Clinical Validation of SMD-AFECG for Predicting New-Onset Atrial Fibrillation Within 2 Hours Using Single-Lead ECG Data

NCT07722078 | Not Yet Recruiting

• 2 other identifiers: HU-NOAF-01RS-2026-25543193
• Study Type: observational
• Target: 797
• Locations: 0 countries
• Sites: N/A

Brief Summary

The purpose of this retrospective study is to evaluate the clinical performance of SMD-AFECG, an artificial intelligence-based medical device software that predicts the risk of atrial fibrillation occurring within 2 hours using single-lead electrocardiogram data. A total of 797 eligible electrocardiogram datasets collected through VitalDB at Seoul National University Hospital will be included. The performance of SMD-AFECG will be evaluated separately for new-onset atrial fibrillation in patients without a previous history of atrial fibrillation (NOAF) and atrial fibrillation episodes in patients with a previous history of atrial fibrillation (RAF). Two physicians blinded to the software results will review the electrocardiogram data and relevant medical records to establish the reference-standard classification. The blinded electrocardiogram datasets will then be analyzed using SMD-AFECG, and the software-generated predictions will be compared with the reference standard to evaluate the area under the receiver operating characteristic curve for NOAF and RAF.

Conditions

Atrial Fibrillation (AF); Atrial Fibrillation New Onset

Keywords

New-Onset Atrial Fibrillation; Recurrent Atrial Fibrillation; Atrial Fibrillation Prediction; Single-Lead Electrocardiogram; Artificial Intelligence; Software as a Medical Device; SMD-AFECG; Repeated Atrial Fibrillation

Outcome Measures

Primary Outcomes (2)

• AUROC of SMD-AFECG for Predicting New-Onset Atrial Fibrillation Within 2 Hours

  The area under the receiver operating characteristic curve (AUROC) will be calculated by comparing the maximum risk score generated by SMD-AFECG with the reference-standard classification of the NOAF-positive and NOAF-negative ECG datasets. A two-sided 95% confidence interval will be estimated using DeLong's method with a Wald-type confidence interval. The performance criterion will be met if the lower bound of the 95% confidence interval is greater than 0.7753.

  During the AF-free ECG window immediately preceding AF onset for positive cases or the selected index time for negative cases (up to 2 hours)

• AUROC of SMD-AFECG for Predicting Repeated Atrial Fibrillation Within 2 Hours

  The area under the receiver operating characteristic curve (AUROC) will be calculated by comparing the maximum risk score generated by SMD-AFECG with the reference-standard classification of the RAF-positive and RAF-negative ECG datasets. A two-sided 95% confidence interval will be estimated using DeLong's method with a Wald-type confidence interval. The performance criterion will be met if the lower bound of the 95% confidence interval is greater than 0.8299.

  During the AF-free ECG window immediately preceding AF onset for positive cases or the selected index time for negative cases (up to 2 hours)

Secondary Outcomes (14)

• AUPRC of SMD-AFECG for Predicting New-Onset Atrial Fibrillation Within 2 Hours

  During the AF-free ECG window immediately preceding AF onset for positive cases or the selected index time for negative cases, up to 2 hours

• AUPRC of SMD-AFECG for Predicting Repeated Atrial Fibrillation Within 2 Hours

  During the AF-free ECG window immediately preceding AF onset for positive cases or the selected index time for negative cases, up to 2 hours

• Threshold-Specific Sensitivity of SMD-AFECG for Predicting New-Onset Atrial Fibrillation Within 2 Hours

  During the AF-free ECG window immediately preceding AF onset for positive cases or the selected index time for negative cases, up to 2 hours

• Threshold-Specific Sensitivity of SMD-AFECG for Predicting Repeated Atrial Fibrillation Within 2 Hours

  During the AF-free ECG window immediately preceding AF onset for positive cases or the selected index time for negative cases, up to 2 hours

• Threshold-Specific Specificity of SMD-AFECG for Predicting New-Onset Atrial Fibrillation Within 2 Hours

  During the AF-free ECG window immediately preceding AF onset for positive cases or the selected index time for negative cases, up to 2 hours

Study Arms (4)

NOAF Positive Group

Single-lead electrocardiogram datasets from patients without a previous history of atrial fibrillation that include the first atrial fibrillation episode. The datasets include an atrial fibrillation-free electrocardiogram period before the onset of atrial fibrillation and electrocardiogram data following its onset. SMD-AFECG will be retrospectively applied to estimate the risk of atrial fibrillation occurring within 2 hours.

NOAF Negative Group

Single-lead electrocardiogram datasets from patients without a previous history of atrial fibrillation and without an atrial fibrillation episode during the predefined assessment period. The datasets include a continuous atrial fibrillation-free electrocardiogram period before a selected index time and electrocardiogram data following the index time. SMD-AFECG will be retrospectively applied to estimate the risk of atrial fibrillation occurring within 2 hours.

RAF Positive Group

Single-lead electrocardiogram datasets from patients with a previous history of atrial fibrillation that include an atrial fibrillation episode. The datasets include an atrial fibrillation-free electrocardiogram period before the onset of atrial fibrillation and electrocardiogram data following its onset. SMD-AFECG will be retrospectively applied to estimate the risk of atrial fibrillation occurring within 2 hours.

RAF Negative Group

Single-lead electrocardiogram datasets from patients with a previous history of atrial fibrillation and without an atrial fibrillation episode during the predefined assessment period. The datasets include a continuous atrial fibrillation-free electrocardiogram period before a selected index time and electrocardiogram data following the index time. SMD-AFECG will be retrospectively applied to estimate the risk of atrial fibrillation occurring within 2 hours.

Eligibility Criteria

• Age: 19 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Patients aged 19 years or older whose continuous single-lead electrocardiogram data were collected through VitalDB at Seoul National University Hospital from September 1, 2022, to before September 30, 2025. Eligible datasets will be identified retrospectively from the VitalDB registry and corresponding clinical records. The study population includes patients with and without a previous history of atrial fibrillation and with or without an atrial fibrillation episode during the predefined assessment window. Eligible datasets will be classified into the NOAF-positive, NOAF-negative, RAF-positive, and RAF-negative groups.

You may qualify if:

• Existing continuous single-lead electrocardiogram data collected through VitalDB at Seoul National University Hospital from September 1, 2022, to before September 30, 2025
• Participant aged 19 years or older at the time of electrocardiogram data collection
• Availability of an electrocardiogram dataset meeting one of the following criteria:
• No previous history of atrial fibrillation and a first atrial fibrillation episode, with continuous atrial fibrillation-free electrocardiogram data for the 2 hours before onset and electrocardiogram data for 1 hour after onset (NOAF-positive group)
• No previous history of atrial fibrillation and no atrial fibrillation episode, with continuous atrial fibrillation-free electrocardiogram data for the 2 hours before a selected index time and electrocardiogram data for 1 hour after the index time (NOAF-negative group)
• Previous history of atrial fibrillation and an atrial fibrillation episode, with continuous atrial fibrillation-free electrocardiogram data for the 2 hours before onset and electrocardiogram data for 1 hour after onset (RAF-positive group)
• Previous history of atrial fibrillation and no atrial fibrillation episode, with continuous atrial fibrillation-free electrocardiogram data for the 2 hours before a selected index time and electrocardiogram data for 1 hour after the index time (RAF-negative group)
• If atrial fibrillation occurred within 2 hours after the start of electrocardiogram recording, availability of electrocardiogram data from the start of recording through up to 1 hour after atrial fibrillation onset, with a minimum recorded electrocardiogram duration of 10 minutes

You may not qualify if:

• Electrocardiogram data considered to be of inadequate quality because of noise, poor equipment handling, unclear signals, artifacts, or similar problems
• Electrocardiogram data with signal loss of 5 percent or greater
• Electrocardiogram data with a heart rate below 30 beats per minute or above 300 beats per minute
• Data collected from a participant who was pregnant or breastfeeding at the time of data collection
• Data previously used for training or validation of the artificial intelligence model
• Data considered unsuitable for this clinical study by the principal investigator

Sponsors & Collaborators

• HUINNO Co., Ltd: lead
• Seoul National University Hospital: collaborator
• Korea Medical Device Development Fund: collaborator

MeSH Terms

Conditions

Atrial Fibrillation

Condition Hierarchy (Ancestors)

Arrhythmias, Cardiac; Heart Diseases; Cardiovascular Diseases; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Central Study Contacts

JooYeon Yoo

CONTACT

+82-2-2051-3161; clinical_trial@huinno.com

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: RETROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: July 20, 2026
• First Posted: July 23, 2026
• Study Start (Estimated): October 1, 2026
• Primary Completion (Estimated): November 30, 2026
• Study Completion (Estimated): December 31, 2026
• Last Updated: July 23, 2026

Record last verified: 2026-07

Data Sharing

• IPD Sharing: Will not share