Cardiac Amyloidosis
Conditions
Keywords
Cardiac Amyloidosis, Artificial Intelligence, Deep Learning
Brief summary
This is a single center, diagnostic clinical trial in which the investigators aim to prospectively validate a deep learning model that identifies patients with features suggestive of cardiac amyloidosis, including transthyretin cardiac amyloidosis (ATTR-CA). Cardiac Amyloidosis is an age-related infiltrative cardiomyopathy that causes heart failure and death that is frequently unrecognized and underdiagnosed. The investigators have developed a deep learning model that identifies patients with features of ATTR-CA and other types of cardiac amyloidosis using echocardiographic, ECG, and clinical factors. By applying this model to the population served by NewYork-Presbyterian Hospital, the investigators will identify a list of patients at highest predicted risk for having undiagnosed cardiac amyloidosis. The investigators will then invite these patients for further testing to diagnose cardiac amyloidosis. The rate of cardiac amyloidosis diagnosis of patients in this study will be compared to rate of cardiac amyloidosis diagnosis in historic controls from the following two groups: (1) patients referred for clinical cardiac amyloidosis testing at NewYork-Prebysterian Hospital and (2) patients enrolled in the Screening for Cardiac Amyloidosis With Nuclear Imaging in Minority Populations (SCAN-MP) study.
Detailed description
Heart failure is a leading cause of death in the United States and throughout the world. One cause of heart failure is transthyretin cardiac amyloidosis (ATTR-CA), in which misfolded proteins deposit into the heart. This condition is often diagnosed very late when patients have severe symptoms. In this study, the investigators are trying to use a computer algorithm to find patients with cardiac amyloidosis that has not been diagnosed or suspected by their doctors. The investigators will look at patients seen at Columbia University Irving Medical Center and use our algorithm to identify 100 patients with a high probability of having cardiac amyloidosis and bring them in to be tested. * ATTR-CA diagnosis: A diagnosis of ATTR-CA will be made according to consensus guidelines by an amyloidosis expert. These criteria include either (1) imaging criteria with requires that a patient's cardiac amyloid scintigraphy single-photon emission computed tomography (SPECT) scan shows myocardial uptake, increase left ventricular (LV) wall thickness by cardiac imaging that is unexplained by loading conditions, and follow-up monoclonal protein testing shows no evidence of clinical amyloid light-chain (AL) amyloidosis or (2) pathologic criteria with a biopsy showing systemic transthyretin deposition. * Cardiac amyloidosis (AL-CA) diagnosis: A clinical diagnosis of AL-CA will be by an amyloidosis expert according to society guidelines. These includes a diagnosis made in one of the following settings: (1) cardiac biopsy showing AL deposition and (2) extra-cardiac biopsy showing AL deposition with typical cardiac features on imaging such as echocardiography or cardiac magnetic resonance imaging.
Interventions
DEVICECardiac amyloidosis deep learning model
This is a deep learning algorithm which intakes a patient's age, sex, clinical factors known to be related to amyloidosis and their ECG and echocardiogram results and determines their estimated risk for having cardiac amyloidosis.
Sponsors
Pfizer
American Heart Association
Eidos Therapeutics, a BridgeBio company
Pierre Elias
Study design
Allocation
NA
Intervention model
SINGLE_GROUP
Primary purpose
DIAGNOSTIC
Masking
NONE
Eligibility
Sex/Gender
ALL
Age
50 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* High predicted probability of having cardiac amyloidosis as determined by deep learning model. * Age ≥ 50 years. * Electronically stored ECG and echocardiogram within 5 years of study start date. * Ability for the patient or health care proxy to understand and sign the informed consent after the study has been explained.
Exclusion criteria
* Primary amyloidosis (AL) or secondary amyloidosis (AA). * Prior liver or heart transplantation. * Active malignancy or non-amyloid disease with expected survival of less than 1 year. * Previous testing for cardiac amyloidosis such as amyloid nuclear scintigraphy, cardiac, or fat pad biopsy. * Impairment from stroke, injury or other medical disorder that precludes participation in the study. * Disabling dementia or other mental or behavioral disease * Nursing home resident.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Rate of Cardiac Amyloidosis Diagnosis | Up to 1 year after identification (1 day of participant assessment) | The primary outcome is the rate of cardiac amyloidosis diagnosis (inclusive of transthyretin and light chain cardiac amyloidosis) which is performed in response to patient identification using the deep learning model, reported as the number of participants who had a positive diagnosis for ATTR-CM (transthyretin amyloid cardiomyopathy). |
Countries
United States
Participant flow
Participants by arm
| Arm | Count |
|---|---|
| Intervention Arm Patients who are identified by the deep learning model as being at high risk for undiagnosed cardiac amyloidosis who are enrolled in the study.
Cardiac amyloidosis deep learning model: This is a deep learning algorithm which intakes a patient's age, sex, clinical factors known to be related to amyloidosis and their ECG and echocardiogram results and determines their estimated risk for having cardiac amyloidosis. | 50 |
| Total | 50 |
Baseline characteristics
| Characteristic | Intervention Arm |
|---|---|
| Age, Continuous | 80 years STANDARD_DEVIATION 10 |
| Orthopedic manifestations Carpal tunnel syndrome | 7 Participants |
| Orthopedic manifestations Degenerative joint disease | 6 Participants |
| Orthopedic manifestations Spinal stenosis | 7 Participants |
| Race/Ethnicity, Customized Hispanic | 10 Participants |
| Race/Ethnicity, Customized Non-Hispanic Black | 22 Participants |
| Race/Ethnicity, Customized Non-Hispanic White | 16 Participants |
| Race/Ethnicity, Customized Other or unknown | 2 Participants |
| Region of Enrollment United States | 50 participants |
| Sex: Female, Male Female | 18 Participants |
| Sex: Female, Male Male | 32 Participants |
Adverse events
| Event type | EG000 affected / at risk |
|---|---|
| deaths Total, all-cause mortality | 0 / 50 |
| other Total, other adverse events | 0 / 50 |
| serious Total, serious adverse events | 0 / 50 |
Outcome results
Primary
Rate of Cardiac Amyloidosis Diagnosis
The primary outcome is the rate of cardiac amyloidosis diagnosis (inclusive of transthyretin and light chain cardiac amyloidosis) which is performed in response to patient identification using the deep learning model, reported as the number of participants who had a positive diagnosis for ATTR-CM (transthyretin amyloid cardiomyopathy).
Time frame: Up to 1 year after identification (1 day of participant assessment)
| Arm | Measure | Value (COUNT_OF_PARTICIPANTS) |
|---|---|---|
| Intervention Arm | Rate of Cardiac Amyloidosis Diagnosis | 24 Participants |