首页|Study Findings from Fondazione Policlinico Universitario A.Gemelli IRCCS Broade n Understanding of Machine Learning (A Machine Learning Predictive Model of Bloo dstream Infection in Hospitalized Patients)
Study Findings from Fondazione Policlinico Universitario A.Gemelli IRCCS Broade n Understanding of Machine Learning (A Machine Learning Predictive Model of Bloo dstream Infection in Hospitalized Patients)
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 artificial intelligenc e is the subject of a new report.According to news originating from Rome,Italy,by NewsRx correspondents,research stated,"The aim of the study was to build a machine learning-based predictive model to discriminate between hospitalized p atients at low risk and high risk of bloodstream infection (BSI).A Data Mart in cluding all patients hospitalized between January 2016 and December 2019 with su spected BSI was built." Our news reporters obtained a quote from the research from Fondazione Policlinic o Universitario A.Gemelli IRCCS:"Multivariate logistic regression was applied to develop a clinically interpretable machine learning predictive model.The mod el was trained on 2016-2018 data and tested on 2019 data.A feature selection ba sed on a univariate logistic regression first selected candidate predictors of B SI.A multivariate logistic regression with stepwise feature selection in five-f old cross-validation was applied to express the risk of BSI.A total of 5660 hos pitalizations (4026 and 1634 in the training and the validation subsets,respect ively) were included.Eleven predictors of BSI were identified.The performance of the model in terms of AUROC was 0.74.Based on the interquartile predicted ri sk score,508 (31.1%) patients were defined as being at low risk,7 76 (47.5%) at medium risk,and 350 (21.4%) at high ris k of BSI."
Fondazione Policlinico Universitario A.Gemelli IRCCSRomeItalyEuropeCyborgsEmerging TechnologiesMachine Lear ning
NETL
NSTL
