首页|Researchers at Semmelweis Egyetem Target Machine Learning (The role of machine l earning in the modern management of heart failure)
Researchers at Semmelweis Egyetem Target Machine Learning (The role of machine l earning in the modern management of heart failure)
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 – Data detailed on artificial intelligen ce have been presented. According to news originating from the Semmelweis Egyete m by NewsRx correspondents, research stated, “The use of machine learning is exp loding in all areas of healthcare, including the diagnosis and treatment of hear t failure. Supervised machine learning can help predict the onset of heart failu re, establish the diagnosis, and even predict decompensations. Conversely, unsup ervised machine learning is chiefly used for phenotyping of the heart failure po pulation.” Our news editors obtained a quote from the research from Semmelweis Egyetem: “Se veral studies have identified distinctive groups of heart failure patients, but the widespread clinical implementation is still lacking. Our study aims to ident ify groups with similar characteristics among patients cared for HFrEF at the Ci ty Major Heart and Vascular Clinic of Semmelweis University using unsupervised m achine learning and to describe the characteristic features of the resulting gro ups. We then examine the differences in outcome between the resulting groups. Me thods: data from outpatients with reduced left ventricular ejection fraction hea rt failure were collected in a prospective registry. A total of 27 parameters in cluded anamnestic data, laboratory tests, echocardiographic parameters and EQ5D quality of life questionnaire scores. The composite of hospitalization for heart failure and all-cause mortality was considered as the endpoint of the study. Sp ectral clustering was used to divide the population into three groups. The group s were plotted spatially using principal component analysis. Finally, we compare d the groups in terms of parameters and endpoint occurrence. Three characteristi c groups were identified in the analysis of 259 patients. The first group consis ted of 89 patients with ischemic etiology, more complaining, renal failure, and requiring duck diuretic therapy. The second group of 99 patients consisted of pr edominantly younger patients with atrial fibrillation, non-ischemic cardiomyopat hy, dilated left ventricle, and a lower ejection fraction, almost exclusively on ARNI therapy. The third group of 71 patients included patients with the best ej ection fraction, frequently taking ACE inhibitors and MRAs, and not requiring lo op diuretics. Group 1 had significantly worse prognosis than group 2 (p=0.013) w ith a trend to worse prognosis compared to group 3.”
Semmelweis EgyetemCyborgsEmerging Te chnologiesMachine Learning
NETL
NSTL
