ICML 2021spotlight16 citations

Neural Pharmacodynamic State Space Modeling

Zeshan M Hussain, Rahul G. Krishnan, David Sontag

Abstract

Modeling the time-series of high-dimensional, longitudinal data is important for predicting patient disease progression. However, existing neural network based approaches that learn representations of patient state, while very flexible, are susceptible to overfitting. We propose a deep generative model that makes use of a novel attention-based neural architecture inspired by the physics of how treatments affect disease state. The result is a scalable and accurate model of high-dimensional patient biomarkers as they vary over time. Our proposed model yields significant improvements in generalization and, on real-world clinical data, provides interpretable insights into the dynamics of cancer progression.

BibTeX
@InProceedings{pmlr-v139-hussain21a,
  title = 	 {Neural Pharmacodynamic State Space Modeling},
  author =       {Hussain, Zeshan M and Krishnan, Rahul G. and Sontag, David},
  booktitle = 	 {Proceedings of the 38th International Conference on Machine Learning},
  pages = 	 {4500--4510},
  year = 	 {2021},
  editor = 	 {Meila, Marina and Zhang, Tong},
  volume = 	 {139},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {18--24 Jul},
  publisher =    {PMLR},
  pdf = 	 {http://proceedings.mlr.press/v139/hussain21a/hussain21a.pdf},
  url = 	 {https://proceedings.mlr.press/v139/hussain21a.html},
  abstract = 	 {Modeling the time-series of high-dimensional, longitudinal data is important for predicting patient disease progression. However, existing neural network based approaches that learn representations of patient state, while very flexible, are susceptible to overfitting. We propose a deep generative model that makes use of a novel attention-based neural architecture inspired by the physics of how treatments affect disease state. The result is a scalable and accurate model of high-dimensional patient biomarkers as they vary over time. Our proposed model yields significant improvements in generalization and, on real-world clinical data, provides interpretable insights into the dynamics of cancer progression.}
}