首页|University of Urbino Reports Findings in Machine Learning (Federated unsupervise d random forest for privacy-preserving patient stratification)
University of Urbino Reports Findings in Machine Learning (Federated unsupervise d random forest for privacy-preserving patient stratification)
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 Urbino, Italy, by NewsRx journalists, research stated, “In the realm of precision medicine, effective pa tient stratification and disease subtyping demand innovative methodologies tailo red for multiomics data. Clustering techniques applied to multi-omics data have become instrumental in identifying distinct subgroups of patients, enabling a f iner-grained understanding of disease variability.” The news correspondents obtained a quote from the research from the University o f Urbino, “Meanwhile, clinical datasets are often small and must be aggregated f rom multiple hospitals. Online data sharing, however, is seen as a significant c hallenge due to privacy concerns, potentially impeding big data’s role in medica l advancements using machine learning. This work establishes a powerful framewor k for advancing precision medicine through unsupervised random forest-based clus tering in combination with federated computing. We introduce a novel multi-omics clustering approach utilizing unsupervised random forests. The unsupervised nat ure of the random forest enables the determination of cluster-specific feature i mportance, unraveling key molecular contributors to distinct patient groups. Our methodology is designed for federated execution, a crucial aspect in the medica l domain where privacy concerns are paramount. We have validated our approach on machine learning benchmark datasets as well as on cancer data from The Cancer G enome Atlas. Our method is competitive with the state-of-the-art in terms of dis ease subtyping, but at the same time substantially improves the cluster interpre tability. Experiments indicate that local clustering performance can be improved through federated computing.”
NETL
NSTL
