RAPID: Using Smartphones to detect and monitor respiratory symptoms in COVID-19 patients

该项目将开发、改进和评估一种基于智能手机的解决方案，以可靠地跟踪血氧饱和度(SpO2)以及呼吸频率和容量的变化。最近对新冠肺炎患者的分析显示了一些不同寻常的发现。例如，呼吸系统症状和血氧饱和度水平之间存在不一致。这可能会导致患者病情急剧恶化，而不会出现通常的痛苦迹象。现有的智能手机解决方案无法检测到血氧含量的显著下降，而血氧含量是检测患者是否需要住院的关键。对呼吸信号和血氧水平的准确家庭跟踪可以帮助监测和跟踪新冠肺炎患者，并区分哪些人是稳定的，哪些人正在恶化。该项目将使用智能手机实现两种信息丰富、可扩展且经济高效的测量：(I)SpO2和(Ii)呼吸频率和容量变化。虽然市场上有很多独立的脉搏血氧仪，它们都是FDA批准的，工作正常(准确度为±2%)，但大多数人没有它们，也不太可能购买特殊用途的设备。最近，已经有几款基于智能手机和智能手表的应用程序发布，声称可以测量血氧饱和度，但它们并不可靠。这些应用程序只需使用手机的摄像头来测量反射的变化。虽然这些应用程序可以可靠地捕捉脉搏，甚至在一定程度上捕捉血液中的血红蛋白浓度，但它对血氧饱和度并不起作用，因为没有单独的信号来比较有氧和无氧的血红蛋白。一般来说，脉搏血氧仪的工作原理是通过测量两个不同波长(红光：660 nm和近红外线：940 nm)下血红蛋白(经皮)的光吸收。这两个波段都可以在宽带白色LED中找到，例如用于智能手机闪光灯的LED，并且可以由图像传感器(相机)读取，因为它们使用红外在照片中进行距离测量。通过将滤光片连接到智能手机闪光灯上，这两个不同的波段可以从宽带信号源中分离出来，被手机的摄像头捕捉到，并用作脉搏血氧计。在监测呼吸信号/频率方面，该项目将建立在研究人员之前在阿片类药物过量检测方面的工作的基础上，该工作利用智能手机的扬声器和麦克风以非接触式方式监测人的胸部运动。在较高的水平上，智能手机使用设备的扬声器传输听不到的高频定制声音信号。这些信号由受试者的胸部反射，并使用设备的麦克风进行记录。如麦克风所见，呼吸引起的胸部运动会引起这些反射的变化。这些变化可以被检测到，并可以使用智能手机上的信号处理算法获得呼吸信号。该系统现在可以得到改进，以检测由于病毒感染和呼吸困难(如低氧)而引起的呼吸频率的变化。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This project will develop, refine, and evaluate a smartphone-based solution to reliably track changes in blood oxygen saturation (SpO2) and respiration rate and volume. Recent analysis of COVID-19 patients have shown some unusual findings. For example, there is a discordance between the respiratory symptoms and the blood oxygen saturation levels. This can lead to sharp deterioration of patient status without the individual experiencing the usual signs of distress. Existing smartphone solutions do not work in detecting significant drop in blood oxygenation, which is essential to detect whether the person needs to be hospitalized. Accurate in-home tracking of respiratory signals and blood oxygenation levels can help to monitor and follow patients with COVID-19 and identify those who are stable vs. those who are deteriorating.This project will enable two informative, scalable, and cost-effective measurements using smartphones: (i) SpO2 and (ii) respiration rate and volume changes. Although there are many standalone pulse oximeters on the market which are FDA approved and work well (accuracy of ±2%), most people don't have them and are unlikely to buy special purpose devices. Recently, several smartphone and smartwatch based apps have been released that claim to measure oxygen saturation, but they are not reliable. These applications simply use the phone's camera to measure the change in reflection. While these apps can capture pulse reliably, and even capture the blood hemoglobin concentration to some degree, it does not work for oxygen saturation as there are no separate signals to compare oxygenated against deoxygenated hemoglobin. In general, pulse oximetry works by measuring the light absorption in hemoglobin (transdermally) at two different wavelengths (red: 660nm and near-infrared: 940nm). Both of these bands can be found in broadband white LEDs, such as those used for flash on smartphones and can be read by the image sensors (cameras), as they use infrared for distance measurements in photographs. With optical filters attached to the smartphone flash, these two distinct bands can be separated out from the broadband source, captured by the phone's camera, and be used as a pulse oximeter. For monitoring respiration signal/rate, the project will build on the investigators' previous work on opioid overdose detection, which leverages the speakers and microphones of a smartphone to monitor the chest motion of a person in a contactless fashion. At a high level, the smartphone transmits inaudible high-frequency custom sound signals using the device's speaker. These signals are reflected by the subject's chest and recorded using the device's microphones. The chest motion due to breathing causes a change in these reflections as seen by the microphones. These changes can be detected and the respiration signal can be obtained using signal processing algorithms on the smartphone. This system can now be improved to detect changes in respiration rates caused due to the onset of viral infections and difficult breathing conditions like hypoxia.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.