A novel machine learning-assisted clinical diagnosis support model for early identification of pancreatic injuries in patients with blunt abdominal trauma: a cross-national study

Abstract. Background. The recognition of pancreatic injury in blunt abdominal trauma is often severely delayed in clinical practice. The aim of this study was to develop a machine learning model to support clinical diagnosis for early detection of abdominal trauma. Methods. We retrospectively analyz...

Full description

Saved in:
Bibliographic Details
Main Authors: Sai Huang, Xuan Zhang, Bo Yang, Yue Teng, Li Mao, Lili Wang, Jing Wang, Xuan Zhou, Li Chen, Yuan Yao, Cong Feng
Format: Article
Language:English
Published: Wolters Kluwer Health/LWW 2023-12-01
Series:Emergency and Critical Care Medicine
Online Access:http://journals.lww.com/10.1097/EC9.0000000000000096
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850151573393506304
author Sai Huang
Xuan Zhang
Bo Yang
Yue Teng
Li Mao
Lili Wang
Jing Wang
Xuan Zhou
Li Chen
Yuan Yao
Cong Feng
author_facet Sai Huang
Xuan Zhang
Bo Yang
Yue Teng
Li Mao
Lili Wang
Jing Wang
Xuan Zhou
Li Chen
Yuan Yao
Cong Feng
author_sort Sai Huang
collection DOAJ
description Abstract. Background. The recognition of pancreatic injury in blunt abdominal trauma is often severely delayed in clinical practice. The aim of this study was to develop a machine learning model to support clinical diagnosis for early detection of abdominal trauma. Methods. We retrospectively analyzed of a large intensive care unit database (Medical Information Mart for Intensive Care [MIMIC]-IV) for model development and internal validation of the model, and performed outer validation based on a cross-national data set. Logistic regression was used to develop three models (PI-12, PI-12-2, and PI-24). Univariate and multivariate analyses were used to determine variables in each model. The primary outcome was early detection of a pancreatic injury of any grade in patients with blunt abdominal trauma in the first 24 hours after hospitalization. Results. The incidence of pancreatic injuries was 5.56% (n = 18) and 6.06% (n = 6) in the development (n = 324) and internal validation (n = 99) cohorts, respectively. Internal validation cohort showed good discrimination with an area under the receiver operator characteristic curve (AUC) value of 0.84 (95% confidence interval [CI]: 0.71–0.96) for PI-24. PI-24 had the best AUC, specificity, and positive predictive value (PPV) of all models, and thus it was chosen as the final model to support clinical diagnosis. PI-24 performed well in the outer validation cohort with an AUC value of 0.82 (95% CI: 0.65–0.98), specificity of 0.97 (95% CI: 0.91–1.00), and PPV of 0.67 (95% CI: 0.00–1.00). Conclusion. A novel machine learning-based model was developed to support clinical diagnosis to detect pancreatic injuries in patients with blunt abdominal trauma at an early stage.
format Article
id doaj-art-c87c43942b364763b5d331fdfe03534b
institution OA Journals
issn 2097-0617
2693-860X
language English
publishDate 2023-12-01
publisher Wolters Kluwer Health/LWW
record_format Article
series Emergency and Critical Care Medicine
spelling doaj-art-c87c43942b364763b5d331fdfe03534b2025-08-20T02:26:10ZengWolters Kluwer Health/LWWEmergency and Critical Care Medicine2097-06172693-860X2023-12-013414214810.1097/EC9.0000000000000096202312000-00002A novel machine learning-assisted clinical diagnosis support model for early identification of pancreatic injuries in patients with blunt abdominal trauma: a cross-national studySai Huang0Xuan Zhang1Bo Yang2Yue Teng3Li Mao4Lili Wang5Jing Wang6Xuan Zhou7Li Chen8Yuan Yao9Cong Feng10a Department of Hematology, Fifth Medical Center of Chinese PLA General Hospital, Beijing, Chinac Hospital Management Institute, Medical Innovation Research Department, Chinese PLA General Hospital, Beijing, Chinad Department of General Thoracic Surgery, First Medical Center of Chinese PLA General Hospital, Beijing, Chinae Department of Emergency Medicine, General Hospital of Northern Theatre Command, Shenyang, Liaoning, Chinac Hospital Management Institute, Medical Innovation Research Department, Chinese PLA General Hospital, Beijing, Chinaf Department of General Medicine, First Medical Center of Chinese PLA General Hospital, Beijing, Chinaf Department of General Medicine, First Medical Center of Chinese PLA General Hospital, Beijing, Chinag Department of Emergency, Hainan Hospital of Chinese PLA General Hospital, Sanya, Hainan, Chinaf Department of General Medicine, First Medical Center of Chinese PLA General Hospital, Beijing, Chinac Hospital Management Institute, Medical Innovation Research Department, Chinese PLA General Hospital, Beijing, Chinab National Clinical Research Center of Geriatric Diseases, Chinese PLA General Hospital, Beijing, ChinaAbstract. Background. The recognition of pancreatic injury in blunt abdominal trauma is often severely delayed in clinical practice. The aim of this study was to develop a machine learning model to support clinical diagnosis for early detection of abdominal trauma. Methods. We retrospectively analyzed of a large intensive care unit database (Medical Information Mart for Intensive Care [MIMIC]-IV) for model development and internal validation of the model, and performed outer validation based on a cross-national data set. Logistic regression was used to develop three models (PI-12, PI-12-2, and PI-24). Univariate and multivariate analyses were used to determine variables in each model. The primary outcome was early detection of a pancreatic injury of any grade in patients with blunt abdominal trauma in the first 24 hours after hospitalization. Results. The incidence of pancreatic injuries was 5.56% (n = 18) and 6.06% (n = 6) in the development (n = 324) and internal validation (n = 99) cohorts, respectively. Internal validation cohort showed good discrimination with an area under the receiver operator characteristic curve (AUC) value of 0.84 (95% confidence interval [CI]: 0.71–0.96) for PI-24. PI-24 had the best AUC, specificity, and positive predictive value (PPV) of all models, and thus it was chosen as the final model to support clinical diagnosis. PI-24 performed well in the outer validation cohort with an AUC value of 0.82 (95% CI: 0.65–0.98), specificity of 0.97 (95% CI: 0.91–1.00), and PPV of 0.67 (95% CI: 0.00–1.00). Conclusion. A novel machine learning-based model was developed to support clinical diagnosis to detect pancreatic injuries in patients with blunt abdominal trauma at an early stage.http://journals.lww.com/10.1097/EC9.0000000000000096
spellingShingle Sai Huang
Xuan Zhang
Bo Yang
Yue Teng
Li Mao
Lili Wang
Jing Wang
Xuan Zhou
Li Chen
Yuan Yao
Cong Feng
A novel machine learning-assisted clinical diagnosis support model for early identification of pancreatic injuries in patients with blunt abdominal trauma: a cross-national study
Emergency and Critical Care Medicine
title A novel machine learning-assisted clinical diagnosis support model for early identification of pancreatic injuries in patients with blunt abdominal trauma: a cross-national study
title_full A novel machine learning-assisted clinical diagnosis support model for early identification of pancreatic injuries in patients with blunt abdominal trauma: a cross-national study
title_fullStr A novel machine learning-assisted clinical diagnosis support model for early identification of pancreatic injuries in patients with blunt abdominal trauma: a cross-national study
title_full_unstemmed A novel machine learning-assisted clinical diagnosis support model for early identification of pancreatic injuries in patients with blunt abdominal trauma: a cross-national study
title_short A novel machine learning-assisted clinical diagnosis support model for early identification of pancreatic injuries in patients with blunt abdominal trauma: a cross-national study
title_sort novel machine learning assisted clinical diagnosis support model for early identification of pancreatic injuries in patients with blunt abdominal trauma a cross national study
url http://journals.lww.com/10.1097/EC9.0000000000000096
work_keys_str_mv AT saihuang anovelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT xuanzhang anovelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT boyang anovelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT yueteng anovelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT limao anovelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT liliwang anovelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT jingwang anovelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT xuanzhou anovelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT lichen anovelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT yuanyao anovelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT congfeng anovelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT saihuang novelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT xuanzhang novelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT boyang novelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT yueteng novelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT limao novelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT liliwang novelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT jingwang novelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT xuanzhou novelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT lichen novelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT yuanyao novelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy
AT congfeng novelmachinelearningassistedclinicaldiagnosissupportmodelforearlyidentificationofpancreaticinjuriesinpatientswithbluntabdominaltraumaacrossnationalstudy