딥카디오

RESOURCE

논문

(심방세동 위험) 정상 동율동(동리듬) 상태에서 심방세동을 식별하는 인공지능(Artificial Intelligence, 12유도 심전도 , AIAFib) : 임상시험, 다기관 후향적 연구

작성일
첨부파일

이 연구는 정상 심박동(동성 리듬) 상태에서 측정한 12유도 심전도(ECG)를 분석해 발작성 심방세동(PAF)을 예측하는 인공지능(AI) 알고리즘의 유효성을 대규모로 검증하고, 이 AI의 예측 결과가 환자의 실제 임상적 예후와 어떻게 연관되는지 확인하기 위한 다기관 후향적 연구입니다.

 

연구진은 국내 10개 대학병원에서 약 10년간(2012~2021년) 수집된 5만 건 이상의 심전도 데이터와 환자의 임상 기록(동반 질환, 입원 내역, 시술 결과, 사망률 등)을 종합적으로 분석합니다. 이를 통해 단순히 AI 모델의 심방세동 예측 정확도를 평가하는 것에 그치지 않고, AI가 분류한 위험도(고위험/저위험)에 따라 환자의 입원 시기나 시술 예후, 생존율 등에 어떤 차이가 발생하는지 생존 분석 등 엄격한 통계 기법을 통해 입증할 계획입니다. 결과적으로 이 연구는 심방세동의 조기 발견 및 선제적 관리를 위한 새로운 위험도 평가 기준을 제시하여, 향후 심혈관 질환 진단과 치료에 있어 인공지능이 기여할 수 있는 혁신적인 가능성을 증명하는 것을 목표로 합니다.

 

 

Introduction

Atrial fibrillation (AF) is the most common arrhythmia, contributing significantly to morbidity and mortality. In a previous study, we developed a deep neural network for predicting paroxysmal atrial fibrillation (PAF) during sinus rhythm (SR) using digital data from standard 12-lead electrocardiography (ECG).

  • Primary Aim: To validate an existing artificial intelligence (AI)-enhanced ECG algorithm for predicting PAF in a multicenter tertiary hospital.

  • Secondary Objective: To investigate whether the AI-enhanced ECG is associated with AF-related clinical outcomes.

Methods and Analysis

We will conduct a retrospective cohort study of more than 50,000 12-lead ECGs from November 1, 2012, to December 31, 2021, at 10 Korean University Hospitals.

  • Data Collection: Data will be collected from patient records, including baseline demographics, comorbidities, laboratory findings, echocardiographic findings, hospitalizations, and related procedural outcomes, such as AF ablation and mortality.

  • Data Processing: De-identification of ECG data through data encryption and anonymization will be conducted, and the data will be analyzed using the AI algorithm previously developed for AF prediction.

  • Statistical Analysis:

    • AUROC: An area under the receiver operating characteristic curve will be created to test and validate the datasets and assess the AI-enabled ECGs acquired during the sinus rhythm to determine whether AF is present.

    • Kaplan–Meier Survival Functions: Will be used to estimate the time to hospitalization, AF-related procedure outcomes, and mortality, with log-rank tests to compare patients with low and high risk of AF by AI.

    • Cox Proportional Hazards Regression: A multivariate analysis will estimate the effect of AI-enhanced ECG multimorbidity on clinical outcomes after stratifying patients by AF probability by AI.

 

Discussion

This study will advance PAF prediction based on AI-enhanced ECGs.

  • Significance: This approach is a novel method for risk stratification and emphasizes shared decision-making for early detection and management of patients with newly diagnosed AF.

  • Future Impact: The results may revolutionize PAF management and unveil the wider potential of AI in predicting and managing cardiovascular diseases.

 

Ethics and Dissemination

  • Dissemination: The study findings will be published in peer-reviewed publications and disseminated at national and international conferences and through social media.

  • Ethics Approval: This study was approved by the institutional review boards of all participating university hospitals. Data extraction, storage, and management were approved by the data review committees of all institutions.

 

Clinical Trial Registration: [cris.nih.go.kr], identifier (KCT0007881)

목록