Temporal Phenotyping using Deep Predictive Clustering of Disease Progression

TL;DR

This paper introduces a deep learning method for clustering patient time-series data to identify groups with similar future health outcomes, aiding personalized treatment and prognosis prediction.

Contribution

It presents a novel deep predictive clustering approach that emphasizes homogeneous future outcomes, improving clustering quality for clinical applications.

Findings

Outperforms existing benchmarks in clustering accuracy.

Identifies clinically meaningful patient subgroups.

Enhances decision-making with actionable clusters.

Abstract

Due to the wider availability of modern electronic health records, patient care data is often being stored in the form of time-series. Clustering such time-series data is crucial for patient phenotyping, anticipating patients' prognoses by identifying "similar" patients, and designing treatment guidelines that are tailored to homogeneous patient subgroups. In this paper, we develop a deep learning approach for clustering time-series data, where each cluster comprises patients who share similar future outcomes of interest (e.g., adverse events, the onset of comorbidities). To encourage each cluster to have homogeneous future outcomes, the clustering is carried out by learning discrete representations that best describe the future outcome distribution based on novel loss functions. Experiments on two real-world datasets show that our model achieves superior clustering performance over state-of-the-art benchmarks and identifies meaningful clusters that can be translated into actionable information for clinical decision-making.