Machine Learning Approach Based on Echocardiographic Data to Improve Prediction of Cardiovascular Events in Hypertrophic Cardiomyopathy (2022PI172)

Pr. Nicolas GIRERD

Status: Enrolling

Conditions: Hypertrophic Cardiomyopathy

Study type: Observational

Funder types: Other

Identifiers

NCT06256913

2022PI172

Details and patient eligibility

About

Hypertrophic cardiomyopathy is a pathology with a highly variable course, ranging from patients who are asymptomatic throughout their lives to those who experience sudden death and/or terminal heart failure.

The main objective is to develop and validate an algorithm (constructed through supervised learning) using cardiac imaging data to predict the risk of cardiovascular events in sarcomeric hypertrophic cardiomyopathy.

Enrollment: 870 estimated patients

Sex: All

Ages: 18+ years old

Volunteers: No Healthy Volunteers

Inclusion criteria

• Age >18
• Patients with confirmed sarcomeric hypertrophic cardiomyopathy

Exclusion criteria

• Echocardiographic data not allowing deep analysis (technical default, bad echogenicity of the patient)
• Other causes of left ventricular hypertrophy that may hamper the diagnosis (p.e. aortic or sub-aortic stenosis, severe renal insufficiency, hypertension).
• History of ischemic heart disease or associated myocarditis
• Opposition of the patient to the use of his/her data

Trial design

870 participants in 2 patient groups

Patients with sarcomeric hypertrophic cardiomyopathy and cardiovascular events

Description:

Patients with confirmed sarcomeric hypertrophic cardiomyopathy who experienced cardiovascular events.

Patients with sarcomeric hypertrophic cardiomyopathy free of cardiovascular events

Description:

Patients with confirmed sarcomeric hypertrophic cardiomyopathy free of cardiovascular events.