Artificial Intelligence Guided Echocardiographic Screening of Rare Diseases (EchoNet-Screening)

NCT ID: NCT05139797

Last Updated: 2025-06-27

Basic Information

• Recruitment Status: RECRUITING
• Total Enrollment: 300 participants
• Study Classification: OBSERVATIONAL
• Study Start Date: 2021-11-18
• Study Completion Date: 2027-06-01

Brief Summary

Despite rapidly advancing developments in targeted therapeutics and genetic sequencing, persistent limits in the accuracy and throughput of clinical phenotyping has led to a widening gap between the potential and the actual benefits realized by precision medicine.

Recent advances in machine learning and image processing techniques have shown that machine learning models can identify features unrecognized by human experts and more precisely/accurately assess common measurements made in clinical practice.

The investigators have developed an algorithm, termed EchoNet-LVH, to identify cardiac hypertrophy and identify patients who would benefit from additional screening for cardiac amyloidosis and will prospectively evaluate its accuracy in identifying patients whom would benefit from additional screening for cardiac amyloidosis.

Detailed Description

Despite rapidly advancing developments in targeted therapeutics and genetic sequencing, persistent limits in the accuracy and throughput of clinical phenotyping has led to a widening gap between the potential and the actual benefits realized by precision medicine. This conundrum is exemplified by current approaches to assessing morphologic alterations of the heart. If reliably identified, certain cardiac diseases (e.g. cardiac amyloidosis and hypertrophic cardiomyopathy) could avoid misdiagnosis and receive efficient treatment initiation with specific targeted therapies. The ability to reliably distinguish between cardiac disease types of similar morphology but different etiology would also enhance specificity for linking genetic risk variants and determining mechanisms

Recent advances in machine learning and image processing techniques have shown that machine learning models can identify features unrecognized by human experts and more precisely/accurately assess common measurements made in clinical practice. In echocardiography, this ability for precision measurement and detection is important in both disease screening as well as diagnosis of cardiovascular disease.

Echocardiography is routinely and frequently used for diagnosis and prognostication in routine clinical care, however there is often subjectivity in interpretation and heterogeneity in application. Human attention is fatigable and has heterogenous interpretation between providers. AI guided disease screening workflows have been proposed for rare diseases such as cardiac amyloidosis and other diseases with relatively low prevalence but significant human impact with targeted therapies when detected early. This is an area particularly suitable for AI as there are multiple mimics where diseases like hypertrophic cardiomyopathy, cardiac amyloidosis, aortic stenosis, and other phenotypes might visually be similar but can be distinguished by AI algorithms. The investigators have developed an algorithm, termed EchoNet-LVH, to identify cardiac hypertrophy and identify patients who would benefit from additional screening for cardiac amyloidosis, hypertrophic cardiomyopathy and other diseases. E

Conditions

Cardiac Amyloidosis

Study Design

• Observational Model Type: COHORT
• Study Time Perspective: PROSPECTIVE

Study Groups

Artificial Intelligence Screening for Cardiac Amyloidosis

An artificial intelligence algorithm will produce a probability of cardiac amyloidosis that will trigger referral to specialty clinic for further evaluation.

EchoNet-LVH screening for cardiac amyloidosis

Intervention Type: OTHER

An AI algorithm identifies LVH, low voltage, and high suspicion for cardiac amyloidosis. The intervention is the suspicion score. Patients with high suspicion score will be referred to specialty clinic for standard of care evaluation, screening, and treatment as determined by physicians.

Interventions

EchoNet-LVH screening for cardiac amyloidosis

An AI algorithm identifies LVH, low voltage, and high suspicion for cardiac amyloidosis. The intervention is the suspicion score. Patients with high suspicion score will be referred to specialty clinic for standard of care evaluation, screening, and treatment as determined by physicians.

Intervention Type: OTHER

Eligibility Criteria

Inclusion Criteria

• Patients who have a high suspicion for cardiac amyloidosis by AI algorithm

Exclusion Criteria

• Patients who decline to be seen at specialty clinic
• Patients who have passed away

• Minimum Eligible Age: 18 Years
• Eligible Sex: ALL
• Accepts Healthy Volunteers: No

Sponsors

Cedars-Sinai Medical Center

OTHER

Sponsor Role: lead

Responsible Party

Lily Stern

Staff Physician

Responsibility Role: PRINCIPAL_INVESTIGATOR

Locations

Cedars-Sinai Medical Centre (Los Angeles)

Los Angeles, California, United States

Site Status: RECRUITING

Countries

United States

Facility Contacts

Lily Stern, MD

Role: primary

lily.stern@cshs.org

310-248-8300

Related Links

https://arxiv.org/abs/2106.12511

Related Info

Other Identifiers

STUDY00001720

Identifier Type: -

Identifier Source: org_study_id