Heart Rate Topic Models

Authors

  • Alexander Van Esbroeck University of Michigan
  • Chih-Chun Chia University of Michigan
  • Zeeshan Syed University of Michigan

DOI:

https://doi.org/10.1609/aaai.v26i1.8337

Abstract

A key challenge in reducing the burden of cardiovascular disease is matching patients to treatments that are most appropriate for them. Different cardiac assessment tools have been developed to address this goal. Recent research has focused on heart rate motifs, i.e., short-term heart rate sequences that are over- or under-represented in long-term electrocardiogram (ECG) recordings of patients experiencing cardiovascular outcomes, which provide novel and valuable information for risk stratification. However, this approach can leverage only a small number of motifs for prediction and results in difficult to interpret models. We address these limitations by identifying latent structure in the large numbers of motifs found in long-term ECG recordings. In particular, we explore the application of topic models to heart rate time series to identify functional sets of heart rate sequences and to concisely describe patients using task-independent features for various cardiovascular outcomes. We evaluate the approach on a large collection of real-world ECG data, and investigate the performance of topic mixture features for the prediction of cardiovascular mortality. The topics provided an interpretable representation of the recordings and maintained valuable information for clinical assessment when compared with motif frequencies, even after accounting for commonly used clinical risk scores.

Downloads

Published

2021-09-20

How to Cite

Van Esbroeck, A., Chia, C.-C., & Syed, Z. (2021). Heart Rate Topic Models. Proceedings of the AAAI Conference on Artificial Intelligence, 26(1), 1635-1641. https://doi.org/10.1609/aaai.v26i1.8337