A radiomics-clinical predictive model for difficult laparoscopic cholecystectomy based on preoperative CT imaging: a retrospective single center study

Abstract Background Accurately identifying difficult laparoscopic cholecystectomy (DLC) preoperatively remains a clinical challenge. Previous studies utilizing clinical variables or morphological imaging markers have demonstrated suboptimal predictive performance. This study aims to develop an optim...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui-Tao Sun, Chang-Lei Li, Yu-Min Jiang, Ao-Yun Hao, Kui Liu, Kun Li, Bin Tan, Xiao-Nan Yang, Jiu-Fa Cui, Wen-Ye Bai, Wei-Yu Hu, Jing-Yu Cao, Chao Qu
Format: Article
Language:English
Published: BMC 2025-07-01
Series:World Journal of Emergency Surgery
Subjects:
Online Access:https://doi.org/10.1186/s13017-025-00635-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849332935260372992
author Rui-Tao Sun
Chang-Lei Li
Yu-Min Jiang
Ao-Yun Hao
Kui Liu
Kun Li
Bin Tan
Xiao-Nan Yang
Jiu-Fa Cui
Wen-Ye Bai
Wei-Yu Hu
Jing-Yu Cao
Chao Qu
author_facet Rui-Tao Sun
Chang-Lei Li
Yu-Min Jiang
Ao-Yun Hao
Kui Liu
Kun Li
Bin Tan
Xiao-Nan Yang
Jiu-Fa Cui
Wen-Ye Bai
Wei-Yu Hu
Jing-Yu Cao
Chao Qu
author_sort Rui-Tao Sun
collection DOAJ
description Abstract Background Accurately identifying difficult laparoscopic cholecystectomy (DLC) preoperatively remains a clinical challenge. Previous studies utilizing clinical variables or morphological imaging markers have demonstrated suboptimal predictive performance. This study aims to develop an optimal radiomics-clinical model by integrating preoperative CT-based radiomics features with clinical characteristics. Methods A retrospective analysis was conducted on 2,055 patients who underwent laparoscopic cholecystectomy (LC) for cholecystitis at our center. Preoperative CT images were processed with super-resolution reconstruction to improve consistency, and high-throughput radiomic features were extracted from the gallbladder wall region. A combination of radiomic and clinical features was selected using the Boruta-LASSO algorithm. Predictive models were constructed using six machine learning algorithms and validated, with model performance evaluated based on the AUC, accuracy, Brier score, and DCA to identify the optimal model. Model interpretability was further enhanced using the SHAP method. Results The Boruta-LASSO algorithm identified 10 key radiomic and clinical features for model construction, including the Rad-Score, gallbladder wall thickness, fibrinogen, C-reactive protein, and low-density lipoprotein cholesterol. Among the six machine learning models developed, the radiomics-clinical model based on the random forest algorithm demonstrated the best predictive performance, with an AUC of 0.938 in the training cohort and 0.874 in the validation cohort. The Brier score, calibration curve, and DCA confirmed the superior predictive capability of this model, significantly outperforming previously published models. The SHAP analysis further visualized the importance of features, enhancing model interpretability. Conclusion This study developed the first radiomics-clinical random forest model for the preoperative prediction of DLC by machine learning algorithms. This predictive model supports safer and individualized surgical planning and treatment strategies.
format Article
id doaj-art-84b6d1a764cd4fa288358def4477c04f
institution Kabale University
issn 1749-7922
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series World Journal of Emergency Surgery
spelling doaj-art-84b6d1a764cd4fa288358def4477c04f2025-08-20T03:46:03ZengBMCWorld Journal of Emergency Surgery1749-79222025-07-0120111710.1186/s13017-025-00635-1A radiomics-clinical predictive model for difficult laparoscopic cholecystectomy based on preoperative CT imaging: a retrospective single center studyRui-Tao Sun0Chang-Lei Li1Yu-Min Jiang2Ao-Yun Hao3Kui Liu4Kun Li5Bin Tan6Xiao-Nan Yang7Jiu-Fa Cui8Wen-Ye Bai9Wei-Yu Hu10Jing-Yu Cao11Chao Qu12Department of Hepatobiliary and Pancreatic Surgery, The Affiliated Hospital of Qingdao UniversityDepartment of Hepatobiliary and Pancreatic Surgery, The Affiliated Hospital of Qingdao UniversityDepartment of Hepatobiliary and Pancreatic Surgery, The Affiliated Hospital of Qingdao UniversityDepartment of Hepatobiliary and Pancreatic Surgery, The Affiliated Hospital of Qingdao UniversityDepartment of Hepatobiliary and Pancreatic Surgery, The Affiliated Hospital of Qingdao UniversityDepartment of Hepatobiliary and Pancreatic Surgery, The Affiliated Hospital of Qingdao UniversityDepartment of Hepatobiliary and Pancreatic Surgery, The Affiliated Hospital of Qingdao UniversityDepartment of Radiology, The Affiliated Hospital of Qingdao UniversityDepartment of Radiology, The Affiliated Hospital of Qingdao UniversityDepartment of Hepatobiliary and Pancreatic Surgery, The Affiliated Hospital of Qingdao UniversityDepartment of Hepatobiliary and Pancreatic Surgery, The Affiliated Hospital of Qingdao UniversityDepartment of Hepatobiliary and Pancreatic Surgery, The Affiliated Hospital of Qingdao UniversityDepartment of Hepatobiliary and Pancreatic Surgery, The Affiliated Hospital of Qingdao UniversityAbstract Background Accurately identifying difficult laparoscopic cholecystectomy (DLC) preoperatively remains a clinical challenge. Previous studies utilizing clinical variables or morphological imaging markers have demonstrated suboptimal predictive performance. This study aims to develop an optimal radiomics-clinical model by integrating preoperative CT-based radiomics features with clinical characteristics. Methods A retrospective analysis was conducted on 2,055 patients who underwent laparoscopic cholecystectomy (LC) for cholecystitis at our center. Preoperative CT images were processed with super-resolution reconstruction to improve consistency, and high-throughput radiomic features were extracted from the gallbladder wall region. A combination of radiomic and clinical features was selected using the Boruta-LASSO algorithm. Predictive models were constructed using six machine learning algorithms and validated, with model performance evaluated based on the AUC, accuracy, Brier score, and DCA to identify the optimal model. Model interpretability was further enhanced using the SHAP method. Results The Boruta-LASSO algorithm identified 10 key radiomic and clinical features for model construction, including the Rad-Score, gallbladder wall thickness, fibrinogen, C-reactive protein, and low-density lipoprotein cholesterol. Among the six machine learning models developed, the radiomics-clinical model based on the random forest algorithm demonstrated the best predictive performance, with an AUC of 0.938 in the training cohort and 0.874 in the validation cohort. The Brier score, calibration curve, and DCA confirmed the superior predictive capability of this model, significantly outperforming previously published models. The SHAP analysis further visualized the importance of features, enhancing model interpretability. Conclusion This study developed the first radiomics-clinical random forest model for the preoperative prediction of DLC by machine learning algorithms. This predictive model supports safer and individualized surgical planning and treatment strategies.https://doi.org/10.1186/s13017-025-00635-1Laparoscopic cholecystectomyRadiomicsMachine learningSurgical difficulty prediction
spellingShingle Rui-Tao Sun
Chang-Lei Li
Yu-Min Jiang
Ao-Yun Hao
Kui Liu
Kun Li
Bin Tan
Xiao-Nan Yang
Jiu-Fa Cui
Wen-Ye Bai
Wei-Yu Hu
Jing-Yu Cao
Chao Qu
A radiomics-clinical predictive model for difficult laparoscopic cholecystectomy based on preoperative CT imaging: a retrospective single center study
World Journal of Emergency Surgery
Laparoscopic cholecystectomy
Radiomics
Machine learning
Surgical difficulty prediction
title A radiomics-clinical predictive model for difficult laparoscopic cholecystectomy based on preoperative CT imaging: a retrospective single center study
title_full A radiomics-clinical predictive model for difficult laparoscopic cholecystectomy based on preoperative CT imaging: a retrospective single center study
title_fullStr A radiomics-clinical predictive model for difficult laparoscopic cholecystectomy based on preoperative CT imaging: a retrospective single center study
title_full_unstemmed A radiomics-clinical predictive model for difficult laparoscopic cholecystectomy based on preoperative CT imaging: a retrospective single center study
title_short A radiomics-clinical predictive model for difficult laparoscopic cholecystectomy based on preoperative CT imaging: a retrospective single center study
title_sort radiomics clinical predictive model for difficult laparoscopic cholecystectomy based on preoperative ct imaging a retrospective single center study
topic Laparoscopic cholecystectomy
Radiomics
Machine learning
Surgical difficulty prediction
url https://doi.org/10.1186/s13017-025-00635-1
work_keys_str_mv AT ruitaosun aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT changleili aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT yuminjiang aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT aoyunhao aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT kuiliu aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT kunli aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT bintan aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT xiaonanyang aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT jiufacui aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT wenyebai aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT weiyuhu aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT jingyucao aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT chaoqu aradiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT ruitaosun radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT changleili radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT yuminjiang radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT aoyunhao radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT kuiliu radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT kunli radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT bintan radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT xiaonanyang radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT jiufacui radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT wenyebai radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT weiyuhu radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT jingyucao radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy
AT chaoqu radiomicsclinicalpredictivemodelfordifficultlaparoscopiccholecystectomybasedonpreoperativectimagingaretrospectivesinglecenterstudy