Neural Pharmacodynamic State Space Modeling

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.

Publication
Proceedings of the Thirty-Eighth International Conference on Machine Learning (ICML)
Zeshan Hussain
Zeshan Hussain
MD/PhD Student

Zeshan’s research interests include modelling time-series data, particularly clinical data, deep generative models, as well as chronic disease progression modelling.

David Sontag
David Sontag
Associate Professor of EECS

My research focuses on advancing machine learning and artificial intelligence, and using these to transform health care.

Related