Data-Driven Discovery of Feature Groups in Clinical Time Series

TL;DR

This paper introduces a novel method for automatically discovering clinically interpretable feature groups in multivariate time series data, improving predictive performance without relying solely on expert knowledge.

Contribution

The proposed approach learns feature groups by clustering weights of embedding layers, seamlessly integrating into supervised training and outperforming static clustering methods.

Findings

Outperforms static clustering on synthetic data

Achieves comparable results to expert-defined groups on real data

Learns clinically interpretable feature groups

Abstract

Clinical time series data are critical for patient monitoring and predictive modeling. These time series are typically multivariate and often comprise hundreds of heterogeneous features from different data sources. The grouping of features based on similarity and relevance to the prediction task has been shown to enhance the performance of deep learning architectures. However, defining these groups a priori using only semantic knowledge is challenging, even for domain experts. To address this, we propose a novel method that learns feature groups by clustering weights of feature-wise embedding layers. This approach seamlessly integrates into standard supervised training and discovers the groups that directly improve downstream performance on clinically relevant tasks. We demonstrate that our method outperforms static clustering approaches on synthetic data and achieves performance comparable to expert-defined groups on real-world medical data. Moreover, the learned feature groups are clinically interpretable, enabling data-driven discovery of task-relevant relationships between variables.