首页|Tsinghua University Reports Findings in Sepsis (Prediction of sepsis within 24 h ours at the triage stage in emergency departments using machine learning)
Tsinghua University Reports Findings in Sepsis (Prediction of sepsis within 24 h ours at the triage stage in emergency departments using machine learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Blood Diseases and Con ditions - Sepsis is the subject of a report. According to news reporting origina ting from Beijing, People's Republic of China, by NewsRx correspondents, researc h stated, "Sepsis is one of the main causes of mortality in intensive care units (ICUs). Early prediction is critical for reducing injury." Our news editors obtained a quote from the research from Tsinghua University, "A s approximately 36 % of sepsis occur within 24 h after emergency de partment (ED) admission in Medical Information Mart for Intensive Care (MIMIC-IV ), a prediction system for the ED triage stage would be helpful. Previous method s such as the quick Sequential Organ Failure Assessment (qSOFA) are more suitabl e for screening than for prediction in the ED, and we aimed to find a light-weig ht, convenient prediction method through machine learning. We accessed the MIMIC -IV for sepsis patient data in the EDs. Our dataset comprised demographic inform ation, vital signs, and synthetic features. Extreme Gradient Boosting (XGBoost) was used to predict the risk of developing sepsis within 24 h after ED admission . AdditionAlly, SHapley Additive exPlanations (SHAP) was employed to provide a c omprehensive interpretation of the model's results. Ten percent of the patients were randomly selected as the testing set, while the remaining patients were use d for training with 10-fold cross-validation. For 10-fold cross-validation on 14 ,957 samples, we reached an accuracy of 84.1%±0.3% and an area under the receiver operating characteristic (ROC) curve of 0.92±0.02. The model achieved similar performance on the testing set of 1,662 patients. SHA P values showed that the five most important features were acuity, arrival trans portation, age, shock index, and respiratory rate. Machine learning models such as XGBoost may be used for sepsis prediction using only a smAll amount of data c onveniently collected in the ED triage stage."
BeijingPeople's Republic of ChinaAsi aBlood Diseases and ConditionsBloodstream InfectionCyborgsEmerging Techn ologiesHealth and MedicineMachine LearningRisk and PreventionSepsisSep ticemia
NETL
NSTL
