Prospective Validation Study of AI-based Prediction Algorithm for the Prediction of Paroxysmal Atrial Fibrillation

Brief Summary: The purpose of this study is to predict the occurrence of paroxysmal atrial fibrillation by finding high-risk group from normal sinus rhythm ECG through artificial intelligence-based prediction algorithm.

Detailed Description: This study is a multi-center, prospective observational validation study. Patients aged 18 or above who are hospitalized at our hospital or who visited the outpatient clinic with arrhythmia symptoms (such as palpitation) after the clinical research approval will be enrolled. The normal sinus rhythm electrocardiogram (ECG) at the time of participation in the study is recorded and put into the artificial intelligence prediction algorithm. The result of risk stratification is blinded and will not be informed to both the research director and subjects. After applying wearable devices to the subject, the ECG recorded for the first week is analyzed to confirm the occurrence of paroxysmal atrial fibrillation (the gold standard for diagnosis of atrial fibrillation). When the wearable devices are removed, the 12 lead electrocardiogram will be taken again, and if it shows normal sinus rhythm electrocardiogram, then it will be put into the artificial intelligence prediction algorithm to calculate the result as well.

Recruitment & Eligibility

Inclusion Criteria

Participants must be above 20 in age
Participants are patients with symptom of arrhythmia who visited outpatient clinic or who have been hospitalized

Exclusion Criteria

Excluding patients with cardiac implantable electronic device such as pacemakers, implantable defibrillators (ICD), or cardiac resynchronization therapy (CRT).
Excluding pregnant women and lactating women.

Arm && Interventions

Group	Intervention	Description
Low risk group for paroxysmal atrial fibrillation	MobiCare	Subject patients are above 20 in age who are hospitalized in our hospital or outpatients with arrhythmia symptoms after the clinical research approval. The sinus rhythm electrocardiogram at the time of the patient's participation in the study is put into the artificial intelligence prediction algorithm, and the risk stratification results are blinded and are not informed to both the research director and the subjects. For the low-risk group, after attaching the wearable electrocardiogram to the subject, the electrocardiogram recorded a week later is analyzed to confirm the occurrence of atrial fibrillation.
High risk group for paroxysmal atrial fibrillation	MobiCare	Subject patients are above 20 in age who are hospitalized in our hospital or outpatients with arrhythmia symptoms after the clinical research approval. The sinus rhythm electrocardiogram at the time of the patient's participation in the study is put into the artificial intelligence prediction algorithm, and the risk stratification results are blinded and are not informed to both the research director and the subjects. For the highrisk group, after attaching the wearable electrocardiogram to the subject, the electrocardiogram recorded a week later is analyzed to confirm the occurrence of atrial fibrillation.

Primary Outcome Measures

Name	Time	Method
Occurrence of paroxysmal AF	1 week	The AI prediction algorithm classifies patients into high-risk and low-risk categories for predicting paroxysmal atrial fibrillation within a week, based on ECG recordings of those with normal sinus rhythm. The accuracy of the prediction will be assessed through the use of a wearable device that records occurrence of paroxysmal atrial fibrillation over the course of a week.

Secondary Outcome Measures

Name	Time	Method
Performance verification of AI prediction model	1 week	The artificial intelligence prediction algorithm categorizes patients into high-risk and low-risk groups when predicting paroxysmal atrial fibrillation within one week based on normal sinus rhythm ECG data. The AI prediction algorithm's performance is assessed based on the data obtained from the primary outcome, which involves confirming whether atrial fibrillation recorded through a week-long use of a wearable device. We will gauge the algorithm's effectiveness by evaluating its predictive abilities, encompassing sensitivity, specificity, positive predictive rate, negative predictive rate, and the F1 score.

Locations (11): Chonnam National University Hospital
🇰🇷
Gwangju, Korea, Republic of
Chungbuk National University Hospital
🇰🇷
Chungbuk, Korea, Republic of
Korea University Anam Hospital
🇰🇷
Seoul, Korea, Republic of
Gachon University Gil Medical Center
🇰🇷
Incheon, Korea, Republic of
Kyung Hee University Hospital
🇰🇷
Seoul, Korea, Republic of
Yongin Severance Hospital
🇰🇷
Gyeonggi-do, Korea, Republic of
Ewha Womans University Seoul Hospital
🇰🇷
Seoul, Korea, Republic of
Ewha Womans University Mokdong Hospital
🇰🇷
Seoul, Korea, Republic of
Hanyang University Seoul Hospital
🇰🇷
Seoul, Korea, Republic of
Chung-Ang University Hospital
🇰🇷
Seoul, Korea, Republic of
Korea University Guro Hospital
🇰🇷
Seoul, Korea, Republic of