PFI-TT: Remote Respiratory Diagnostics through Visualization of Exhale Flow

PFI-TT：通过呼气流量可视化进行远程呼吸诊断

• 批准号: 1941221
• 负责人: Min-Hyung Choi
• 金额: $ 25万
• 依托单位: University of Colorado at Denver-Downtown Campus
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-06-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1941221&HistoricalAwards=false
• 关键词: PFI; TT; Remote; Respiratory; Diagnostics

The broader impact/commercial potential of this Partnerships for Innovation – Technology Translation (PFI-TT) project is to enable the accurate detection of abnormal respiratory behaviors and breathing disorders through visualized exhale flow behaviors. Early and accurate detection of declines in pulmonary function through respiratory monitoring plays a vital role in the mitigation of serious health consequences caused by pulmonary diseases. For millions of Americans, these complications include decreased cognitive function, increased cardiovascular risk, as well as permanent disabilities including irreversible lung damage. These health conditions can be caused by a wide variety of pulmonological complications resulting from: Sleep-Disordered Breathing (SDB), Ear-Nose-Throat (ENT)-related conditions, and early-stage lung damage due to Chronic Obstructed Pulmonary Disease (COPD). The objective of this innovation is to broaden our understanding of natural, unconstrained breathing behaviors that can be used to identify abnormalities due to numerous pulmonary conditions and diseases. This project proposes to develop the first optical-based breathing diagnostic tool for pulmonologists that enables new diagnostic pulmonary evaluations. Through analysis of visualized flow behaviors, this technology enables a new form of non-contact analysis that can be used to: increase patient populations including children and infants, improve diagnostic outcomes, and promote preventative care solutions for pulmonologists. The proposed project incorporates the development, design, implementation, and validation of an integrated hardware-software diagnostic prototype facilitating visual, quantitative, and qualitative analysis of expiratory breathing behaviors. The underlying technology provides a unique approach to extracting physical measurements from visual data through the use of filtered thermal and depth imaging combined with data-driven fluid flow models. This approach includes a multifaceted design that integrates analytical, numerical, and machine learning methods to provide an inverse modeling approach for measuring respiratory behaviors. Key contributions of this research include: (1) accurate evaluation of pulmonary function based on visualized exhale behaviors providing quantitative measurements for flow, volume, exhale strength, and natural nose-mouth breathing distributions and (2) the development of a functional prototype that provides real-time visualization of expiratory breathing behaviors, continuous monitoring, and diagnostics. The realization of this innovation allows pulmonologists to break away from the current set of tube-based and wearable devices that require effort-based tests that are inconsistent, tedious, and uncomfortable for use in any extended duration. By introducing this new direction in how we monitor, measure, and evaluate pulmonary function, the proposed work strives to create a pivotal shift in the technological evaluation of natural breathing.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该创新-技术转化合作伙伴关系（PFI-TT）项目的更广泛影响/商业潜力是通过可视化呼气流量行为准确检测异常呼吸行为和呼吸障碍。通过呼吸监测早期准确检测肺功能下降在减轻肺部疾病引起的严重健康后果方面起着至关重要的作用。对于数百万美国人来说，这些并发症包括认知功能下降，心血管风险增加，以及永久性残疾，包括不可逆的肺损伤。这些健康状况可能由多种肺部并发症引起：睡眠呼吸障碍（SDB），耳鼻咽喉（ENT）相关疾病和慢性阻塞性肺疾病（COPD）引起的早期肺损伤。这项创新的目的是拓宽我们对自然、不受约束的呼吸行为的理解，这些呼吸行为可用于识别由于许多肺部疾病和疾病引起的异常。该项目旨在为肺病学家开发第一个基于光学的呼吸诊断工具，以实现新的诊断肺部评估。通过分析可视化的血流行为，该技术实现了一种新形式的非接触式分析，可用于：增加包括儿童和婴儿在内的患者人群，改善诊断结果，并为肺病学家推广预防性护理解决方案。拟议的项目包括一个集成的硬件-软件诊断原型的开发，设计，实施和验证，促进呼气呼吸行为的视觉，定量和定性分析。基础技术提供了一种独特的方法，通过使用过滤的热和深度成像结合数据驱动的流体流动模型，从视觉数据中提取物理测量。该方法包括多方面的设计，其集成了分析、数值和机器学习方法，以提供用于测量呼吸行为的逆向建模方法。本研究的主要贡献包括：（1）基于可视化呼气行为的肺功能准确评估，提供流量、容量、呼气强度和自然口鼻呼吸分布的定量测量;（2）开发功能原型，提供呼气呼吸行为的实时可视化、连续监测和诊断。这一创新的实现允许肺科医生摆脱当前的一套基于管和可穿戴设备，这些设备需要基于努力的测试，这些测试在任何延长的持续时间内都是不一致的、乏味的和不舒服的。 通过在我们如何监测、测量和评估肺功能方面引入这一新方向，拟议的工作努力在自然呼吸的技术评估方面创造关键转变。该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的知识价值和更广泛的影响审查标准进行评估来支持。