Artificial Intelligence Enhanced ECG to Detect Cardiac Amyloidosis

Artificial Intelligence Enhanced ECG to Detect Cardiac Amyloidosis: Protocol for a Pragmatic Cluster Randomized Clinical Trial (PREDICT-AMY)

The purpose of this study is to assess a novel artificial intelligence (AI)-enabled electrocardiogram (ECG)-based screening tool for improving the diagnosis of cardiac amyloidosis (CA).

Study Overview

• Status: Completed
• Conditions: Cardiac Amyloidosis
• Intervention / Treatment: Other: AI ECG Amyloid algorithm

Detailed Description

This pragmatic trial will be the first study to prospectively evaluate the use of the AI ECG dashboard along with an augmented report in everyday practice. The findings will also guide future implementation strategies and inform the translation of many of the current and future AI algorithms into the clinical setting. The participants are the providers. Basic demographic information about the providers will be collected as well as their reactions to the trial based educational guidance supplied to them. Patient health information will be collected on their patients using a HIPPA waiver. There will be no patient contact.

• Study Type: Interventional
• Enrollment (Actual): 20143
• Phase: Not Applicable

Contacts and Locations

Study Locations

• United States
  • Arizona
    • Scottsdale, Arizona, United States, 85259
      • Mayo Clinic in Arizona
  • Florida
    • Jacksonville, Florida, United States, 32224
      • Mayo Clinic in Florida
  • Minnesota
    • Rochester, Minnesota, United States, 55905
      • Mayo Clinic in Rochester
  • Wisconsin
    • Eau Claire, Wisconsin, United States, 54701
      • Mayo Clinic Health System - Eau Claire

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Mayo Clinic cardiology or hematology providers who care for adult patients
• Mayo Clinic providers who consent to participate on this study

Exclusion Criteria:

- None

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Screening
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Notification of the AI ECG algorithm and the A3E scores; Provider-facing recommendation report that alerts to provider for positive AI ECG Amyloid Score, standardized amyloid order set, diagnostic algorithm and reminders	Other: AI ECG Amyloid algorithm; Artificial intelligence enabled electrocardiogram screening tool used to identify the predictive model that best differentiates those at greatest risk for an amyloidosis diagnosis
No Intervention: Usual Care; No alerts to provider for positive AI ECG Amyloid Score, standardized amyloid order set, diagnostic algorithm and reminders

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
To determine if AI ECG algorithm and enhanced algorithms and education enable earlier diagnosis of cardiac amyloidosis	The number of patients diagnosed with cardiac amyloidosis in cardiology and hematology practices will be compared between those providers undergoing the AI ECG intervention to those randomized to standard practice arm	1 year

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
To determine if AI ECG and enhanced algorithms and education enable earlier diagnosis of cardiac amyloidosis intervention across different practice types (strata)	Performance of AI ECG intervention across cardiology and hematology practices and between community and tertiary facilities will be analyzed by measuring rates of cardiac amyloidosis diagnosis across these strata	1 year
To assess provider satisfaction with the AI ECG intervention	For a screening tool to be effective, it has to be user friendly. The providers randomized to the AI ECG intervention arm will be surveyed to understand their experience. This endpoint will be descriptive. Providers will answer a 6 question using a 5-point Likert scale (higher number is more favorable).	1 year
To assess differential costs between the intervention arm and the standard of care arm	Upon trial completion, the difference in clinical expenditures between the intervention and standard of care arms will be compared. To this end, the rates of test ordering will be counted and compared between the interventional arm and the standard of care arm. A cost will be assigned to each test to calculate expenditures per correct diagnosis. The test of interest will include: NT-proBNP, troponin, protein electrophoresis with isotyping, serum immunoglobulin free light chains, 24-hour urinary protein with immunofixation, cardiac magnetic resonance imaging, echocardiogram, technetium pyrophosphate nuclear cardiac scintigraphy , endomyocardial biopsy, and fat aspirate.	1 year

Collaborators and Investigators

• Sponsor: Mayo Clinic
• Investigators: Principal Investigator: Angela Dispenzieri, MD, Mayo Clinic

Publications and helpful links

Helpful Links

• Mayo Clinic Clinical Trials

Study record dates

Study Major Dates

• Study Start (Actual): June 19, 2023
• Primary Completion (Actual): July 23, 2025
• Study Completion (Actual): July 23, 2025

Study Registration Dates

• First Submitted: September 16, 2022
• First Submitted That Met QC Criteria: September 22, 2022
• First Posted (Actual): September 27, 2022

Study Record Updates

• Last Update Posted (Actual): February 17, 2026
• Last Update Submitted That Met QC Criteria: February 13, 2026
• Last Verified: February 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Nervous System Diseases; Neuromuscular Diseases; Metabolism, Inborn Errors; Genetic Diseases, Inborn; Metabolic Diseases; Peripheral Nervous System Diseases; Neurodegenerative Diseases; Heredodegenerative Disorders, Nervous System; Proteostasis Deficiencies; Amyloid Neuropathies; Amyloidosis, Familial; Amyloidosis; Congenital, Hereditary, and Neonatal Diseases and Abnormalities; Nutritional and Metabolic Diseases; Amyloid Neuropathies, Familial
• Other Study ID Numbers: PREDICT-AMY (Other Identifier: Sponsor Protocol Number); 22-005311 (Other Identifier: Mayo Clinic Institutional Review Board); NCI-2024-00928 (Registry Identifier: CTRP (Clinical Trial Reporting Program))

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No