Neural Pharmacodynamic State Space Modeling

Zeshan Hussain · Rahul G. Krishnan · David Sontag

[ Abstract ] [ Livestream: Visit Optimization 4 ] [ Paper ]
Tue 20 Jul 7:40 p.m. — 7:45 p.m. PDT
[ Paper ]

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.

Chat is not available.