AI Echocardiographic Screening for Cardiac Amyloidosis

Recruiting at 3 trial locations

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Cedars-Sinai Medical Center

Disqualifiers: Decline consent, Not suspicious echocardiogram

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

500 Participants Needed

Trial Summary

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What data supports the effectiveness of the treatment EchoNet-LVH for cardiac amyloidosis?

The research suggests that using artificial intelligence (AI) to automatically calculate heart function measurements, like left ventricular ejection fraction (LVEF) and global longitudinal strain (GLS), can effectively identify abnormalities in cardiac amyloidosis, similar to traditional manual methods. Additionally, machine learning models have shown strong performance in distinguishing cardiac amyloidosis from similar heart conditions, which could lead to timely and effective interventions. ^{1 2 3 4 5}

Is AI echocardiographic screening for cardiac amyloidosis safe for humans?

The research articles provided do not contain specific safety data for AI echocardiographic screening for cardiac amyloidosis or related technologies like EchoNet-LVH. They focus on the effectiveness and diagnostic capabilities of AI in detecting cardiac conditions. ^{1 2 4 6 7}

How does the treatment EchoNet-LVH differ from other treatments for cardiac amyloidosis?

EchoNet-LVH is unique because it uses artificial intelligence (AI) to automatically analyze echocardiograms, which helps in the early detection and diagnosis of cardiac amyloidosis. This approach is faster and reduces variability compared to traditional manual methods, potentially leading to earlier and more accurate diagnosis. ^{1 4 5 7 8}

What is the purpose of this trial?

Recent advances in machine learning and image processing techniques have shown that machine learning models can identify features unrecognized by human experts and accurately assess common measurements made in clinical practice. Echocardiography is the most common form of cardiac imaging and is routinely and frequently used for diagnosis. However, there is often subjectivity and heterogeneity in interpretation. Artificial intelligence (AI)'s ability for precision measurement and detection is important in both disease screening as well as diagnosis of cardiovascular disease. Cardiac amyloidosis (CA) is a rare, underdiagnosed disease with targeted therapies that reduce morbidity and increase life expectancy. However, CA is frequently overlooked and confused with heart failure with preserved ejection fraction. Some estimates suggest that CA can be as prevalence as 1% in a general population, with even higher prevalence in patients with left ventricular hypertrophy, heart failure, and other cardiac symptoms that might prompt echocardiography. 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.

Research Team

David Ouyang, MD

Principal Investigator

Cedars-Sinai Medical Center

Eligibility Criteria

This trial is for individuals who may have cardiac amyloidosis, a rare heart condition often mistaken for other types of heart failure. It's especially aimed at those with symptoms or conditions that could be related to this disease and would typically undergo echocardiography.

Inclusion Criteria

Patients receiving an echocardiogram that is determined to be suspicious by EchoNet-LVH

Exclusion Criteria

I have chosen not to give my consent for participation.

Patients receiving an echocardiogram that is determined to be not suspicious by EchoNet-LVH

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

AI-Enhanced Echocardiogram Review

Potential participants are identified by automated AI-enhanced echocardiogram review and chart reviewed by CA experts for enrollment appropriateness

4-6 weeks

Follow-up

Participants are monitored for confirmation of cardiac amyloidosis and other outcomes

1 year

Treatment Details

Interventions

• EchoNet-LVH

Trial Overview The trial is testing an AI algorithm called EchoNet-LVH designed to improve the detection of cardiac amyloidosis using routine echocardiogram images. The goal is to see if this technology can more accurately identify patients who need further screening.

Participant Groups

Group I: Suspicious by EchoNet-LVH Algorithm Experimental Treatment 1 Intervention

Each potential participant identified by automated AI-enhanced echocardiogram review will be chart reviewed by each site's CA experts for appropriateness of enrollment and clinican suspicion for CA. Based on the judgement of CA experts, potential participants that meet eligibility criteria will be called to be consented, followed in the study, and referred to see the CA expert.

Who Is Running the Clinical Trial?

Cedars-Sinai Medical Center

Lead Sponsor

Trials

523

Recruited

165,000+

Palo Alto Veteran Affairs Hospital

Collaborator

Trials

1

Recruited

500+

Providence Heart & Vascular Institute

Collaborator

Trials

2

Recruited

620+

Northwestern Medicine

Collaborator

Trials

14

Recruited

9,500+

Findings from Research

A study involving 138 patients (74 with cardiac amyloidosis and 64 with hypertrophic cardiomyopathy) demonstrated that machine learning models, particularly random forest and gradient boosting, can effectively differentiate between these two conditions with high accuracy (AUC up to 0.98).

The use of machine learning combined with speckle tracking echocardiography shows promise in improving the timely diagnosis of cardiac amyloidosis, which is often misdiagnosed, potentially leading to better patient outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Machine learning algorithms to automate differentiating cardiac amyloidosis from hypertrophic cardiomyopathy. Wu, ZW., Zheng, JL., Kuang, L., et al.[2023]

References

1. United States pubmed.ncbi.nlm.nih.gov

Artificial intelligence based left ventricular ejection fraction and global longitudinal strain in cardiac amyloidosis. [2023]

2. England pubmed.ncbi.nlm.nih.gov

Cardiac amyloidosis screening using a relative apical sparing pattern in patients with left ventricular hypertrophy. [2021]

3. England pubmed.ncbi.nlm.nih.gov

Phasic left atrial strain analysis to discriminate cardiac amyloidosis in patients with unclear thick heart pathology. [2021]

4. United States pubmed.ncbi.nlm.nih.gov

Machine learning algorithms to automate differentiating cardiac amyloidosis from hypertrophic cardiomyopathy. [2023]

5. United States pubmed.ncbi.nlm.nih.gov

Echocardiographic evaluation of cardiac amyloid. [2021]

6. England pubmed.ncbi.nlm.nih.gov

Evaluation of patients with cardiac amyloidosis using echocardiography, ECG and right heart catheterization. [2016]

7. England pubmed.ncbi.nlm.nih.gov

Artificial intelligence-enabled fully automated detection of cardiac amyloidosis using electrocardiograms and echocardiograms. [2021]

8. Switzerland pubmed.ncbi.nlm.nih.gov

Convolutional Neural Networks for Fully Automated Diagnosis of Cardiac Amyloidosis by Cardiac Magnetic Resonance Imaging. [2021]