Machine Learning for Survival Data

The project aims at studying machine learning algorithms for survival analysis, with main focus on survival trees and survival random forests. The topic presents still some unclear points, mainly dealing with performance assessment. Moreover, there is still not an harmonization of all the proposed methods. An analysis from both a theoretical and practical point of view is carried out with the aim of sheding light on the topic.

Scientific coordinators: Ambra Macis, Marica Manisera, Marco Sandri, Paola Zuccolotto.

Seminal papers

Survival trees: a pathway among features and open issues of the main R packages

Macis A., Survival trees: a pathway among features and open issues of the main R packages, EJASA (forthcoming).

Supplementary File 1 – Tutorial in R 

Supplementary File 2 – Structure of  Trees

Supplementary File 3 – Script 

Survival analysis aims to study the occurrence of a particular event during a follow-up period. Recently, many machine learning methods have been used for analyzing right-censored data. Among these, survival trees are a useful tool of recursive partitioning for defining homogeneous groups in terms of survival probability. However, there are still some unclear points on how to work with these methods from a practical point of view. Indeed, even if there are a lot of proposed methods, many of these present little documentation, mainly concerning the corresponding R functions. Moreover, there does not exist an harmonization of all these proposals. This work aims to shed light on the topic and to provide a practical guide for simulating survival data, fitting survival trees and evaluating their performance with the statistical software R.