The Transthyretin Amyloid Cardiomyopathy Early Detection With Artificial Intelligence (TRACE-AI) Network Study
Overview
- Phase
- Not Applicable
- Status
- Active, not recruiting
- Sponsor
- Yale University
- Enrollment
- 1,500,000
- Locations
- 11
- Primary Endpoint
- To describe the prevalence of probable AI-defined ATTR-CM in defined cohorts of individuals who have undergone standard cardiovascular investigations across a diverse network of US-based health care delivery systems
Overview
Brief Summary
This is a multi-center, observational study with the overall objective to examine the scale of under-diagnosis for transthyretin amyloid cardiomyopathy (ATTR-CM) across a broad range of diverse health systems in the US using a fully federated deployment of an artificial intelligence (AI) toolkit of algorithms that detect ATTR-CM on electrocardiography (ECG), point-of-care ultrasound (POCUS), and transthoracic echocardiography (TTE).
Study Design
- Study Type
- Observational
- Observational Model
- Cohort
- Time Perspective
- Prospective
Eligibility Criteria
- Ages
- 50 Years to 95 Years (Adult, Older Adult)
- Sex
- All
- Accepts Healthy Volunteers
- No
Inclusion Criteria
- •Age 50-95
- •At least one retrievable ECG and/or 2D echo file (DICOM or equivalent video file) from EHR.
Exclusion Criteria
- •Unavailable key demographics (age, gender, race, ethnicity)
- •Individuals who have opted out of research studies
- •Objective-specific inclusion and exclusion criteria:
- •Primary Objective:
- •Additional exclusion criteria:
- •For subgroup analyses: when evaluating the prevalence of probable ATTR-CM status across demographic groups, we will exclude those with missing baseline demographic information (age, sex, race, geographic region).
- •Secondary Objective 1:
- •Additional inclusion criteria:
- •'Cases': ATTR-CM diagnosis defined by ICD-10 codes (Table 1) OR abnormal bone scintigraphy testing consistent with ATTR-CM OR treatment with an approved transthyretin stabilizer or other ATTR-CM-specific therapy
- •'Controls': any individuals not meeting the case definition. In these participants, we will consider all eligible ECG, POCUS, or TTE studies performed up to 12 months before diagnosis (first date of ICD code appearance, abnormal bone scintigraphy or treatment onset, whichever happened first) and any time after. 'Controls' will be drawn from ECGs, POCUS, or TTE studies performed in individuals not meeting the 'case' criteria above, including individuals who have never undergone dedicating testing or those who underwent e.g., bone scintigraphy, but with negative (or equivocal) findings.
Outcomes
Primary Outcomes
To describe the prevalence of probable AI-defined ATTR-CM in defined cohorts of individuals who have undergone standard cardiovascular investigations across a diverse network of US-based health care delivery systems
Time Frame: At enrollment
Secondary Outcomes
- Validate the diagnostic performance of AI-enabled ECG, POCUS, and TTE algorithms for ATTR-CM(At enrollment)
- To examine the association between the AI-defined probability of ATTR-CM and the incidence of adverse cardiovascular events(At enrollment)