The Journal of heart and lung transplantation : the official publication of the International Society for Heart Transplantation · 2021
Machine-learning-based exploration to identify remodeling patterns associated with death or heart-transplant in pediatric-dilated cardiomyopathy.
СтатьяПоддержка исследования: вне правительства СШАНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Garcia-Canadilla Patricia, Sanchez-Martinez Sergio, Martí-Castellote Pablo M, Slorach Cameron, Hui Wei, Piella Gemma, Aguado Ainhoa M, Nogueira Mariana, Mertens Luc, Bijnens Bart H, Friedberg Mark K
Аннотация
AIMS: We investigated left ventricular (LV) remodeling, mechanics, systolic and diastolic function, combined with clinical characteristics and heart-failure treatment in association to death or heart-transplant (DoT) in pediatric idiopathic, genetic or familial dilated cardiomyopathy (DCM), using interpretable machine-learning.
METHODS AND RESULTS: Echocardiographic and clinical data from pediatric DCM and healthy controls were retrospectively analyzed. Machine-learning included whole cardiac-cycle regional longitudinal strain, aortic, mitral and pulmonary vein Doppler velocity traces, age and body surface area. We used unsupervised multiple kernel learning for data dimensionality reduction, positioning patients based on complex conglomerate information similarity. Subsequently, k-means identified groups with similar phenotypes. The proportion experiencing DoT was evaluated. Pheno-grouping identified 5 clinically distinct groups that were associated with differing proportions of DoT. All healthy controls clustered in groups 1 to 2, while all, but one, DCM subjects, clustered in groups 3 to 5; internally validating the algorithm. Cluster-5 comprised the oldest, most medicated patients, with combined systolic and diastolic heart-failure and highest proportion of DoT. Cluster-4 included the youngest patients characterized by severe LV remodeling and systolic dysfunction, but mild diastolic dysfunction and the second-highest proportion of DoT. Cluster-3 comprised young patients with moderate remodeling and systolic dysfunction, preserved apical strain, pronounced diastolic dysfunction and lowest proportion of DoT.
CONCLUSIONS: Interpretable machine-learning, using full cardiac-cycle systolic and diastolic data, mechanics and clinical parameters, can potentially identify pediatric DCM patients at high-risk for DoT, and delineate mechanisms associated with risk. This may facilitate more precise prognostication and treatment of pediatric DCM.
METHODS AND RESULTS: Echocardiographic and clinical data from pediatric DCM and healthy controls were retrospectively analyzed. Machine-learning included whole cardiac-cycle regional longitudinal strain, aortic, mitral and pulmonary vein Doppler velocity traces, age and body surface area. We used unsupervised multiple kernel learning for data dimensionality reduction, positioning patients based on complex conglomerate information similarity. Subsequently, k-means identified groups with similar phenotypes. The proportion experiencing DoT was evaluated. Pheno-grouping identified 5 clinically distinct groups that were associated with differing proportions of DoT. All healthy controls clustered in groups 1 to 2, while all, but one, DCM subjects, clustered in groups 3 to 5; internally validating the algorithm. Cluster-5 comprised the oldest, most medicated patients, with combined systolic and diastolic heart-failure and highest proportion of DoT. Cluster-4 included the youngest patients characterized by severe LV remodeling and systolic dysfunction, but mild diastolic dysfunction and the second-highest proportion of DoT. Cluster-3 comprised young patients with moderate remodeling and systolic dysfunction, preserved apical strain, pronounced diastolic dysfunction and lowest proportion of DoT.
CONCLUSIONS: Interpretable machine-learning, using full cardiac-cycle systolic and diastolic data, mechanics and clinical parameters, can potentially identify pediatric DCM patients at high-risk for DoT, and delineate mechanisms associated with risk. This may facilitate more precise prognostication and treatment of pediatric DCM.