广西医科大学学报2024，Vol.41Issue(5)：748-755,8.DOI:10.16190/j.cnki.45-1211/r.2024.05.016
机器学习预测急性上消化道出血患者干预及再出血的风险价值
The value of predicting intervention and rebleeding risk for patients with acute upper gastro-intestinal bleeding based on machine learning
摘要
Abstract
Objective:To investigate the value of machine learning(ML)in predicting blood transfusion inter-vention and rebleeding in patients with acute upper gastrointestinal bleeding(AUGIB).Methods:A retrospective analysis was conducted on the clinical data of 512 AUGIB patients who were admitted to the Third People's Hos-pital of Yunnan Province from July 2020 to October 2023.Variable importance analysis was performed using eX-treme gradient boosting(XGBoost),and the top 10 factors in importance ranking were selected as variables in the model.Classification predictions were carried out and compared using logistic regression,XGBoost,random for-est,support vector machine(SVM),and K-nearest neighbors algorithms(KNN).The best model was chosen,and interpretable analysis of the features selected by ML was performed using SHAP plots.The clinical value was as-sessed by comparing the best model with the commonly used AUGIB scoring systems.Results:The XGBoost al-gorithm model identified the top 10 risk factors for transfusion intervention as hemoglobin,international normal-ized ratio(INR),albumin,systolic blood pressure,urea,anesthesia risk score,pulse,creatinine,age,and presence of shock.Using these important features for modeling,the XGBoost algorithm provided the best predictive per-formance for transfusion intervention in AUGIB patients and it achieved the highest score,indicating its superior ability to identify patients at risk for gastrointestinal bleeding who required transfusion intervention,and outper-forming the common clinical Glasgow Blatchford(GBS),AIMS65,ABC,and T scoring systems.According to the XGBoost algorithm model,the top 10 important features scores for patients with rebleeding were age,creati-nine,INR,hemoglobin,anesthesia risk score,albumin,systolic blood pressure,urea,liver cirrhosis,and gender.Modeling with these top 10 risk factors,the XGBoost algorithm also showed the best predictive performance for re-bleeding in AUGIB patients,surpassing the aforementioned four scoring systems.Conclusion:In predicting the value of transfusion intervention and rebleeding in AUGIB patients,ML model is superior to GBS,AIMS65,ABC and T scoring systems.The XGBoost model algorithm is superior,with better effectiveness.关键词
机器学习/极限梯度提升算法/急性上消化道出血/风险评估Key words
machine learning/eXtreme gradient boosting/acute upper gastrointestinal bleeding/risk assessment分类
医药卫生引用本文复制引用
刘界宇,黄继华,李泗云,吉玉屏,刘中建,张帆..机器学习预测急性上消化道出血患者干预及再出血的风险价值[J].广西医科大学学报,2024,41(5):748-755,8.基金项目
云南省"兴滇英才支持计划"名医资助项目(No.XDYC-MY-2022-0007) （No.XDYC-MY-2022-0007）
云南省科技厅科技计划项目(No.202301AY070001-225 （）
No.202301AU070131) （）
