首页|University Hospital San Juan de Alicante Reports Findings in Machine Learning (A step forward in the diagnosis of urinary tract infections: from machine learnin g to clinical practice)
University Hospital San Juan de Alicante Reports Findings in Machine Learning (A step forward in the diagnosis of urinary tract infections: from machine learnin g to clinical practice)
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 Machine Learning is th e subject of a report. According to news reporting originating from Alicante, Sp ain, by NewsRx correspondents, research stated, “Urinary tract infections (UTIs) are common infections within the Emergency Department (ED), causing increased l aboratory workloads and unnecessary antibiotics prescriptions. The aim of this s tudy was to improve UTI diagnostics in clinical practice by application of machi ne learning (ML) models for real-time UTI prediction.” Our news editors obtained a quote from the research from University Hospital San Juan de Alicante, “In a retrospective study, patient information and outcomes f rom Emergency Department patients, with positive and negative culture results, w ere used to design models - ‘Random Forest’ and ‘Neural Network’ - for the predi ction of UTIs. The performance of these predictive models was validated in a cro ss-sectional study. In a quasi-experimental study, the impact of UTI risk assess ment was investigated by evaluating changes in the behaviour of clinicians, meas uring changes in antibiotic prescriptions and urine culture requests. First, we trained and tested two different predictive models with 8692 cases. Second, we i nvestigated the performance of the predictive models in clinical practice with 9 62 cases (Area under the curve was between 0.81 to 0.88). The best performance w as the combination of both models. Finally, the assessment of the risk for UTIs was implemented into clinical practice and allowed for the reduction of unnecess ary urine cultures and antibiotic prescriptions for patients with a low risk of UTI, as well as targeted diagnostics and treatment for patients with a high risk of UTI.”
AlicanteSpainEuropeCyborgsDiagno stics and ScreeningDrugs and TherapiesEmerging TechnologiesHealth and Medi cineMachine LearningUrinary Tract
NETL
NSTL
