What type of study is this?

This is a Validation Study study.

What question did this study set out to answer?

This research aims to develop a unified framework for survival prediction by integrating machine learning and traditional survival analysis.

March 8, 2026DiagnosticsOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Unified framework combines feature selection with survival analysis, improving risk stratification in heart failure and METABRIC breast cancer.

This research aims to develop a unified framework for survival prediction by integrating machine learning and traditional survival analysis.
Identified prognostic clinical features using ML models like GBM-Cox, RSF, and LASSO-Cox with 5-fold stratified cross-validation.
Validated results with Cox Proportional Hazards and Kaplan–Meier analysis.
Evaluated the framework's robustness across heart failure and METABRIC breast cancer datasets.
In heart failure, age group and blood pressure stratified risk groups; high-risk patients had higher mortality (HR: 2.61).
In METABRIC, Nottingham Prognostic Index showed significant survival separation (p < 0.001); high-risk had an HR of 2.73 and shorter median survival (104.7 vs. 252.3 months).
C-index values ranged from 0.665 to 0.794, indicating stable performance across cohorts.

Tan et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Unified framework combines feature selection with survival analysis, improving risk stratification in heart failure and METABRIC breast cancer.