Atrial Fibrillation Risk Estimation With Single-lead Handheld Electrocardiograms
For patients and families
In plain language
An automatic summary of structured registry data. It is an orientation aid, not a substitute for the official protocol or a physician assessment.
- What is being studied
- The protocol lists: 1L ECG screening, Patch monitor.
- Who it may be relevant to
- Registry conditions: Atrial Fibrillation (AF). Basic parameters: 18 years — 90 years · All.
- What needs checking
- Age, condition and sex are only basic indicators. Prior treatment, laboratory values and other mandatory requirements appear in the eligibility criteria below.
- Where it takes place
- United States
- Next step
- Save the trial, show it to the treating physician, and confirm current recruitment with the study center. Costs, documents and travel →
Unsure about the terms? Read our patient guide →
Overview
The goal of this prospective, non-randomized pilot study is to learn whether predictions from a previously validated 12-lead ECG-based artificial intelligence (AI) algorithm (ECG-AI) identify people more likely to have undiagnosed atrial fibrillation (AF). The main questions it aims to answer are: Do people predicted to have high risk of AF using ECG-AI have a higher rate of new AF diagnosis using 1L ECG screening compared with people predicted to have a low risk? Do AI-based AF risk estimates from the 12-lead ECG correlate with AF risk estimates from the 1L ECG? Do people find 1L ECG screening for AF acceptable and useful? Participants will: Undergo screening with 1L ECG mailed to their home Complete a survey assessing attitudes toward 1L ECG screening Complete a 14-day patch monitor on 1 or 2 occasions depending on 1L ECG results
Detailed description
This is a prospective, non-randomized pilot study designed to assess whether our 12-lead ECG algorithm can identify individuals with AF detectable using 1L ECG. We will also assess whether AF risk estimates from the 1L ECG correlate with those using the 12-lead ECG. We also plan to assess participant attitudes toward the use of 1L ECGs for AF risk estimation.
Using our AF risk algorithm on existing 12-lead ECGs, will categorize prospective participants into low AF risk (\<1% 1-year AF risk) versus high AF risk (\>10% 1-year AF risk). We will mail 1L ECG devices to participants and ask them to obtain 3 tracings which we will then use to estimate AF risk using a 1L ECG version of our AF risk algorithm. We will then screen perform patch monitor screening for AF and compare the rates of AF detection between the two groups.
This study involves use of two consumer digital devices. The AliveCor KardiaMobile 1L ECG device is an FDA cleared cardiac rhythm assessment device capable of producing a 1L ECG in conjunction with a compatible smartphone. The Zio®XT is an FDA cleared medical-grade 1L ECG rhythm monitor.
This pilot study has three main outcomes: 1) prospectively ascertained estimated AF risk using the handheld 1L ECG algorithm, 2) incident AF at 12 months, ascertained using the linked EHR and/or the results of the study patch monitors, and 3) perceived acceptability and usefulness of the handheld ECG. No physical study visits are required according to this protocol.
Interventions
- Diagnostic test 1L ECG screening
Individuals will undergo 1L ECG screening using the AliveCor KardiaMobile 1L ECG device - Diagnostic test Patch monitor
Individuals who are found to have evidence of AF on 1L ECG will undergo assessment with 14-day patch monitor at the time of initial screen. Otherwise all study participants will undergo 14-day patch monitor at the 1-year timepoint.
Primary outcome measures
- New AF diagnosis (%) [Time frame: 1 year]
- Acceptability and usefulness [Time frame: 0]
- AI-based AF risk correlation [Time frame: 0]
Eligibility criteria
Inclusion criteria
- Men and women aged 50-90 who are new or established patients in an MGH primary care or ambulatory cardiology practice
- Willing to provide consent to participate in the study to access data from electronic health records (EHR)
- At least 1 12-lead ECG obtained within 5 years prior to study start date for AF risk estimation
- Have access to a smart phone or tablet to use with the AliveCor KardiaMobile 1L ECG device
Exclusion criteria
- History of atrial fibrillation or atrial flutter as documented in the patient's current electronic health record medical problem list or self-reported diagnosis
- Implanted cardiac devices (pacemakers, implantable cardiac defibrillators, or cardiac resynchronization therapy, and implantable loop recorders)
- History of allergy to adhesive
Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.
Healthy volunteers: Yes
Study design
- Allocation
- Non-randomized
- Model
- Parallel assignment
- Masking
- Single blind
- Primary purpose
- Diagnostic
Study locations
United States · 1 center
- Mass General Brigham — Boston
Publications
- Khurshid S, Friedman SF, Al-Alusi MA, Kany S, Sommers T, Anderson CD, Ho JE, McManus DD, Borowsky LH, Ashburner JM, Lubitz SA, Atlas SJ, Maddah M, Singer DE, Ellinor PT. Artificial intelligence-enabled analysis of handheld single-lead electrocardiograms to predict incident atrial fibrillation: an analysis of the VITAL-AF randomized trial. NPJ Digit Med. 2025 Nov 26;8(1):776. doi: 10.1038/s41746-02 PMID 41299008
- Khurshid S, Friedman S, Reeder C, Di Achille P, Diamant N, Singh P, Harrington LX, Wang X, Al-Alusi MA, Sarma G, Foulkes AS, Ellinor PT, Anderson CD, Ho JE, Philippakis AA, Batra P, Lubitz SA. ECG-Based Deep Learning and Clinical Risk Factors to Predict Atrial Fibrillation. Circulation. 2022 Jan 11;145(2):122-133. doi: 10.1161/CIRCULATIONAHA.121.057480. Epub 2021 Nov 8. PMID 34743566
Identifiers
NCT: NCT07468123 · 2024P002767