Machine-learning-based exploration to identify remodeling patterns associated with death or heart-transplant in
Patricia Garcia-Canadilla1, Sergio Sanchez-Martinez1, Pablo M Martí-Castellote2
1Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS) Barcelona, Spain.
Insights
Interpretable machine learning identified distinct patient groups in pediatric dilated cardiomyopathy (DCM). Certain phenotypes, particularly those with severe heart failure, showed a higher risk of death or heart transplant (DoT).
Area of Science:
- Cardiology
- Pediatric Cardiology
- Machine Learning in Medicine
Background:
- Pediatric dilated cardiomyopathy (DCM) is a complex condition affecting heart function.
- Risk stratification for adverse outcomes like death or heart transplant (DoT) in pediatric DCM is crucial for timely intervention.
Purpose of the Study:
- To investigate left ventricular (LV) remodeling, mechanics, and function in pediatric DCM using interpretable machine learning.
- To associate clinical characteristics and heart failure treatment with the risk of DoT in pediatric DCM patients.
Main Methods:
- Retrospective analysis of echocardiographic and clinical data from pediatric DCM patients and healthy controls.
- Application of unsupervised multiple kernel learning and k-means clustering for patient phenotyping based on cardiac function and clinical data.
- Evaluation of the proportion of patients experiencing DoT within identified phenotypic groups.
Main Results:
- Five distinct patient groups were identified, with healthy controls clustering separately from DCM patients.
- Cluster-5, comprising older, highly medicated patients with combined systolic and diastolic heart failure, had the highest DoT proportion.
- Cluster-4 showed severe LV remodeling and systolic dysfunction with a high DoT risk, while Cluster-3 had moderate dysfunction and the lowest DoT risk.
Conclusions:
- Interpretable machine learning can identify pediatric DCM patients at high risk for DoT.
- This approach aids in delineating mechanisms associated with DoT risk, potentially improving prognostication and treatment strategies.
- Full cardiac-cycle data, mechanics, and clinical parameters are valuable for risk stratification in pediatric DCM.
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.
Related Concept Videos
01:30Cardiomyopathy II: Dilated Cardiomyopathy
01:29Cardiomyopathy V: Interprofessional Care
01:29Cardiomyopathy III: Hypertrophic Cardiomyopathy
01:23Mitral Stenosis II: Clinical features and Diagnostic Tests