Exploratory Study of Apple Watch Electrocardiographic Diagnostic Performance Enhanced by an Artificial Intelligence Algorithm

Étude Exploratoire Des Performances de Diagnostic Électrocardiographique de l'Apple Watch augmentée d'un Algorithme d'Intelligence Artificielle

Status

Completed

Phases

Unknown

Study type

Observational

Source

ClinicalTrials.gov

Registry ID

NCT04792905

Enrollment

200

Registered

2021-03-11

Start date

2021-03-30

Completion date

2021-07-19

Last updated

2021-09-08

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Atrial Fibrillation

Brief summary

This observational exploratory prospective study will evaluate the performance on an Artificial Intelligence (AI) solution interpreting ECG (electrocardiogram) collected from an Apple Watch (AI-AW) in the detection of Atrial Fibrillation (AF)

Detailed description

After being informed about the study, participants hospitalized for ablation or cardioversion or having a cardiac rhythm consultation at the investigational center will have Apple Watch ECG recordings done simultaneously with 12-lead ECG measurements performed in accordance with the existing in-stay subject monitoring protocol. AI-AW will be compared to standard manual 12-lead ECG reviewed by cardiologists for AF detection.

Interventions

DEVICECardiologs

Two Apple Watch recordings (one recording with the watch on the wrist and one on the left side of the abdomen) interpreted by Cardiologs AI done simultaneously with each 12-lead ECG

Study design

Observational model

CASE_ONLY

Time perspective

CROSS_SECTIONAL

Eligibility

Sex/Gender

ALL

Age

22 Years to No maximum

Healthy volunteers

Inclusion criteria

* Patient aged 22 or older, able and willing to participate in the study * Patient admitted to hospital for ablation, cardioversion or cardiac electrophysiological exploration or who come for regular rhythmology consultations * Patient who has read the information note and has given his or her consent before any procedure related to the study * Patient affiliated to social security

Exclusion criteria

* Pregnant or breastfeeding women * Patient with a pacemaker, implantable defibrillator or cardiac resynchronisation therapy device. * Subject related to the investigator or any other staff member directly involved in the conduct of the study * Patient incapable of giving consent, minor or adult patient protected by law

Design outcomes

Primary

Measure	Time frame	Description
Performance of AF detection	1 day	Performance of AF detection by an artificial intelligence (AI) solution interpreting ECG collected via Apple Watches (AI-AW), compared to physician's diagnosis from the 12 leads ECG

Secondary

Measure	Time frame	Description
AW versus AI-AW	1 day	Comparison of Apple Watch (AW) and AI-AW AF detection performance
AI-AW versus AI-12lead	1 day	Comparison of the performance of AF detection by AI-AW and AI applied to the 12-lead ECG

Countries

France

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Feb 4, 2026