AI-Based Prediction of Atrial Fibrillation in ESUS Patients With ICM (SMART-ESUS)

Predicting Atrial Fibrillation in Patients With Post-implantable Cardiac Monitor Implementation : A Prospective, Long-term Follow-up Study Using Comprehensive AI ECG Analysis : Multicenter Prospective Study

This study investigates patients with Embolic Stroke of Undetermined Source (ESUS) who have received an Implantable Cardiac Monitor (ICM). The main purpose is to evaluate the predictive value of an Artificial Intelligence ECG analysis tool, named SmartECG-AF.

Participants will be classified into two groups based on the AI analysis: a "High Risk" group and a "Low to Intermediate Risk" (control) group. The study aims to compare the incidence rate of atrial fibrillation (AF) events over time between these two groups. Additionally, the study will analyze the relationship between the AI-predicted risk levels and the occurrence of major cardiovascular events during the follow-up period.

Study Overview

• Status: Recruiting
• Conditions: Embolic Stroke of Undetermined Source

Detailed Description

Embolic Stroke of Undetermined Source (ESUS) accounts for a significant proportion of ischemic strokes, and occult Atrial Fibrillation (AF) is considered a major etiology. While Implantable Cardiac Monitors (ICMs) are the gold standard for long-term rhythm monitoring, identifying patients at the highest risk for AF remains a clinical challenge.

This multicenter, prospective study aims to validate the clinical utility of an artificial intelligence-based electrocardiogram analysis algorithm, "SmartECG-AF," in this specific population. The algorithm analyzes 12-lead ECGs recorded during sinus rhythm to detect subtle signs of electrical remodeling associated with paroxysmal AF.

Enrolled patients with ESUS who have undergone ICM implantation will have their baseline ECGs analyzed by the SmartECG-AF algorithm. Based on the AI-generated probability score, patients will be stratified into a "High Risk" group and a "Low to Intermediate Risk" group. The study will longitudinally track these patients to compare the time-to-event for ICM-detected AF between the two groups. Additionally, the study will evaluate the correlation between the AI risk score and the incidence of Major Adverse Cardiovascular Events (MACE), providing evidence for AI-guided risk stratification in cryptogenic stroke management.

• Study Type: Observational
• Enrollment (Estimated): 92

Contacts and Locations

• Study Contact: Name: Yong-Soo Baek, MD, PhD; Phone Number: +82-32-890-2200; Email: existsoo@inha.ac.kr
• Study Contact Backup: Name: Hyoung Seok Lee, MD; Phone Number: +82-32-890-3575; Email: hyoungseok_lee@inha.ac.kr

Study Locations

• South Korea
  • Ansan, South Korea
    • Recruiting
    • Korea University Ansan Hospital
    • Contact: Sangmi Oh; Phone Number: +82-31-412-5114; Email: osm221001@gmail.com
    • Contact: Seung-yong Shin, M.D., Ph.D.; Phone Number: +82-31-412-5114; Email: theshin04@naver.com
  • Incheon, South Korea
    • Recruiting
    • Inha University Hospital
    • Contact: Hyerim Park; Phone Number: +82-32-890-2114; Email: rimvely1126@naver.com
    • Contact: Yong-Soo Baek, MD, PhD; Phone Number: +82-32-890-2200; Email: existsoo@inha.ac.kr
  • Jeju City, South Korea
    • Recruiting
    • Jeju National University Hospital
    • Contact: Jin-hee Kim; Phone Number: +82-64-717-6000; Email: wpwndurh77@naver.com
    • Contact: Ki Yung Boo, MD, PhD; Phone Number: +82-64-717-6000; Email: pidori@hanmail.net
  • Seoul, South Korea
    • Recruiting
    • Korea University Guro Hospital
    • Contact: Yoonhee Choi; Phone Number: +82-2--2626-2336; Email: grkmcgrca009@kumc.or.kr
    • Contact: Dae-in Lee, MD, PhD; Phone Number: +82-2-2626-1114; Email: acttopia@gmail.com
  • Suwon, South Korea
    • Recruiting
    • Ajou University Hospital
    • Contact: Jihee Kang; Phone Number: +82-31-219-4329; Email: haagendasss@gmail.com
    • Contact: Kwang-No Lee, MD, PhD; Phone Number: +82-31-219-7830; Email: knlee81@ajou.ac.kr

Participation Criteria

Eligibility Criteria

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

• Sampling Method: Non-Probability Sample

Study Population

Patients diagnosed with Embolic Stroke of Undetermined Source (ESUS) aged 30 years or older who have received or are scheduled to receive an Implantable Cardiac Monitor (ICM). Participants are recruited from five tertiary referral hospitals in South Korea (Inha University Hospital, Jeju National University Hospital, Korea University Guro Hospital, Korea University Ansan Hospital, and Ajou University Hospital).

Description

Inclusion Criteria:

• Patients aged 30 years or older.
• Patients diagnosed with Embolic Stroke of Undetermined Source (ESUS) who have undergone or are scheduled for Implantable Cardiac Monitor (ICM) implantation.
• Patients who have undergone at least one 12-lead ECG examination within 2 weeks before or after the date of ICM implantation.
• Patients maintaining Sinus Rhythm on ECG at the time of enrollment.
• Patients who have voluntarily signed the informed consent form.

Exclusion Criteria:

• Patients diagnosed with Atrial Fibrillation (AF) at least once prior to the date of enrollment.
• Patients whose ICM battery status is at Elective Replacement Interval (ERI), making recording impossible.
• Patients whose ECGs cannot be analyzed by the AI algorithm (SmartECG-AF) due to severe artifacts or noise, or are incompatible with digital analysis.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort
High Risk Group; Patients classified as having a high risk of atrial fibrillation by the SmartECG-AF AI algorithm.
Low to Intermediate Risk Group; Patients classified as having a low to intermediate risk of atrial fibrillation by the SmartECG-AF AI algorithm.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Incidence of Atrial Fibrillation (Time-to-Event)	Comparison of the cumulative incidence rate of atrial fibrillation (AF) events between the High Risk group and the Low to Intermediate Risk group (classified by SmartECG-AF). AF occurrence is confirmed by reviewing data recorded on the Implantable Cardiac Monitor (ICM).	Up to 12 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Incidence of Major Adverse Cardiovascular Events (MACE)	Evaluation of the composite rate of major clinical events including recurrent stroke, hospitalization for heart failure, myocardial infarction, and all-cause death (cardiovascular and non-cardiovascular). The study will analyze the correlation between the occurrence of these events and the AI-predicted risk levels.	Up to 12 months

Collaborators and Investigators

• Sponsor: Inha University Hospital
• Collaborators: DeepCardio Co., Ltd.
• Investigators: Principal Investigator: Yong-Soo Baek, MD, PhD, Inha University Hospital

Study record dates

Study Major Dates

• Study Start (Actual): November 19, 2025
• Primary Completion (Estimated): May 1, 2027
• Study Completion (Estimated): May 1, 2028

Study Registration Dates

• First Submitted: January 9, 2026
• First Submitted That Met QC Criteria: January 9, 2026
• First Posted (Estimated): January 16, 2026

Study Record Updates

• Last Update Posted (Estimated): January 16, 2026
• Last Update Submitted That Met QC Criteria: January 9, 2026
• Last Verified: January 1, 2026

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Implantable Cardiac Monitor; Cryptogenic Stroke; Deep Learning; Electrocardiography; Risk Prediction
• Additional Relevant MeSH Terms: Cerebrovascular Disorders; Brain Diseases; Central Nervous System Diseases; Nervous System Diseases; Vascular Diseases; Cardiovascular Diseases; Stroke; Ischemic Stroke
• Other Study ID Numbers: 2024-07-024

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: Individual participant data will not be shared to protect participant privacy and confidentiality. The informed consent form signed by participants does not include authorization for the release of individual raw data to third parties.

Drug and device information, study documents

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