Unsupervised Time Series Clustering of Left Atrial Strain for Cardiovascular Risk Assessment.
Researchers
Journal
Modalities
Models
Abstract
Early identification of individuals at high risk of developing cardiovascular (CV) events is of paramount importance for efficient risk management. Here, we investigated whether employing unsupervised machine learning methods on time series data of left atrial (LA) strain could distinguish clinically meaningful phenogroups associated with the risk of developing adverse events.In 929 community-dwelling individuals (mean age, 51.6 years; 52.9% women), we acquired clinical and echocardiographic data, including LA strain traces, at baseline and collected cardiac events on average 6.3 years later. We employed two unsupervised learning techniques: (i) an ensemble of Deep Convolutional Neural Network Autoencoder (AE) with k-medoids and (ii) Self-Organizing Map to cluster spatiotemporal patterns within LA strain curves. Clinical characteristics and cardiac outcome were used to evaluate the validity of the k clusters using the original cohort, while an external population cohort (n=378) was used to validate the trained models.In both approaches the optimal number of clusters was 5. The first three clusters had differences in sex distribution and heart rate, but had a similar low CV risk profile. On the other hand, cluster 5 had the worst CV profile and a higher prevalence of left ventricular remodeling and diastolic dysfunction compared to other clusters. The respective indexes of cluster 4 were in between those of clusters 1-3 and 5. After adjustment for traditional risk factors, cluster 5 had the highest risk of cardiac events as compared to cluster 1, 2 and 3 (HR: 1.36; 95%CI:1.09‒1.70; P=0.0063). Similar LA strain patterns were obtained when the models were applied to the external validation cohort, and clinical characteristics revealed similar CV risk profiles across all clusters.Unsupervised machine learning algorithms employed in time series LA strain curves identified clinically meaningful clusters of LA deformation and provide incremental prognostic information over traditional risk factors.Copyright © 2023. Published by Elsevier Inc.