Predicting Short- and Long-term Future Occurrence of Atrial Fibrillation from Single-Lead ECG in Normal Sinus Rhythm with an Explainable Deep Learning Model.

使用可解释的深度学习模型，根据正常窦性心律的单导联心电图预测未来短期和长期房颤的发生。

• 批准号: 10441204
• 负责人: Giorgio Quer
• 金额: $ 22.19万
• 依托单位: SCRIPPS RESEARCH INSTITUTE, THE
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-01 至 2024-03-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10441204
• 关键词: Address; Algorithms; Anticoagulants; Atrial Fibrillation; Clinical; Clinical Data; Clinical Trials; Collaborations; Data; Data Science; Data Set; Devices; Diagnosis; Diagnostic; EKG P Wave; Early Diagnosis; Early identification; Elderly; Electrocardiogram; Event; Future; Goals; Health; Health Technology; Home; Hour; Individual; Ischemic Stroke; Lead; Learning; Left; Measures; Methods; Monitor; Outcome; Participant; Persons; Photoplethysmography; Play; Population; Preventive therapy; Probability; Prospective Studies; Research Personnel; Retrospective Studies; Risk; Role; Series; Signal Transduction; Sinus; Stroke; Techniques; Technology; Time; Validation; Work; base; clinically relevant; cohort; comorbidity; cost; deep learning; deep learning model; design; diagnostic accuracy; digital health; follow-up; high risk; improved; learning strategy; mortality; novel; novel strategies; prospective; screening; smart watch; stroke risk; tool; uptake; wearable sensor technology

Project Summary/Abstract More than 30 million individuals worldwide are diagnosed with atrial fibrillation (AF), however, another 13% of individuals with AF are left undiagnosed. People with AF have a five-fold increased risk of stroke with up to one-third of all strokes shown to be related to AF. Timely administration of appropriate preventative therapies, especially anticoagulants, can significantly decrease the complications of AF, including strokes, by 65% and mortality by 30%. Digital health technologies offer new approaches to identify individuals with undiagnosed AF, in particular paroxysmal AF (PAF), characterized by occasional episodes of limited duration, for whom a 10-second 12-lead electrocardiography (ECG) performed in the clinical setting is unlikely to overlap with an AF event. Continuous monitoring is promising, but still costly and burdensome for elderly individuals, who are at higher risk. To maximize the diagnostic yield of these technologies, we propose novel methods to predict the future occurrence of AF from a single-lead ECG during normal sinus rhythm. Only recently it was shown that it is possible to predict the future occurrence of AF from 12-lead ECGs in normal sinus rhythm collected in a clinical setting. Here, we propose to predict the occurrence of AF with commercially available single- lead ECG devices, which will enable a scalable alternative for early detection in a non-clinical setting. To achieve this goal, we will analyze retrospectively the raw single-lead ECG data of 10,000+ individuals with PAF over 14 days of monitoring. Validation work will then be carried out in a unique set of 1,718 asymptomatic individuals who participated in the prospective mSToPS clinical trial of AF screening (mean age 73), with full clinical information and co-morbidities. The three aims of this project are: 1. Compute the probability of a future AF event in the short-term for an individual in normal sinus rhythm using classic single-lead ECG features and representation learning based features. 2. Develop a method for long-term prediction of AF onset by evaluating individuals with AF detected in 1, 3, 6 and 12 months from the initial monitored period of normal sinus rhythm and by validating the algorithms using the mSToPS dataset with 3 years of clinical follow-up and annotated co-morbidities. 3. Develop a technique to provide a preliminary interpretation of representation learning features for time-series data applied to the short- and long-term prediction. This retrospective study will develop and optimize new predictive techniques from single-lead ECGs, available through consumer devices, with the goal of identifying individuals at high risk of developing AF. A future direction to build on from this study's results would include a prospective study of AF prediction using consumer single-lead ECG to improve clinical outcomes.

项目概要/摘要 全球有超过 3000 万人被诊断患有心房颤动 (AF)，然而，另一个 13% 的 AF 患者未被诊断出来。患有房颤的人中风的风险增加五倍 多达三分之一的中风与房颤有关。及时给予适当的 预防性治疗，尤其是抗凝剂，可以显着减少房颤并发症， 包括中风，死亡率降低 65%，死亡率降低 30%。 数字健康技术提供了识别未确诊房颤患者的新方法，特别是 阵发性 AF (PAF)，其特点是在有限的时间内偶尔发作，对于这些患者来说，需要 10 秒的时间 在临床环境中进行的 12 导联心电图 (ECG) 不太可能与 AF 事件重叠。 持续监测是有希望的，但对于老年人来说仍然成本高昂且负担重。 风险较高。 为了最大限度地提高这些技术的诊断率，我们提出了预测未来的新方法 正常窦性心律期间单导联心电图发生房颤。直到最近才表明，它 可以通过收集的正常窦性心律的 12 导联心电图来预测未来 AF 的发生 临床环境。在这里，我们建议用市售的单片机来预测 AF 的发生 领先的心电图设备，这将为非临床环境中的早期检测提供可扩展的替代方案。 为了实现这一目标，我们将回顾性分析 10,000 多名个体的原始单导联心电图数据 使用 PAF 进行超过 14 天的监测。然后验证工作将在一组独特的 1,718 参加房颤筛查前瞻性 mSTOPS 临床试验的无症状个体（平均 73 岁），具有完整的临床信息和合并症。该项目的三个目标是： 1. 计算正常窦性心律的个体未来短期内发生 AF 事件的概率 使用经典的单导联心电图特征和基于表示学习的特征。 2. 通过评估在 自正常窦性心律初始监测期起 1、3、6 和 12 个月，并通过验证 使用 mSTOPS 数据集的算法，进行了 3 年的临床随访并注释了合并症。 3. 开发一种技术来提供表征学习特征的初步解释 应用于短期和长期预测的时间序列数据。 这项回顾性研究将开发和优化单导联心电图的新预测技术， 通过消费设备提供，目的是识别患有 AF 高风险的个体。 以这项研究结果为基础的未来方向将包括房颤预测的前瞻性研究 使用消费者单导联心电图来改善临床结果。