首页|Central South University Reports Findings in Gastrointestinal Bleeding (Prognosi s of major bleeding based on residual variables and machine learning for critica l patients with upper gastrointestinal bleeding: A multicenter study)
Central South University Reports Findings in Gastrointestinal Bleeding (Prognosi s of major bleeding based on residual variables and machine learning for critica l patients with upper gastrointestinal bleeding: A multicenter study)
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 Digestive System Disea ses and Conditions - Gastrointestinal Bleeding is the subject of a report. Accor ding to news reporting originating from Changsha, People’s Republic of China, by NewsRx correspondents, research stated, “Upper gastrointestinal bleeding (UGIB) is a significant cause of morbidity and mortality worldwide. This study investi gates the use of residual variables and machine learning (ML) models for predict ing major bleeding in patients with severe UGIB after their first intensive care unit (ICU) admission.” Our news editors obtained a quote from the research from Central South Universit y, “The Medical Information Mart for Intensive Care IV and eICU databases were u sed. Conventional ML and long short-term memory models were constructed using pr e-ICU and ICU admission day data to predict the recurrence of major gastrointest inal bleeding. In the models, residual data were utilized by subtracting the nor mal range from the test result. The models included eight algorithms. Shapley ad ditive explanations and saliency maps were used for feature interpretability. Tw enty-five ML models were developed using data from 2604 patients. The light grad ient-boosting machine algorithm model using pre-ICU admission residual data outp erformed other models that used test results directly, with an AUC of 0.96. The key factors included aspartate aminotransferase, blood urea nitrogen, albumin, l ength of ICU admission, and respiratory rate. ML models using residuals improved the accuracy and interpretability in predicting major bleeding during ICU admis sion in patients with UGIB.”
ChangshaPeople’s Republic of ChinaAs iaCyborgsDigestive System Diseases and ConditionsEmerging TechnologiesGa stroenterologyGastrointestinal BleedingHealth and MedicineMachine Learning
NETL
NSTL
