Skip to content

A Study on the Effectiveness of the Application of an Artificial Intelligence Algorithm for Calibrating PPG With ECG to Improve the Accuracy of Atrial Fibrillation Burden Estimation

A Study on the Effectiveness of the Application of an Artificial Intelligence Algorithm for Calibrating PPG With ECG to Improve the Accuracy of Atrial Fibrillation Burden Estimation

Status
Completed
Phases
Unknown
Study type
Observational
Source
ClinicalTrials.gov
Registry ID
NCT06552468
Acronym
EASE-AF
Enrollment
1054
Registered
2024-08-14
Start date
2024-01-14
Completion date
2024-11-27
Last updated
2024-12-31

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

Conditions

Atrial Fibrillation

Keywords

Atrial Fibrillation Burden、 AI Correction、W-PPG

Brief summary

Use the ECG watch to collect W-PPG and W-ECG data. Through artificial intelligence algorithms, compare the W-PPG data collected by the ECG watch and the W-PPG data calibrated by the W-ECG data of the ECG watch with the P-ECG data manually annotated after being collected by the ECG recorder. Then evaluate the effectiveness of the calibrated algorithm in improving the accuracy of estimating atrial fibrillation burden.

Detailed description

After the subjects are fully informed and sign the informed consent form, they will be asked to wear the ECG recorder and the ECG watch simultaneously to collect P-ECG data as well as W-PPG and W-ECG data respectively. The collection period is from the patient's admission to the time before the patient's surgery. The collected data will be analyzed by the Smart-AF of Xinjikang Company. The W-PPG data collected by the ECG watch and the W-PPG data calibrated by the W-ECG data of the ECG watch will be compared with the P-ECG data that has been manually annotated after being collected by the ECG recorder. The differences in identifying atrial fibrillation and in the statistics of atrial fibrillation burden between the W-PPG data of atrial fibrillation patients and the P-ECG data as well as the W-PPG and P-ECG data calibrated by comparison with the W-ECG data will be compared. ECG Watch ECG Monitoring Method: 1. Positive Alert: W-PPG detects atrial fibrillation and prompts measurement of W-ECG When W-PPG detects atrial fibrillation, the data is uploaded to the server for confirmation. If the server detects atrial fibrillation, it triggers a vibration message to prompt the measurement of W-ECG. If a valid W-ECG measurement is not completed within 5 minutes after the message alert, a vibration reminder is triggered again, with a maximum of two reminders per trigger point. When the daily reminder count reaches 10, no further reminders will be given; for the first 5 reminders, each pair of reminders must be at least 20 minutes apart, and for the last 5 reminders, each pair must be at least 40 minutes apart. 2. Periodic Reminder: Scheduled reminders for W-ECG measurement Vibration reminders are triggered at fixed times: 09:00, 10:30, 11:30, 13:00, 14:00, 15:30, 17:00, 18:00, 19:00, 20:30. If a 60-second W-ECG measurement is not completed within 5 minutes after each trigger, a vibration reminder is triggered again, with a maximum of two vibration reminders per trigger point. 3. Voluntary Measurement: Active measurement of W-ECG During the period when the subject is wearing the watch, they can voluntarily measure W-ECG.

Interventions

DEVICEAF monitoring by a smartwatch with PPG

The device we used for intervention is a smartwatch (JKwear 1, Chengdu CVhealth Science and Technology Co., Ltd, CN) for collecting watch-recorded-PPG (W-PPG).

Sponsors

Beijing Anzhen Hospital
Lead SponsorOTHER

Study design

Observational model
COHORT
Time perspective
PROSPECTIVE

Eligibility

Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No

Inclusion criteria

Patients must meet all of the following criteria to be included in the study: 1. Aged 18 and above; 2. There was a clear electrocardiogram record of atrial fibrillation in the past, and atrial fibrillation ablation surgery will be performed during this hospitalization; 3. Patients who agree to wear both the ECG watch and the ECG recorder simultaneously;

Exclusion criteria

Patients who meet any of the following criteria cannot be included in this study: 1. Unable to complete the wearing due to problems such as limited mobility. 2. Severe skin diseases such as severe skin allergies or skin ulcers. 3. Those with chronic insomnia who have not received drug treatment. 4. Patients with severe cardiovascular and cerebrovascular diseases who may need emergency treatment at any time. 5. Those with a history of Parkinson's disease, schizophrenia, or epilepsy. 6. Black people and those with overly dark skin.

Design outcomes

Primary

MeasureTime frameDescription
Automatically analyze the W-PPG data and the W-PPG data calibrated by W-ECG.One dayAutomatically analyze the W-PPG data and the W-PPG data calibrated by W-ECG through the Smart-AF of Xinjikang Company, and then compare the analyzed results with the P-ECG results manually annotated and proofread.

Secondary

MeasureTime frameDescription
Automatically analyze the W-PPG data and the W-PPG data calibrated by W-ECG.One dayAutomatically analyze the W-PPG data calibrated by W-ECG through artificial intelligence algorithms. Then compare the analyzed results with the P-ECG results that have been manually annotated and proofread. Finally, evaluate the sensitivity and specificity of the artificial intelligence algorithms in analyzing and identifying atrial fibrillation from the W-PPG data calibrated by W-ECG.

Countries

China

Outcome results

None listed

Source: ClinicalTrials.gov · Data processed: Jul 15, 2026