Random Survival Forest for Censored Functional Data

TL;DR

This paper proposes a novel Random Survival Forest method tailored for censored functional data, enabling better modeling and prediction of survival trajectories in medical studies with incomplete data.

Contribution

It introduces the Censored Functional Data structure and adapts RSF to handle this data type, improving survival analysis accuracy.

Findings

Effective in ranking variable importance

Improved modeling of survival trajectories

Good performance on SOFA dataset

Abstract

This paper introduces a Random Survival Forest (RSF) method for functional data. The focus is specifically on defining a new functional data structure, the Censored Functional Data (CFD), for dealing with temporal observations that are censored due to study limitations or incomplete data collection. This approach allows for precise modelling of functional survival trajectories, leading to improved interpretation and prediction of survival dynamics across different groups. A medical survival study on the benchmark SOFA data set is presented. Results show good performance of the proposed approach, particularly in ranking the importance of predicting variables, as captured through dynamic changes in SOFA scores and patient mortality rates.