Deep learning for algorithmic detection of pulmonary hypertension using a combined digital stethoscope and single-lead electrocardiogram

使用组合数字听诊器和单导联心电图进行肺动脉高压算法检测的深度学习

• 批准号: 10705310
• 负责人: Gaurav Choudhary
• 金额: $ 110.58万
• 依托单位: EKO DEVICES, INC.
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-15 至 2025-08-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10705310
• 关键词: Address; Adult; Algorithms; Award; Cardiac; Cardiac Catheterization Procedures; Caring; Cellular Phone; Chest; Classification; Clinical; Complex; Data; Data Set; Databases; Detection; Diagnosis; Diagnostic; Disease; Early Diagnosis; Echocardiography; Eko; Electrocardiogram; Enrollment; Evaluation; Functional disorder; Goals; Health Services Accessibility; Hospitalization; Human Resources; Investigation; Label; Lead; Location; Marketing; Measures; Medical Device; Modality; Morbidity - disease rate; Outcome Study; Patient-Focused Outcomes; Patients; Performance; Personal Computers; Phase; Phenotype; Prognosis; Public Health; Pulmonary Hypertension; Quality-Adjusted Life Years; Randomized; Running; Screening procedure; Sensitivity and Specificity; Severities; Signal Transduction; Small Business Innovation Research Grant; Specificity; Stethoscopes; Stream; Symptoms; Tablet Computer; Testing; Time; Training; Validation; care costs; clinical decision support; cloud software; comorbidity; cost; deep learning; deep learning algorithm; design; digital; improved; innovation; mortality; novel; patient screening; point of care; pressure; prototype; pulmonary arterial pressure; research clinical testing; screening; support tools; trial comparing

Abstract This SBIR Direct to Phase II project will develop a deep learning-based clinical decision support algorithm for screening and detecting pulmonary hypertension (PH) using phonocardiogram and electrocardiogram data recording using the Eko DUO Digital Stethoscopes. The screening tool will help to decrease the number of patients with pulmonary hypertension that remain undertreated simply because their condition is not diagnosed. The gold standard diagnostic for pulmonary hypertension is right heart catheterization which is costly, invasive, and requires specialized personnel.To address these challenges, Eko developed the DUO, a digital stethoscope in a handheld form factor with built-in single lead electrocardiogram. The DUO is designed to stream digitized phonocardiograms and electrocardiograms to a smartphone, tablet or personal computer. There, the signal can be analyzed with the decision support algorithm we developed as part of this project. The specific aims of this study are : (1) build a database of matched ECG/PCG recording labeled against right heart catheterization and echocardiograms, and (2) develop and clinically test a deep learning algorithm that can detect PH and stratify its severity. By integrating this deep learning algorithm into Eko’s mobile and cloud software platform, we anticipate this algorithm will enable more accurate screening for pulmonary hypertension in adult patients, leading to earlier diagnosis and better patient outcomes.

抽象的 该 SBIR Direct 进入 II 期项目将开发基于深度学习的临床决策支持 使用心音图筛查和检测肺动脉高压（PH）的算法和 使用 Eko DUO 数字听诊器记录心电图数据。筛选工具 将有助于减少剩余肺动脉高压患者的数量 仅仅因为他们的病情没有得到诊断而得不到充分治疗。黄金标准诊断 肺动脉高压是一种昂贵的、侵入性的、需要右心导管检查的方法 为了应对这些挑战，Eko 开发了 DUO，这是一种数字 手持式听诊器，内置单导联心电图。双人组是 旨在将数字化心音图和心电图传输到智能手机、平板电脑 或个人电脑。在那里，可以使用我们的决策支持算法来分析信号 作为该项目的一部分开发。本研究的具体目标是：（1）建立数据库 匹配的 ECG/PCG 记录标记为右心导管插入术和超声心动图， (2) 开发并临床测试一种深度学习算法，该算法可以检测 PH 并对其进行分层 严重程度。通过将这种深度学习算法集成到 Eko 的移动和云软件中 平台，我们预计该算法将能够更准确地筛查肺部疾病 成人患者的高血压，从而实现早期诊断和更好的患者预后。