Clustering Interval-Censored Time-Series for Disease Phenotyping

TL;DR

This paper introduces a deep generative model for clustering time-series data in disease phenotyping, effectively correcting for interval censoring noise to improve accuracy and interpretability.

Contribution

It presents a novel continuous-time clustering model that accounts for interval censoring, enhancing disease subtype discovery from real-world clinical time-series data.

Findings

Outperforms benchmarks on synthetic data in accuracy and stability.

Recovers known clinical subtypes in heart failure and Parkinson's datasets.

Demonstrates the adverse effects of interval censoring on disease phenotyping.

Abstract

Unsupervised learning is often used to uncover clusters in data. However, different kinds of noise may impede the discovery of useful patterns from real-world time-series data. In this work, we focus on mitigating the interference of interval censoring in the task of clustering for disease phenotyping. We develop a deep generative, continuous-time model of time-series data that clusters time-series while correcting for censorship time. We provide conditions under which clusters and the amount of delayed entry may be identified from data under a noiseless model. On synthetic data, we demonstrate accurate, stable, and interpretable results that outperform several benchmarks. On real-world clinical datasets of heart failure and Parkinson's disease patients, we study how interval censoring can adversely affect the task of disease phenotyping. Our model corrects for this source of error and recovers known clinical subtypes.