Data-driven clustering supports adaptive remodeling of athlete's hearts: An echocardiographic study from the Taipei Summer Universiade.

ABSTRACT

BACKGROUND/PURPOSE: Sport-specific adaptations of athlete's hearts are still under investigation. This study sought to 1) identify athlete groups with similar characteristics by clustering echocardiographic data; 2) externally validate the data-driven clusters with sport classifications of various dynamic or static loads to support the conventional hypothesis-driven approach in delineating the athlete's heart. METHODS: Anthropometric, echocardiographic and electrocardiographic assessments were collected during the 2017 Summer Universiade in Taiwan. Besides standard echocardiography and strain measurements, ventricular-arterial coupling (VAC) was assessed by the ratio of effective arterial elastance (Ea) to left ventricular end-systolic elastance (Ees) as calculated by a modified single-beat algorithm. RESULTS: We grouped 598 elite athletes (348 male, age 23 ± 2.5 years, across 24 disciplines) using Mitchell's classification. The hypothesis-driven analysis showed dynamic training-related adaptations in heart rate and morphology, including ventricular size, mass, and stroke volume. In comparison, the unsupervised approach found two clusters for each sex. Male athletes participating in high dynamic-load exercises had larger chambers, supranormal diastolic functions, depressed Ees, lower Ea and preserved optimal VAC implicating the resting status of a reservoir-rich pump, which affirmed sport-specific adaptation. The female athletes could be clustered with more noticeable functional alterations, such as depressed biventricular strain. However, the imbalanced number between clusters impeded the validation of load-related remodeling. CONCLUSION: Hierarchical clustering could analyze complicated multiparametric interactions among numerous echocardiography-derived phenotypes to discern the adaptive propensity of the athlete's heart. The endorsement or generation of hypotheses by a data-driven approach can be applied to various domains.