IDNetwork: A deep Illness-Death Network based on multi-states event history process for versatile disease prognostication

Aziliz Cottin, Nicolas Pécuchet, Marine Zulian, Agathe Guilloux, Sandrine Katsahian
Proceedings of AAAI Spring Symposium on Survival Prediction - Algorithms, Challenges, and Applications 2021, PMLR 146:1-21, 2021.

Abstract

Multi-state models can capture the different patterns of disease evolution. In particular, the illness-death model is used to follow disease progression from a healthy state to an intermediate state and to a death-related final state. We aim to use those models in order to adapt treatment decisions according to the evolution of the disease. In state-of-the-art methods, the risks of transition are modeled via (semi-) Markov processes and transition-specific Cox proportional hazard (P.H.) models. We propose a neural network architecture called IDNetwork (Illness-Death Network) that relaxes the linear Cox P.H. assumption and integrates a large number of patients’ characteristics. Our method significantly improves the predictive performance compared to state-of-the-art methods on a simulated data set, on two clinical trials for patients with colon cancer and on a real-world data set in breast cancer.

Cite this Paper

BibTeX
@InProceedings{pmlr-v146-cottin21a, title = {IDNetwork: A deep Illness-Death Network based on multi-states event history process for versatile disease prognostication}, author = {Cottin, Aziliz and P{\'e}cuchet, Nicolas and Zulian, Marine and Guilloux, Agathe and Katsahian, Sandrine}, booktitle = {Proceedings of AAAI Spring Symposium on Survival Prediction - Algorithms, Challenges, and Applications 2021}, pages = {1--21}, year = {2021}, editor = {Greiner, Russell and Kumar, Neeraj and Gerds, Thomas Alexander and van der Schaar, Mihaela}, volume = {146}, series = {Proceedings of Machine Learning Research}, month = {22--24 Mar}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v146/cottin21a/cottin21a.pdf}, url = {https://proceedings.mlr.press/v146/cottin21a.html}, abstract = {Multi-state models can capture the different patterns of disease evolution. In particular, the illness-death model is used to follow disease progression from a healthy state to an intermediate state and to a death-related final state. We aim to use those models in order to adapt treatment decisions according to the evolution of the disease. In state-of-the-art methods, the risks of transition are modeled via (semi-) Markov processes and transition-specific Cox proportional hazard (P.H.) models. We propose a neural network architecture called IDNetwork (Illness-Death Network) that relaxes the linear Cox P.H. assumption and integrates a large number of patients’ characteristics. Our method significantly improves the predictive performance compared to state-of-the-art methods on a simulated data set, on two clinical trials for patients with colon cancer and on a real-world data set in breast cancer.} }
Endnote
%0 Conference Paper %T IDNetwork: A deep Illness-Death Network based on multi-states event history process for versatile disease prognostication %A Aziliz Cottin %A Nicolas Pécuchet %A Marine Zulian %A Agathe Guilloux %A Sandrine Katsahian %B Proceedings of AAAI Spring Symposium on Survival Prediction - Algorithms, Challenges, and Applications 2021 %C Proceedings of Machine Learning Research %D 2021 %E Russell Greiner %E Neeraj Kumar %E Thomas Alexander Gerds %E Mihaela van der Schaar %F pmlr-v146-cottin21a %I PMLR %P 1--21 %U https://proceedings.mlr.press/v146/cottin21a.html %V 146 %X Multi-state models can capture the different patterns of disease evolution. In particular, the illness-death model is used to follow disease progression from a healthy state to an intermediate state and to a death-related final state. We aim to use those models in order to adapt treatment decisions according to the evolution of the disease. In state-of-the-art methods, the risks of transition are modeled via (semi-) Markov processes and transition-specific Cox proportional hazard (P.H.) models. We propose a neural network architecture called IDNetwork (Illness-Death Network) that relaxes the linear Cox P.H. assumption and integrates a large number of patients’ characteristics. Our method significantly improves the predictive performance compared to state-of-the-art methods on a simulated data set, on two clinical trials for patients with colon cancer and on a real-world data set in breast cancer.
APA
Cottin, A., Pécuchet, N., Zulian, M., Guilloux, A. & Katsahian, S.. (2021). IDNetwork: A deep Illness-Death Network based on multi-states event history process for versatile disease prognostication. Proceedings of AAAI Spring Symposium on Survival Prediction - Algorithms, Challenges, and Applications 2021, in Proceedings of Machine Learning Research 146:1-21 Available from https://proceedings.mlr.press/v146/cottin21a.html.

Related Material