathological variables were collected. The Least Absolute Shrinkage and Selection Operator regression was used for feature selection, and ten ML algorithms were developed and compared. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), Brier score, and decision curve analysis. Model interpretability was assessed using SHapley Additive exPlanations (SHAP).
Results: Of 411 patients, 263 (63.99%) achieved TO. Eight variables were identified as independent predictors: pancreatic duct diameter > 3 mm, intraoperative blood loss, Nutritional Risk Screening 2002 score, direct bilirubin, triglyceride, carbohydrate antigen 125, male, and body mass index. Among the ten algorithms, the Random Forest model demonstrated the best discrimination (AUC = 0.86; Brier score = 0.15). SHAP analysis confirmed that larger pancreatic duct diameter and reduced blood loss were most strongly associated with TO achievement.
Conclusions: An interpretable ML-based model accurately predicted TO after MIPD. The Random Forest algorithm demonstrated superior performance and may assist in individualized perioperative risk stratification and management.
Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12893-026-04068-8.
Related
- Development and internal validation of machine learning models for predicting lymph node metastasis in cutaneous head and neck melanoma
- Development and temporal validation of nomograms and machine learning models for predicting overall and cancer-specific survival in primary distal cholangiocarcinoma: a SEER-based study
- Development and validation of machine learning models for predicting pancreatic injury observed after tigecycline initiation: a retrospective real-world study
- Development and validation of an interpretable machine learning model for predicting in-hospital mortality among critically ill patients with liver cirrhosis
- A machine learning model for predicting ischemic and bleeding risk after percutaneous coronary intervention: Development and external validation
BibTeX
@article{zhang2026development,
title = {{Development and validation of a machine learning–based model for predicting textbook outcome after minimally invasive pancreaticoduodenectomy}},
author = {Yu Zhang and Xiaoqin Lu and Xiuping Weng and Yuwen Pu and Wenjing Wu},
journal = {BMC Surgery},
year = {2026},
month = aug,
doi = {10.1186/s12893-026-04068-8},
url = {https://doi.org/10.1186/s12893-026-04068-8},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Development and validation of a machine learning–based model for predicting textbook outcome after minimally invasive pancreaticoduodenectomy
AU - Yu Zhang
AU - Xiaoqin Lu
AU - Xiuping Weng
AU - Yuwen Pu
AU - Wenjing Wu
PY - 2026
DA - 2026/08/07
JO - BMC Surgery
DO - 10.1186/s12893-026-04068-8
UR - https://doi.org/10.1186/s12893-026-04068-8
AB - Background: Textbook Outcome (TO) has been proposed as a composite indicator reflecting overall surgical quality. With the expanding use of minimally invasive pancreaticoduodenectomy (MIPD), including laparoscopic and robotic-assisted approaches, reliable prediction of TO achievement has become essential. This study aimed to identify independent predictors of TO after MIPD and to develop an interpretable machine learning (ML)–based prediction model. Methods: We retrospectively analyzed 411 consecutive patients who underwent MIPD at Zhejiang Provincial People’s Hospital between 2017 and 2023. Clinical, operative, and pathological variables were collected. The Least Absolute Shrinkage and Selection Operator regression was used for feature selection, and ten ML algorithms were developed and compared. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), Brier score, and decision curve analysis. Model interpretability was assessed using SHapley Additive exPlanations (SHAP). Results: Of 411 patients, 263 (63.99%) achieved TO. Eight variables were identified as independent predictors: pancreatic duct diameter > 3 mm, intraoperative blood loss, Nutritional Risk Screening 2002 score, direct bilirubin, triglyceride, carbohydrate antigen 125, male, and body mass index. Among the ten algorithms, the Random Forest model demonstrated the best discrimination (AUC = 0.86; Brier score = 0.15). SHAP analysis confirmed that larger pancreatic duct diameter and reduced blood loss were most strongly associated with TO achievement. Conclusions: An interpretable ML-based model accurately predicted TO after MIPD. The Random Forest algorithm demonstrated superior performance and may assist in individualized perioperative risk stratification and management. Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12893-026-04068-8.
SN - 1471-2482
ER -