Dialysis access monitoring using a digital stethoscope-based deep learning system

使用基于数字听诊器的深度学习系统进行透析访问监控

• 批准号: 10255460
• 负责人: PRABIR ROY-CHAUDHURY
• 金额: $ 29.94万
• 依托单位: EKO DEVICES, INC.
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-06-15 至 2024-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10255460
• 关键词: Academic Medical Centers; Algorithms; Arteriovenous fistula; Artificial Intelligence; Auscultation; Blood Vessels; Blood flow; Bluetooth; Caring; Cellular Phone; Classification; Clinic; Collection; Data; Data Set; Databases; Detection; Dialysis procedure; Distal; Early Intervention; Educational process of instructing; Eko; End stage renal failure; Enrollment; Ensure; Failure; Fistula; Goals; Health; Healthcare Systems; Heart Sounds; Hemodialysis; Home; Internet; Intervention; Interventional radiology; Lead; Legal patent; Life Expectancy; Liquid substance; Location; Maintenance; Measurement; Medicare; Meta-Analysis; Modeling; Monitor; Nephrology; Network-based; Neural Network Simulation; Observational Study; Operative Surgical Procedures; Outcome; Patients; Performance; Personal Computers; Phase; Physical Examination; Positioning Attribute; Procedures; Quality of life; Renal Replacement Therapy; Research Design; Small Business Innovation Research Grant; Standardization; Stenosis; Stethoscopes; Study Subject; Survival Rate; System; Tablet Computer; Time; Training; Transplantation; Ultrasonography; Validation; algorithm training; analog; arteriovenous graft; base; clinical database; clinical decision support; clinically relevant; cloud based; cloud software; commercialization; convolutional neural network; cost; data streams; deep learning; deep learning algorithm; deep neural network; digital; evaluation/testing; experience; follow-up; improved; innovation; insight; patient home care; premature; recruit; skills; sound; standard of care; supervised learning; systematic review; tool

This SBIR Phase I project will develop a deep learning-based algorithm to analyze the sound of blood flow in newly created arteriovenous fistulas (AVFs) used for hemodialysis access. This monitoring tool can help to identify fistulas that are unlikely to mature in patients who need surgical intervention to achieve successful maturation. The specific aims of the study are (1) to create the world’s first deep learning-scale database of newly created AVF sounds from hemodialysis patients, and (2) develop and evaluate the performance of a deep learning classification model trained via semi-supervised learning to discriminate between patients with AVFs likely to mature and patients with AVFs unlikely to mature. By integrating this deep learning algorithm into Eko’s mobile and cloud software platform, we anticipate this algorithm will enable better monitoring of the maturation process for newly created fistulas. During Phase I of the project, we will recruit study subjects in access centers at the University of North Carolina (UNC).

该SBIR第一期项目将开发一种基于深度学习的算法来分析血液的声音 用于血液透析通路的新创建的动静脉瘘 (AVF) 中的血流。 可以帮助识别需要手术干预的患者中不太可能成熟的瘘管 该研究的具体目标是（1）创建世界上第一个深度。 来自血液透析患者的新创建的 AVF 声音的学习规模数据库，以及 (2) 开发和 评估通过半监督学习训练的深度学习分类模型的性能 区分可能成熟的 AVF 患者和不太可能成熟的 AVF 患者。 通过将这种深度学习算法集成到 Eko 的移动和云软件平台中，我们预计该算法将能够更好地监测新创建的瘘管的成熟过程。在该项目的第一阶段，我们将在北方大学的访问中心招募研究对象。卡罗来纳州（北卡罗来纳大学）。