Clinical Validation of SMD-RVECG for Predicting Atrial Fibrillation With Rapid Ventricular Response Within 2 Hours (AFRVR)

A Retrospective, Single Center, Single Arm, Superiority Confirmatory Study to Evaluate the Clinical Validity of SMD-RVECG, Artificial Intelligence Software to Predict the Risk of Developing Atrial Fibrillation With Rapid Ventricular Response (AF With RVR) Within 2 Hours Using Single Lead-Based Electrocardiogram Analysis

The purpose of this retrospective study is to evaluate the clinical performance of SMD-RVECG, an artificial intelligence-based medical device software that analyzes single-lead electrocardiogram data to predict the risk of atrial fibrillation with rapid ventricular response occurring within 2 hours.

A total of 348 eligible electrocardiogram datasets collected through VitalDB at Seoul National University Hospital will be included. Atrial fibrillation with rapid ventricular response is defined in this study as atrial fibrillation accompanied by an average heart rate of 110 beats per minute or greater for at least 30 seconds.

Eligible datasets will be classified as positive or negative for atrial fibrillation with rapid ventricular response. Two qualified 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-RVECG, and the software-generated predictions will be compared with the reference standard to evaluate clinical performance.

Study Overview

• Status: Not yet recruiting
• Conditions: Atrial Fibrillation (AF); Atrial Fibrillation With Rapid Ventricular Response
• Intervention / Treatment: Device: SMD-RVECG

Detailed Description

This clinical study is designed as a retrospective, single-center, single-arm, superiority confirmatory clinical performance study conducted at Seoul National University Hospital.

Pre-screening Electronic medical records and the VitalDB registry will be reviewed to identify potentially eligible data. The study will use continuous single-lead electrocardiogram data collected through VitalDB between September 1, 2022, and September 30, 2025, from patients who were 19 years of age or older at the time of data collection.

Screening and Data Collection A screening number will be assigned sequentially to each potentially eligible dataset. Eligibility will be determined by reviewing the predefined inclusion and exclusion criteria. For eligible cases, continuous single-lead electrocardiogram data, signal loss, heart rate, the occurrence and timing of atrial fibrillation with rapid ventricular response episodes, the electrocardiogram data collection period, demographic information, previous history of atrial fibrillation, and pregnancy status will be collected. Directly identifying personal information will not be collected.

Test Dataset Creation Eligible electrocardiogram datasets will be classified into positive and negative groups for atrial fibrillation with rapid ventricular response.

The positive group will include electrocardiogram datasets in which atrial fibrillation is followed by rapid ventricular response, defined as an average heart rate of 110 beats per minute or greater for at least 30 seconds. The dataset will include electrocardiogram data preceding the onset of rapid ventricular response and data following the episode, as specified in the study protocol.

The negative group will include electrocardiogram datasets with atrial fibrillation that is not accompanied by rapid ventricular response during the predefined assessment period.

The planned study dataset consists of 348 cases, including 58 positive cases and 290 negative cases.

Reference Standard Establishment Two anesthesiology and pain medicine specialists with at least 5 years of relevant clinical experience in electrocardiogram-based arrhythmia interpretation will independently review the electrocardiogram data and relevant medical records. The reviewers will assess electrocardiogram data quality, confirm the presence or absence and timing of atrial fibrillation with rapid ventricular response, and establish the reference-standard classification.

The reviewers will be blinded to each other's initial assessments and to the results generated by SMD-RVECG. If the two reviewers disagree, the classification will be determined through consensus and the basis for the consensus will be documented. If consensus cannot be reached, the dataset will be excluded from the study.

Application of the Investigational Device The medical device operator will receive the test electrocardiogram datasets identified only by screening numbers and will be blinded to the positive or negative reference-standard classifications. The datasets will be retrospectively analyzed using SMD-RVECG to generate risk estimates for atrial fibrillation with rapid ventricular response occurring within 2 hours. The software-generated peak risk values and corresponding times will be recorded.

Statistical Analysis The software-generated predictions will be compared with the reference-standard classifications. The primary performance measure is the area under the receiver operating characteristic curve for predicting atrial fibrillation with rapid ventricular response within 2 hours. A two-sided 95% confidence interval will be calculated using Newcombe's Wald method. The study will be considered successful if the lower bound of the 95% confidence interval is greater than 0.8.

Secondary performance measures include the area under the precision-recall curve, threshold-specific precision, recall, F1 score, sensitivity, specificity, positive predictive value, negative predictive value, confusion-matrix results, and prediction time horizon.

Because this retrospective study uses previously collected data, there will be no direct participant contact, additional examination, treatment, or change in clinical care.

• Study Type: Observational
• Enrollment (Estimated): 348

Contacts and Locations

• Study Contact: Name: JooYeon Yoo; Phone Number: +82-2-2051-3161; Email: clinical_trial@huinno.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• 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 between September 1, 2022, and September 30, 2025. The study population includes patients with atrial fibrillation whose eligible electrocardiogram datasets are classified according to the presence or absence of rapid ventricular response. AF with RVR-positive datasets include atrial fibrillation followed by rapid ventricular response, defined as an average heart rate of 110 beats per minute or greater for at least 30 seconds. AF with RVR-negative datasets include atrial fibrillation without rapid ventricular response during the predefined assessment period.

Description

Inclusion Criteria:

• Continuous single-lead electrocardiogram data collected through VitalDB at Seoul National University Hospital between September 1, 2022, and September 30, 2025
• Participant aged 19 years or older at the time of electrocardiogram data collection

• Electrocardiogram data meeting either of the following group definitions:

  • AF with RVR-positive group: atrial fibrillation followed by rapid ventricular response, defined as an average heart rate of 110 beats per minute or greater for at least 30 seconds, with available electrocardiogram data for up to 2 hours before the onset of rapid ventricular response and after the onset in accordance with the protocol
  • AF with RVR-negative group: atrial fibrillation without rapid ventricular response, with 3 hours of electrocardiogram data available before a selected index time corresponding to a similar time during hospitalization as that used for positive cases
• If the relevant episode 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 the episode, with a minimum electrocardiogram recording duration of 10 minutes
• Other data considered suitable for the study by the principal investigator

Exclusion Criteria:

• 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
• Electrocardiogram data from a participant whose baseline heart rate remained at 110 beats per minute or greater irrespective of atrial fibrillation
• Data considered unsuitable for this clinical study by the principal investigator

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
AF With RVR Positive Group; Electrocardiogram datasets from patients with atrial fibrillation in which rapid ventricular response occurred. Rapid ventricular response is defined as an average heart rate of 110 beats per minute or greater for at least 30 seconds. The dataset includes electrocardiogram data preceding the first onset of rapid ventricular response and data following the episode in accordance with the protocol. These datasets will be retrospectively analyzed using SMD-RVECG.	Device: SMD-RVECG; SMD-RVECG is an artificial intelligence-based software as a medical device designed to analyze continuous single-lead electrocardiogram data and estimate the risk of atrial fibrillation with rapid ventricular response occurring within 2 hours. The software generates a risk score ranging from 0 to 100 based on electrocardiogram signal characteristics. In this retrospective study, blinded electrocardiogram datasets identified only by screening numbers will be analyzed using SMD-RVECG. The software-generated risk scores, peak values, and corresponding times will be recorded and compared with the reference-standard classifications. The software will not be used to guide the clinical care of the patients whose data are included.
AF With RVR Negative Group; Electrocardiogram datasets from patients with atrial fibrillation in which rapid ventricular response did not occur during the predefined assessment period. The dataset includes electrocardiogram data from the 3 hours preceding a selected index time corresponding to a similar time during hospitalization as the onset time used for positive cases. These datasets will be retrospectively analyzed using SMD-RVECG.	Device: SMD-RVECG; SMD-RVECG is an artificial intelligence-based software as a medical device designed to analyze continuous single-lead electrocardiogram data and estimate the risk of atrial fibrillation with rapid ventricular response occurring within 2 hours. The software generates a risk score ranging from 0 to 100 based on electrocardiogram signal characteristics. In this retrospective study, blinded electrocardiogram datasets identified only by screening numbers will be analyzed using SMD-RVECG. The software-generated risk scores, peak values, and corresponding times will be recorded and compared with the reference-standard classifications. The software will not be used to guide the clinical care of the patients whose data are included.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
AUROC of SMD-RVECG for Predicting Atrial Fibrillation With Rapid Ventricular Response Within 2 Hours	The area under the receiver operating characteristic curve (AUROC) will be calculated by comparing the maximum risk score generated by SMD-RVECG with the reference-standard classification of the AF with RVR-positive and AF with RVR-negative electrocardiogram datasets. Sensitivity and the false-positive rate will be calculated across the evaluated decision thresholds to construct the receiver operating characteristic curve. A two-sided 95% confidence interval will be estimated using Newcombe's Wald method. The performance criterion will be met if the lower bound of the 95% confidence interval is greater than 0.8.	During retrospective analysis of the predefined electrocardiogram dataset for each case, up to 3 hours

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Area Under the Precision-Recall Curve of SMD-RVECG	The area under the precision-recall curve (AUPRC) will be calculated using the risk scores generated by SMD-RVECG and the reference-standard classification of the AF with RVR-positive and AF with RVR-negative electrocardiogram datasets. A higher AUPRC indicates better discrimination of AF with RVR-positive datasets.	During retrospective analysis of the predefined electrocardiogram dataset for each case, up to 3 hours
Sensitivity of SMD-RVECG for Predicting Atrial Fibrillation With Rapid Ventricular Response	Sensitivity, also referred to as recall, will be calculated at the evaluated decision thresholds as the proportion of reference-standard AF with RVR-positive datasets that are classified as positive by SMD-RVECG.	During retrospective analysis of the predefined electrocardiogram dataset for each case, up to 3 hours
Specificity of SMD-RVECG for Predicting Atrial Fibrillation With Rapid Ventricular Response	Specificity will be calculated at the evaluated decision thresholds as the proportion of reference-standard AF with RVR-negative datasets that are classified as negative by SMD-RVECG.	During retrospective analysis of the predefined electrocardiogram dataset for each case, up to 3 hours
Positive Predictive Value of SMD-RVECG	Positive predictive value, also referred to as precision, will be calculated at the evaluated decision thresholds as the proportion of datasets classified as positive by SMD-RVECG that are AF with RVR-positive according to the reference standard.	During retrospective analysis of the predefined electrocardiogram dataset for each case, up to 3 hours
Negative Predictive Value of SMD-RVECG	Negative predictive value will be calculated at the evaluated decision thresholds as the proportion of datasets classified as negative by SMD-RVECG that are AF with RVR-negative according to the reference standard.	During retrospective analysis of the predefined electrocardiogram dataset for each case, up to 3 hours
F1 Score of SMD-RVECG	The F1 score will be calculated at the evaluated decision thresholds as the harmonic mean of precision and recall. The F1 score ranges from 0 to 1, with higher values indicating a better balance between precision and recall.	During retrospective analysis of the predefined electrocardiogram dataset for each case, up to 3 hours
Prediction Time Horizon of SMD-RVECG for Atrial Fibrillation With Rapid Ventricular Response	For AF with RVR-positive datasets, the prediction time horizon will be calculated as the time interval between the software-generated prediction or alarm and the reference-standard onset of the AF with RVR episode.	Within the 2-hour period preceding the onset of atrial fibrillation with rapid ventricular response

Collaborators and Investigators

• Sponsor: HUINNO Co., Ltd
• Collaborators: Seoul National University Hospital; Korea Medical Device Development Fund

Study record dates

Study Major Dates

• Study Start (Estimated): October 1, 2026
• Primary Completion (Estimated): November 30, 2026
• Study Completion (Estimated): December 31, 2026

Study Registration Dates

• First Submitted: July 20, 2026
• First Submitted That Met QC Criteria: July 20, 2026
• First Posted (Actual): July 23, 2026

Study Record Updates

• Last Update Posted (Actual): July 23, 2026
• Last Update Submitted That Met QC Criteria: July 20, 2026
• Last Verified: July 1, 2026

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Rapid Ventricular Response; Software as a Medical Device; Atrial Fibrillation Prediction; Single-Lead Electrocardiogram; Atrial Fibrillation With Rapid Ventricular Response; AF With RVR; SMD-RVECG
• Additional Relevant MeSH Terms: Cardiovascular Diseases; Pathologic Processes; Heart Diseases; Arrhythmias, Cardiac; Pathological Conditions, Signs and Symptoms; Atrial Fibrillation
• Other Study ID Numbers: HU-AFRVR-01; RS-2026-25543193 (Other Grant/Funding Number: Korea Medical Device Development Foundation)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data collected in this study are not planned to be shared with external researchers. Any future sharing would require separate sponsor approval and compliance with applicable privacy, ethical, and institutional requirements.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No