March 3, 2026Open Access

Outcome Risk Modeling for Disability-Free Longevity: Comparison of Random Forest and Random Survival Forest Methods

Key Points

Random Forest and Random Survival Forest show comparable discrimination and calibration in modeling outcomes.
Both models provide insights into risk modeling but RSF does not consistently outperform RF in accuracy.
Analysis focuses on understanding when time can improve existing outcomes risk modeling techniques.
Further studies in various clinical trial cohorts are necessary to validate these findings and enhance prediction models.

Abstract

The RF and RSF models exhibited comparable discrimination and calibration. We conclude that RSF may not always lead to more accurate predictions of outcomes compared to RF. Further examination in different clinical trial cohorts is needed to better understand the context in which adding time into outcomes risk modeling adds value.

Bookmark

View Full Paper

Cite This Study

Vanghelof et al. (Tue,) studied this question.

synapsesocial.com/papers/69a76184c6e9836116a2f859 https://doi.org/https://doi.org/10.64898/2026.02.13.26346264

Bookmark

View Full Paper