Unsupervised Time-Series Clustering of Left Atrial Strain for Cardiovascular Risk Assessment

Abstract

Background: Early identification of individuals at high risk for developing cardiovascular (CV) events is of para-mount importance for efficient risk management. Here, the authors investigated whether using unsupervised machine learning methods on time-series data of left atrial (LA) strain could distinguish clinically meaningful phenogroups associated with the risk for developing adverse events. Methods: In 929 community-dwelling individuals (mean age, 51.6 years; 52.9% women), clinical and echocardio-graphic data were acquired, including LA strain traces, at baseline, and cardiac events were collected on average 6.3 years later. Two unsupervised learning techniques were used: (1) an ensemble of a deep convolutional neural network autoencoder with k-medoids and (2) a 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 us-ing the original cohort, while an external population cohort (n = 378) was used to validate the trained models. Results: In both approaches, the optimal number of clusters was five. 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 with the other clusters. The respective indexes of cluster 4 were between those of clusters 1 to 3 and 5. After adjust-ment for traditional risk factors, cluster 5 had the highest risk for cardiac events compared with clusters 1, 2, and 3 (hazard ratio, 1.36; 95% CI, 1.09-1.70; P = .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. Conclusion: Unsupervised machine learning algorithms used in time-series LA strain curves identified clinically meaningful clusters of LA deformation and provide incremental prognostic information over traditional risk factors. (J Am Soc Echocardiogr 2023;36:778-87.)