COMMUTE: Communication-efficient transfer learning for multi-site risk prediction

We propose a communication-efficient transfer learning approach (COMMUTE) that effectively incorporates multi-site healthcare data for training a risk prediction model in a target population of interest, accounting for challenges including population heterogeneity and data sharing constraints across...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of biomedical informatics 2023-01, Vol.137, p.104243-104243, Article 104243
Hauptverfasser:	Gu, Tian, Lee, Phil H., Duan, Rui
Format:	Artikel
Sprache:	eng
Schlagworte:	Communication Computer Simulation Electronic Health Records Genomics Machine Learning Multi-site study Risk prediction Synthetic data Transfer learning
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!