首页|University of Leuven (KU Leuven) Reports Findings in Machine Learning (Machine-L earning Approaches for Risk Prediction in Transcatheter Aortic Valve Implantatio n: Systematic Review and Meta-Analysis)
University of Leuven (KU Leuven) Reports Findings in Machine Learning (Machine-L earning Approaches for Risk Prediction in Transcatheter Aortic Valve Implantatio n: Systematic Review and Meta-Analysis)
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 from Leuven, Belgium, by News Rx journalists, research stated, "With the expanding integration of artificial i ntelligence (AI) and machine learning (ML) into the structural heart domain, num erous ML models have emerged for the prediction of adverse outcomes following tr anscatheter aortic valve implantation (TAVI). We aim to identify, describe, and critically appraise ML prediction models for adverse outcomes after TAVI." The news correspondents obtained a quote from the research from the University o f Leuven (KU Leuven), "Key objectives consisted in summarizing model performance , evaluating adherence to reporting guidelines, and transparency. We searched Pu bMed, SCOPUS, and Embase through August 2023. We selected published machine lear ning models predicting TAVI outcomes. Two reviewers independently screened artic les, extracted data, and assessed the study quality according to the PRISMA guid elines (Preferred Reporting Items for Systematic Reviews and Meta-Analyses). Out comes included summary C-statistics and model risk of bias assessed with the Pre diction Model Risk of Bias Assessment Tool (PROBAST). C-statistics were pooled u sing a random-effects model. Twenty-one studies (118,153 patients) employing var ious ML algorithms (76 models) were included in the systematic review. Predictiv e ability of models varied: 11.8% inadequate (C-statistic <0.60), 26.3% adequate (C-statistic 0.60-0.70), 31.6% acceptable (C-statistic 0.70-0.80), and 30.3% demonstrated excelle nt (C-statistic >0.80) performance. Meta-analyses reveal ed excellent predictive performance for early mortality (C-statistic: 0.81 [95 % CI, 0.65-0.91]), acceptable performance for 1-year mortality (C-statistic: 0.76 [95% CI, 0 .67-0.84]), and acceptable performance for predicting permane nt pacemaker implantation (C-statistic: 0.75 [95% CI, 0.51-0.90]). ML models for TAVI outcomes exhibit adequate to excellent performance, suggesting potential clinical utility."
LeuvenBelgiumEuropeCyborgsEmergi ng TechnologiesMachine LearningRisk and Prevention
NETL
NSTL
