首页|Sichuan University Reports Findings in Cerebral Hemorrhage (A novel machine lear ning model for predicting stroke associated pneumonia after spontaneous intracer ebral hemorrhage)
Sichuan University Reports Findings in Cerebral Hemorrhage (A novel machine lear ning model for predicting stroke associated pneumonia after spontaneous intracer ebral hemorrhage)
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 Central Nervous System Diseases and Conditions-Cerebral Hemorrhage is the subject of a report. Accor ding to news reporting originating from Chengdu, People's Republic of China, by NewsRx correspondents, research stated, "Pneumonia is one of the most common com plications after spontaneous intracerebral hemorrhage (sICH), namely stroke asso ciated pneumonia (SAP). Timely identification of targeted patients is beneficial to reduce poor prognosis." Our news editors obtained a quote from the research from Sichuan University, "So far, there is no consensus on SAP prediction, and application of existing predi ctors is limited. The aim of the study is to develop a machine learning model to predict SAP after sICH. We retrospectively reviewed 748 patients diagnosed with sICH and collected their data from four dimensions including demographic featur es, clinical features, medical history, and laboratory tests. Five machine learn ing algorithms including logistic regres-sion, gradient boosting decision tree, r andom forest, extreme gradient boosting, and category boosting were used to buil d and validate the predictive model. And we applied recursive feature eliminatio n with cross-validation to obtain the best feature combination for each model. T he predictive performance was evaluated by the areas under the receiver operatin g characteristic curves (AUC). A total of 237 patients were diagnosed as SAP. Th e model developed by category boosting yielded the most satisfied outcomes overa ll with its AUC in training set and test set were 0.8307 and 0.8178, respectivel y. The incidence of SAP after sICH in our center was 31.68%."
ChengduPeople's Republic of ChinaAsi aCentral Nervous System Diseases and ConditionsCerebral HemorrhageCerebrov ascular Diseases and ConditionsCyborgsEmerging TechnologiesHealth and Medi cineInfectious DiseaseLung Diseases and ConditionsMachine LearningPneumo niaPulmonologyRespiratory Tract Diseases and ConditionsRespiratory Tract I nfectionsStroke
NETL
NSTL
