首页|Santa Maria Nuova Hospital Reports Findings in Atrial Fibrillation (Machine lear ning approach for prediction of outcomes in anticoagulated patients with atrial fibrillation)
Santa Maria Nuova Hospital Reports Findings in Atrial Fibrillation (Machine lear ning approach for prediction of outcomes in anticoagulated patients with atrial fibrillation)
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 Heart Disorders and Di seases - Atrial Fibrillation is the subject of a report. According to news repor ting originating from Florence, Italy, by NewsRx correspondents, research stated , “The accuracy of available prediction tools for clinical outcomes in patients with atrial fibrillation (AF) remains modest. Machine Learning (ML) has been use d to predict outcomes in the AF population, but not in a population entirely on anticoagulant therapy.” Our news editors obtained a quote from the research from Santa Maria Nuova Hospi tal, “Different supervised ML models were applied to predict all-cause death, ca rdiovascular (CV) death, major bleeding and stroke in anticoagulated patients wi th AF, processing data from the multicenter START-2 Register. 11078 AF patients (male n = 6029, 54.3%) were enrolled with a median follow-up period of 1.5 years [IQR 1.0-2.6]. Patients on V itamin K Antagonists (VKA) were 5135 (46.4%) and 5943 (53.6% ) were on Direct Oral Anticoagulants (DOAC). Using Multi-Gate Mixture of Experts , a cross-validated AUC of 0.779 ± 0.016 and 0.745 ± 0.022 were obtained, respec tively, for the prediction of all-cause death and CV-death in the overall popula tion. The best ML model outperformed CHADSVASC and HAS-BLED for all-cause death prediction (p <0.001 for both). When compared to HAS-BLED, Gradient Boosting improved major bleeding prediction in DOACs patients (0.711 v s. 0.586, p<0.001). A very low number of events during fol low-up (52) resulted in a suboptimal ischemic stroke prediction (best AUC of 0.6 06 ± 0.117 in overall population). Body mass index, age, renal function, platele t count and hemoglobin levels resulted the most important variables for ML predi ction.”
FlorenceItalyEuropeAtrial Fibrilla tionCardiac ArrhythmiasCyborgsDrugs and TherapiesEmerging TechnologiesHealth and MedicineHeart DiseaseHeart Disorders and DiseasesMachine Learni ng
NETL
NSTL
