一个基于心电图的可概括的人工智能模型,用于10年心力衰竭风险预测
Liam Butler1, Ibrahim Karabayir1, Dalane W Kitzman1
1Epidemiological Cardiology Research Center, Section on Cardiovascular Medicine, Department of Medicine, Wake Forest School of Medicine, Winston-Salem, North Carolina.
Cardiovascular digital health journal
|January 15, 2024
概括
使用心电图 (ECG) 的人工智能 (AI) 模型可以预测心力衰竭 (HF) 风险. 一个ECG-AI-Cox模型在预测HFpEF和HFrEF亚型方面表现出卓越的性能.
科学领域:
- 心脏病学 心脏病学
- 人工智能的人工智能
- 医学诊断 医学诊断 医学诊断
背景情况:
- 心力衰竭 (HF) 是一个全球性的健康问题,有两个主要亚型:HFpEF和HFrEF.
- 早期风险预测和修改对于管理HF进展至关重要.
- 需要可访问的,人工智能驱动的工具来进行早期高频风险评估.
研究的目的:
- 通过使用多民族动脉样硬化研究 (MESA) 数据,验证人工智能 (AI) 模型对心力衰竭 (HF) 风险预测.
- 评估各种模型的性能,包括ECG-AI,对HFpEF和HFrEF进行分类.
- 将基于AI的模型的预测准确度与传统的临床风险计算器进行比较.
主要方法:
- 六个模型进行了比较:一个ECG-AI模型 (卷积神经网络),临床模型 (ARIC-HF,FHS-HF),Cox比例危险 (CPH) 模型 (CPH,ECG-AI-Cox) 和一个ECG特征 (ECG-Chars) 模型.
- 模型使用ARIC数据进行训练,并根据MESA数据进行验证.
- 使用接收器操作特征曲线 (AUC) 下的面积来评估性能,并通过DeLong测试进行比较.
主要成果:
- 该ECG-AI-Cox模型实现了最高的验证AUC (0.84),优于其他模型.
- 具体的AUC为:ECG-AI (0.77),ECG-Chars (0.73),ARIC-HF (0.76),FHS-HF (0.74),CPH (0.78) 等,这些AUC均为:ECG-AI (0.77),ECG-Chars (0.73),ARIC-HF (0.76),FHS-HF (0.74),CPH (0.78) 等,这些AUC均为:ECG-AI (0.77),ECG-Chars (0.73),ARIC-HF (0.76),ARIC-HF (0.76) 等,这些AUC均为:
- 在对HFrEF (AUC=0.85) 和HFpEF (AUC=0.83) 的分类中,ECG-AI-Cox显示出强的表现.
结论:
- 使用心电图数据的AI模型比传统的高频风险计算器提供更优质的验证预测.
- 电图-AI方法,特别是ECG-AI-Cox模型,有效地预测HF风险,并有助于HFpEF和HFrEF分类.
- 这些发现支持使用人工智能驱动的心电图分析来早期和准确地检测心力衰竭.
相关概念视频
Pathophysiology of Heart Failure
1.6K
Heart failure (HF) is a progressive syndrome involving ventricles that leads to inadequate cardiac output. It can be classified based on location and output or ejection fraction. Ejection fraction (EF) is an essential measurement in the diagnosis and surveillance of HF. Reduced EF corresponds to systolic heart failure (HFrEF). However, HF with preserved ejection fraction (HFpEF) is becoming increasingly prevalent. Also known as diastolic HF, this form of HF is related to aging. The...
1.6K
Electrocardiogram
2.3K
An electrocardiogram (ECG or EKG) is a critical diagnostic tool that records the electrical signals produced by the heart during each heartbeat. This recording is achieved through electrodes placed strategically on the arms, legs, and chest. The electrocardiograph amplifies these signals and produces 12 distinct tracings, offering a comprehensive understanding of the heart's electrical activity.
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and...
2.3K


