Disease-Atlas: Navigating Disease Trajectories Using Deep Learning
Abstract
Joint models for longitudinal and time-to-event data are commonly used in longitudinal studies to forecast disease trajectories over time. While there are many advantages to joint modeling, the standard forms suffer from limitations that arise from a fixed model specification and computational difficulties when applied to high-dimensional datasets. In this paper, we propose a deep learning approach to address these limitations, enhancing existing methods with the inherent flexibility and scalability of deep neural networks while retaining the benefits of joint modeling. Using longitudinal data from the UK Cystic Fibrosis Trust, we demonstrate improvements in performance and scalability, as well as robustness in the presence of irregularly sampled data.
Cite
Text
Lim and van der Schaar. "Disease-Atlas: Navigating Disease Trajectories Using Deep Learning." Proceedings of the 3rd Machine Learning for Healthcare Conference, 2018.Markdown
[Lim and van der Schaar. "Disease-Atlas: Navigating Disease Trajectories Using Deep Learning." Proceedings of the 3rd Machine Learning for Healthcare Conference, 2018.](https://mlanthology.org/mlhc/2018/lim2018mlhc-diseaseatlas/)BibTeX
@inproceedings{lim2018mlhc-diseaseatlas,
title = {{Disease-Atlas: Navigating Disease Trajectories Using Deep Learning}},
author = {Lim, Bryan and van der Schaar, Mihaela},
booktitle = {Proceedings of the 3rd Machine Learning for Healthcare Conference},
year = {2018},
pages = {137-160},
volume = {85},
url = {https://mlanthology.org/mlhc/2018/lim2018mlhc-diseaseatlas/}
}