PT-MESS: A Problem-transformation Approach for Multi-event Survival Analysis

Michela Venturini, Michela Venturini, Felipe Nakano, Felipe Nakano, Celine Vens, Celine Vens

2022

Abstract

Multi-event survival analysis is an under-explored field in literature, typically addressed by modeling each event independently or implying specific event settings. In this context, problem transformations approaches offer a promising alternative to rephrase the setting into standard multi-target regression. Nevertheless, they also suffer from the intrinsic presence of partial information in time-to-event data, since their application often requires the exclusion of censored observations, thus potentially discarding valuable information. In this work, we propose a novel Problem Transformation Approach for Multi-event Survival analySis (PT-MESS), which is capable of exploiting partial information, by encoding the survival outcome in a risk score based on the time-to-event distribution estimation. This approach allows the use of any multi-target machine learning model to address the original survival task. Using random forest as the underlying model, we conducted experiments using real-data multiple benchmarks from the medical domain and synthetic datasets. Our results revealed that PT-MESS provides superior or competitive results compared to competitors from the literature, especially when the events considered had a similar survival distribution.

Paper Citation

in Harvard Style

Venturini M., Nakano F. and Vens C. (2022). PT-MESS: A Problem-transformation Approach for Multi-event Survival Analysis. In Proceedings of the 1st Workshop on Scarce Data in Artificial Intelligence for Healthcare - Volume 1: SDAIH, ISBN 978-989-758-629-3, SciTePress, pages 29-34. DOI: 10.5220/0011531600003523

in Bibtex Style

@conference{sdaih22,
author={Michela Venturini and Felipe Nakano and Celine Vens},
title={PT-MESS: A Problem-transformation Approach for Multi-event Survival Analysis},
booktitle={Proceedings of the 1st Workshop on Scarce Data in Artificial Intelligence for Healthcare - Volume 1: SDAIH,},
year={2022},
pages={29-34},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011531600003523},
isbn={978-989-758-629-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st Workshop on Scarce Data in Artificial Intelligence for Healthcare - Volume 1: SDAIH,
TI - PT-MESS: A Problem-transformation Approach for Multi-event Survival Analysis
SN - 978-989-758-629-3
AU - Venturini M.
AU - Nakano F.
AU - Vens C.
PY - 2022
SP - 29
EP - 34
DO - 10.5220/0011531600003523
PB - SciTePress