Phono- and Electrocardiogram Assisted Detection of Valvular Disease
试验速览
- 阶段
- 不适用
- 状态
- 已完成
- 入组人数
- 156
- 试验地点
- 1
- 主要终点
- Differentiation of clinically significant aortic stenosis from structurally normal hearts
研究概览
简要总结
The diagnosis of valvular heart disease (VHD), or its absence, invariably requires cardiac imaging. A familiar and inexpensive tool to assist in the diagnosis or exclusion of significant VHD could both expedite access to life-saving therapies and reduce the need for costly testing. The FDA-approved Eko Duo device consists of a digital stethoscope and a single-lead electrocardiogram (ECG), which wirelessly pairs with the Eko Mobile application to allow for simultaneous recording and visualization of phono- and electrocardiograms. These features uniquely situate this device to accumulate large sets of auscultatory data on patients both with and without VHD.
In this study, the investigators seek to develop an automated system to identify VHD by phono- and electrocardiogram. Specifically, the investigators will attempt to develop machine learning algorithms to learn the phonocardiograms of patients with clinically important aortic stenosis (AS) or mitral regurgitation (MR), and then task the algorithms to identify subjects with clinically important VHD, as identified by a gold standard, from naïve phonocardiograms. The investigators anticipate that the study has the potential to revolutionize the diagnosis of VHD by providing a more accurate substitute to traditional auscultation.
详细描述
Phono- and Electrocardiogram Assisted Detection of Valvular Disease (PEA-Valve Study)
Specific aim(s) Aim 1: Can a machine learning algorithm derived from simultaneous phono- and electrocardiogram recordings reliably diagnose clinically important aortic stenosis?
Aim 2: Can a machine learning algorithm derived from simultaneous phono- and electrocardiogram recordings reliably diagnose clinically important mitral regurgitation?
Significance Valvular heart disease (VHD) is a common global health problem, with population-based studies showing a prevalence of 10% for aortic stenosis (AS) and 20% for mitral regurgitation (MR). New surgical and interventional advances allow for the treatment of patients at an older age or whose risk of intervention would previously have been untenable. Given that the incidence of both MR and AS increases with increasing age, there is a growing need to identify these conditions so as to offer disease-altering therapies.
In current clinical practice, the diagnosis of VHD relies heavily on echocardiography. This, in turn, requires both a referral from a provider with a clinical suspicion for VHD, typically from an abnormality on auscultation, as well as access to the echocardiogram itself. MR and AS both result in reliably reproducible auscultatory findings: holosystolic and systolic crescendo-decrescendo murmurs, respectively. Yet despite this, auscultation as a diagnostic tool is notoriously poor: its accuracy to detect MR and AS ranges only from 5-40%. These factors all lead to concerns for underdiagnosis of these increasingly treatable conditions.
研究设计
- 研究类型
- Observational
- 观察模型
- Case Control
- 时间视角
- Cross Sectional
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 是
入选标准
- •Able to provide consent
- •Undergoing a complete echocardiogram
排除标准
- •Refusal to participate
结局指标
主要结局
Differentiation of clinically significant aortic stenosis from structurally normal hearts
时间窗: Close of study (after final enrollment of the aortic stenosis validation set), within 1 year.
Identification by the trained machine learning algorithm of clinically important aortic stenosis (defined as moderate-to-severe or greater) from control subjects with structurally normal hearts and no greater than mild valvular heart disease, with comparison to the gold standard echocardiogram interpretation. As our algorithm will provide a continuous "score" to determine the likelihood of disease, the data will primarily come in the form of a receiver operating characteristic curve, for which we will calculate accuracy, specificity, and likelihood ratios at sensitivity cutoffs of 0.9, 0.95, and 0.99.
Differentiation of clinically significant mitral stenosis from structurally normal hearts
时间窗: Close of study (after final enrollment of the mitral regurgitation validation set), within 1 year.
Identification by the trained machine learning algorithm of clinically important mitral regurgitation (defined as moderate-to-severe or greater) from control subjects with structurally normal hearts and no greater than mild valvular heart disease, with comparison to the gold standard echocardiogram interpretation. As our algorithm will provide a continuous "score" to determine the likelihood of disease, the data will primarily come in the form of a receiver operating characteristic curve, for which we will calculate accuracy, specificity, and likelihood ratios at sensitivity cutoffs of 0.9, 0.95, and 0.99..
次要结局
- Differentiation of clinically significant aortic stenosis from the absence of clinically significant aortic stenosis(Close of study (after final enrollment of the aortic stenosis validation set), within 1 year.)
- Differentiation of clinically significant mitral regurgitation from the absence of clinically significant mitral regurgitation(Close of study (after final enrollment of the mitral regurgitation validation set), within 1 year.)