Generative Time Series Models with Interpretable Latent Processes for Complex Disease Trajectories

Cécile Trottet, Manuel Schürch, Amina Mollaysa, Ahmed Allam, Michael Krauthammer

Keywords: Time series, Semi-Supervised learning, Latent processes, Interpretability, Disease Trajectories

TL;DR: A semi-supervised approach combining deep generative models with established medical concepts to analyze complex disease trajectories.

Abstract:

We propose a deep generative time series approach using latent temporal processes for modeling and holistically analyzing complex
disease trajectories and demonstrate its effectiveness in modeling systemic sclerosis.
We aim to find meaningful temporal latent representations of an underlying generative process that
explain the observed disease trajectories in an interpretable and comprehensive way.
To enhance the interpretability of these latent temporal processes,
we develop a semi-supervised approach for disentangling the latent space using established medical concepts.
We show that the learned temporal latent processes can be utilized for further data analysis,
including finding similar patients and clustering the disease into new sub-types.
Moreover, our method enables personalized online monitoring and prediction of multivariate time series including uncertainty quantification.

Submission Number: 5