{"slug": "federatedrsf-federated-random-survival-forests-for-partially-overlapping-medical", "title": "FederatedRSF : Federated Random Survival Forests for Partially Overlapping Medical Data", "summary": "Researchers have developed FederatedRSF, a Python package enabling multi-center survival prediction using federated random survival forests without sharing patient-level data. The method aggregates locally trained survival trees and redistributes only feature-compatible trees to each site, addressing privacy regulations and feature-space heterogeneity where institutions collect different covariates. Evaluated on the GBSG2 breast cancer cohort, the federated model achieved performance comparable to centralized training, offering a solution for robust survival analysis across institutions with partially overlapping medical data.", "body_md": "arXiv:2605.22954v1 Announce Type: new\nAbstract: Multi-center survival prediction can improve robustness and generalizability, yet privacy regulations and institutional governance often prevent pooling patient-level clinical and genomic data across institutions. In practice, deployment is further complicated by feature-space heterogeneity, in which sites collect different covariates or use different sequencing panels, resulting in only partially overlapping feature sets. We present FederatedRSF, a Python package that implements federated random survival forests, aggregating locally trained survival trees and redistributing only feature-compatible trees to each site, enabling inference with partial overlap without sharing raw data. We evaluate FederatedRSF on the GBSG2 breast cancer cohort distributed with the scikit-survival package, simulating feature heterogeneity across clients by withholding subsets of features, and assessing discrimination using Harrell's concordance index (C-Index) under repeated cross-validation and site-splits. The results demonstrated that the federated model can achieve performance comparable to that of the centralized training setting.", "url": "https://wpnews.pro/news/federatedrsf-federated-random-survival-forests-for-partially-overlapping-medical", "canonical_source": "https://arxiv.org/abs/2605.22954", "published_at": "2026-05-25 04:00:00+00:00", "updated_at": "2026-05-25 15:14:16.349157+00:00", "lang": "en", "topics": ["machine-learning", "ai-research", "ai-tools"], "entities": ["FederatedRSF", "GBSG2", "scikit-survival", "Harrell"], "alternates": {"html": "https://wpnews.pro/news/federatedrsf-federated-random-survival-forests-for-partially-overlapping-medical", "markdown": "https://wpnews.pro/news/federatedrsf-federated-random-survival-forests-for-partially-overlapping-medical.md", "text": "https://wpnews.pro/news/federatedrsf-federated-random-survival-forests-for-partially-overlapping-medical.txt", "jsonld": "https://wpnews.pro/news/federatedrsf-federated-random-survival-forests-for-partially-overlapping-medical.jsonld"}}