Open AccessDecentralized Learning Framework of Meta-Survival Analysis for Developing Robust Prognostic Signatures
Author(s) -
Yi Cui,
Bailiang Li,
Ruijiang Li
Publication year - 2017
Publication title -
jco clinical cancer informatics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.188
H-Index - 12
ISSN - 2473-4276
DOI - 10.1200/cci.17.00077
Subject(s) - overfitting , computer science , sample size determination , spurious relationship , data mining , machine learning , meta analysis , artificial intelligence , statistics , medicine , mathematics , artificial neural network
A significant hurdle in developing reliable gene expression-based prognostic models has been the limited sample size, which can cause overfitting and false discovery. Combining data from multiple studies can enhance statistical power and reduce spurious findings, but how to address the biologic heterogeneity across different datasets remains a major challenge. Better meta-survival analysis approaches are needed.