Arrhythmia Detection Using a Smart Phone

描述（由申请人提供）：心房颤动（AF）是世界范围内最常见的持续性心律失常。尽管在过去的十年中出现了新的房颤治疗策略，但临床医生和研究人员面临的主要挑战是房颤的阵发性，通常是短暂的，并且经常无症状的性质。鉴于阵发性和无症状房颤是一个日益严重的临床和公共卫生问题，需要更好，更便宜，更容易获得的房颤检测技术。因此，迫切需要开发易于使用的监测设备以及准确的房颤检测算法，以改善患者护理并降低与治疗这些心律失常及其并发症相关的医疗费用。为此，我们先前开发了敏感的，实时可实现的算法，用于使用市售的，临床适用的心电图记录进行准确的AF检测。我们还对算法进行了改进，使其可以检测短至12次心跳的AF发作。此外，我们最近开发了一款智能手机应用程序来测量心脏间隔系列，可用于实时检测AF。鉴于智能手机的日益普及，我们使用智能手机检测房颤的方法将使患者和医疗保健提供者有机会在医生办公室和患者家中以外的各种条件下监测房颤。由于我们的方法不涉及单独的心电传感器，而是只使用标准的智能手机硬件，因此具有成本效益，从而使患者更好地接受和使用。我们的房颤移动健康检测平台有可能显著改变传统的房颤医疗服务，允许更频繁、快速和以患者为导向的房颤检测。我们的AF原型使用2分钟的iPhone 4s记录，在马萨诸塞州大学医学中心心脏电生理实验室接受电治疗的76名已知持续性AF患者中，其灵敏度为99%，特异性为97%。虽然我们的算法对于房颤检测具有鲁棒性，但主要的限制是它不是设计用于区分室性早搏（PVC）和房性早搏（PAC）与房颤。因此，本R15项目的目标是增强我们的实时可实现的房颤算法，以准确检测和区分正常窦性心律、房颤、室性早搏和房颤；尚未可用的功能。我们相信这项研究将导致快速转化为创新的房颤检测解决方案，从而更有效地监测和诊断房颤。最后，提出的工作有可能显著降低医疗成本，并通过在高危人群中准确、快速地建立房颤诊断来加强患者护理，从而为临床医生提供预防这些危及生命的心律失常的继发并发症的机会。

DESCRIPTION (provided by applicant): Atrial Fibrillation (AF) is the most common sustained dysrhythmia worldwide. Although new AF treatment strategies have emerged over the last decade, a major challenge facing clinicians and researchers is the paroxysmal, often short-lived, and frequently asymptomatic nature of AF. Given that paroxysmal and asymptomatic AF is a growing clinical and public health problem, better, cheaper, and more readily available AF detection technology is needed. There is, therefore, a pressing need to develop methods for readily-accessible monitoring device as well as an accurate AF detection algorithm in order to improve patient care and reduce healthcare costs associated with treating these arrhythmias and their complications. To this end, we have previously developed sensitive, real-time realizable algorithm for accurate AF detection using commercially available, clinically applicable electrocardiographic recordings. We have also made improvement to the algorithm so that it can detect AF episode that is as short as 12 beats. Further, we have recently developed a smart phone application to measure heart interval series which can be used to detect AF in real time. Given the ever-growing popularity of smart phones, our approach to AF detection using a smart phone will give patients as well as health care providers the opportunity to monitor AF under a wide variety of conditions outside of the physician's office and outside of the patient's home. Because our approach does not involve a separate ECG sensor but instead uses only standard smart phone hardware, it is cost-effective, thereby leading to better acceptance and use by patients. Our mobile health for AF detection platform has the potential to markedly change the traditional delivery of AF healthcare, allowing for more frequent, rapid, and patient-directed AF detection. Our AF prototype using 2 minutes of iPhone 4s recordings has demonstrated a sensitivity of 99% and specificity of 97% on 76 subjects with known persistent AF who underwent electrical at the University of Massachusetts Medical Center Cardiac Electrophysiology Laboratory. Although our algorithm is robust for AF detection, a major limitation is that it is not designed to discriminate premature ventricular contractions (PVC) and premature atrial contractions (PAC) from AF. Hence, the objective of this R15 project is to enhance our real-time realizable AF algorithm for accurate detection of, and discrimination between, normal sinus rhythm, AF, PVCs, and PACs; capabilities that are not yet available. We believe this research will result in rapid translation into innovative AF detection solutions, leading to more effective monitoring and diagnosis of AF. Finally, the proposed work has the potential to significantly reduce healthcare costs and enhance patient care by accurately and rapidly establishing the diagnosis of AF in at-risk groups, thereby providing clinicians with an opportunity to prevent secondary complications of these life-threatening arrhythmias.