Risk prediction and effect evaluation of complicated appendicitis based on XGBoost modeling

Abstract Purpose The distinction between complicated appendicitis (CAP) and uncomplicated appendicitis (UAP) remains challenging. The purpose of this study was to construct a safe and economical diagnostic model that can accurately and rapidly differentiate between CAP and UAP. Methods Patient data...

Full description

Saved in:
Bibliographic Details
Main Authors: Sunmeng Chen, Jianfu Xia, Beibei Xu, Yi Huang, Miaomiao Teng, Juyi Pan
Format: Article
Language:English
Published: BMC 2025-04-01
Series:BMC Gastroenterology
Subjects:
Online Access:https://doi.org/10.1186/s12876-025-03847-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849713000576974848
author Sunmeng Chen
Jianfu Xia
Beibei Xu
Yi Huang
Miaomiao Teng
Juyi Pan
author_facet Sunmeng Chen
Jianfu Xia
Beibei Xu
Yi Huang
Miaomiao Teng
Juyi Pan
author_sort Sunmeng Chen
collection DOAJ
description Abstract Purpose The distinction between complicated appendicitis (CAP) and uncomplicated appendicitis (UAP) remains challenging. The purpose of this study was to construct a safe and economical diagnostic model that can accurately and rapidly differentiate between CAP and UAP. Methods Patient data from 773 appendectomies were retrospectively collected, important features were selected using random forests, and the data were divided into training and test sets in a 3:1 ratio. An integrated learning algorithm, Extreme Gradient Boosting (XGBoost), was introduced to predict the risk of CAP and compared with Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (CART) algorithms. A comprehensive comparison of the four algorithms was performed using model performance metrics such as the area under the receiver’s operating characteristic curve (AUC), sensitivity, specificity, accuracy, precision, negative predictive value(NPV), positive predictive value(PPV),calibration curves, and clinical decision curve analysis (DCA). Result The results show that all four prediction models exhibit some predictive ability. The XGBoost model showed the best prediction with AUC, accuracy, sensitivity, specificity,NPV and PPV of 0.914, 0.855, 0.865, 0.846,0.848 and 0.897, respectively, followed by the SVM model with results of AUC, accuracy, sensitivity, specificity,NPV and PPV of 0.882, 0.819, 0.865, 0.779, 0.770 and 0.871, respectively. XGBoost and SVM models show very good calibration. The XGBoost model showed better net clinical benefit compared to the DCA curves of the other models. Conclusion Predictive models based on the XGBoost algorithm have good performance in predicting the risk of acute appendicitis progressing to complicated appendicitis, which helps to optimize clinical decision making.
format Article
id doaj-art-edd9e7ecb9f94741972ccabf817e615e
institution DOAJ
issn 1471-230X
language English
publishDate 2025-04-01
publisher BMC
record_format Article
series BMC Gastroenterology
spelling doaj-art-edd9e7ecb9f94741972ccabf817e615e2025-08-20T03:14:06ZengBMCBMC Gastroenterology1471-230X2025-04-0125111210.1186/s12876-025-03847-6Risk prediction and effect evaluation of complicated appendicitis based on XGBoost modelingSunmeng Chen0Jianfu Xia1Beibei Xu2Yi Huang3Miaomiao Teng4Juyi Pan5Department of General Surgery, The Dingli Clinical College of Wenzhou Medical University (Wenzhou Central Hospital)Department of General Surgery, The Dingli Clinical College of Wenzhou Medical University (Wenzhou Central Hospital)Department of Gastroenterology, Wenzhou Third Clinical Institute Affiliated to Wenzhou Medical University, The Third Affiliated Hospital of Shanghai UniversityDepartment of General Surgery, Wenzhou Third Clinical Institute Affiliated to Wenzhou Medical University, The Third Affiliated Hospital of Shanghai UniversityDepartment of Gastroenterology, Postgraduate Training Base Alliance of Wenzhou Medical UniversityDepartment of Gastroenterology, Wenzhou Third Clinical Institute Affiliated to Wenzhou Medical University, The Third Affiliated Hospital of Shanghai UniversityAbstract Purpose The distinction between complicated appendicitis (CAP) and uncomplicated appendicitis (UAP) remains challenging. The purpose of this study was to construct a safe and economical diagnostic model that can accurately and rapidly differentiate between CAP and UAP. Methods Patient data from 773 appendectomies were retrospectively collected, important features were selected using random forests, and the data were divided into training and test sets in a 3:1 ratio. An integrated learning algorithm, Extreme Gradient Boosting (XGBoost), was introduced to predict the risk of CAP and compared with Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (CART) algorithms. A comprehensive comparison of the four algorithms was performed using model performance metrics such as the area under the receiver’s operating characteristic curve (AUC), sensitivity, specificity, accuracy, precision, negative predictive value(NPV), positive predictive value(PPV),calibration curves, and clinical decision curve analysis (DCA). Result The results show that all four prediction models exhibit some predictive ability. The XGBoost model showed the best prediction with AUC, accuracy, sensitivity, specificity,NPV and PPV of 0.914, 0.855, 0.865, 0.846,0.848 and 0.897, respectively, followed by the SVM model with results of AUC, accuracy, sensitivity, specificity,NPV and PPV of 0.882, 0.819, 0.865, 0.779, 0.770 and 0.871, respectively. XGBoost and SVM models show very good calibration. The XGBoost model showed better net clinical benefit compared to the DCA curves of the other models. Conclusion Predictive models based on the XGBoost algorithm have good performance in predicting the risk of acute appendicitis progressing to complicated appendicitis, which helps to optimize clinical decision making.https://doi.org/10.1186/s12876-025-03847-6Disease risk predictionMachine learningComplicated appendicitisXGBoost modelPredictive modeling
spellingShingle Sunmeng Chen
Jianfu Xia
Beibei Xu
Yi Huang
Miaomiao Teng
Juyi Pan
Risk prediction and effect evaluation of complicated appendicitis based on XGBoost modeling
BMC Gastroenterology
Disease risk prediction
Machine learning
Complicated appendicitis
XGBoost model
Predictive modeling
title Risk prediction and effect evaluation of complicated appendicitis based on XGBoost modeling
title_full Risk prediction and effect evaluation of complicated appendicitis based on XGBoost modeling
title_fullStr Risk prediction and effect evaluation of complicated appendicitis based on XGBoost modeling
title_full_unstemmed Risk prediction and effect evaluation of complicated appendicitis based on XGBoost modeling
title_short Risk prediction and effect evaluation of complicated appendicitis based on XGBoost modeling
title_sort risk prediction and effect evaluation of complicated appendicitis based on xgboost modeling
topic Disease risk prediction
Machine learning
Complicated appendicitis
XGBoost model
Predictive modeling
url https://doi.org/10.1186/s12876-025-03847-6
work_keys_str_mv AT sunmengchen riskpredictionandeffectevaluationofcomplicatedappendicitisbasedonxgboostmodeling
AT jianfuxia riskpredictionandeffectevaluationofcomplicatedappendicitisbasedonxgboostmodeling
AT beibeixu riskpredictionandeffectevaluationofcomplicatedappendicitisbasedonxgboostmodeling
AT yihuang riskpredictionandeffectevaluationofcomplicatedappendicitisbasedonxgboostmodeling
AT miaomiaoteng riskpredictionandeffectevaluationofcomplicatedappendicitisbasedonxgboostmodeling
AT juyipan riskpredictionandeffectevaluationofcomplicatedappendicitisbasedonxgboostmodeling