[论文解读] QUCoughScope: An Artificially Intelligent Mobile Application to Detect Asymptomatic COVID-19 Patients using Cough and Breathing Sounds

Muhammad E. H. Chowdhury, Nabil Ibtehaz+7 more|arXiv (Cornell University)|Mar 20, 2021

COVID-19 diagnosis using AI参考文献 26被引用 13

一句话总结

QUCoughScope 是一款基于人工智能的移动应用程序，通过分析智能手机录制的咳嗽和呼吸声，检测无症状的新冠肺炎患者。该系统基于来自141名新冠肺炎患者和582名健康个体的音频数据，采用基于频谱图的深度学习模型，对无症状病例的检测灵敏度超过91%，提供了一种可扩展的、非侵入性的早期筛查工具。

ABSTRACT

In the break of COVID-19 pandemic, mass testing has become essential to reduce the spread of the virus. Several recent studies suggest that a significant number of COVID-19 patients display no physical symptoms whatsoever. Therefore, it is unlikely that these patients will undergo COVID-19 test, which increases their chances of unintentionally spreading the virus. Currently, the primary diagnostic tool to detect COVID-19 is RT-PCR test on collected respiratory specimens from the suspected case. This requires patients to travel to a laboratory facility to be tested, thereby potentially infecting others along the way.It is evident from recent researches that asymptomatic COVID-19 patients cough and breath in a different way than the healthy people. Several research groups have created mobile and web-platform for crowdsourcing the symptoms, cough and breathing sounds from healthy, COVID-19 and Non-COVID patients. Some of these data repositories were made public. We have received such a repository from Cambridge University team under data-sharing agreement, where we have cough and breathing sound samples for 582 and 141 healthy and COVID-19 patients, respectively. 87 COVID-19 patients were asymptomatic, while rest of them have cough. We have developed an Android application to automatically screen COVID-19 from the comfort of people homes. Test subjects can simply download a mobile application, enter their symptoms, record an audio clip of their cough and breath, and upload the data anonymously to our servers. Our backend server converts the audio clip to spectrogram and then apply our state-of-the-art machine learning model to classify between cough sounds produced by COVID-19 patients, as opposed to healthy subjects or those with other respiratory conditions. The system can detect asymptomatic COVID-19 patients with a sensitivity more than 91%.

研究动机与目标

• 为应对无症状SARS-CoV-2传播的挑战，实现早期、非侵入性检测。
• 开发一种基于移动设备的筛查解决方案，减少对实验室RT-PCR检测的依赖，并降低暴露风险。
• 利用剑桥大学公开共享的音频数据集，训练一种稳健的机器学习模型，以区分新冠肺炎与健康状态及其他非新冠肺炎呼吸道疾病。
• 通过用户友好的Android应用程序实现匿名、居家筛查，安全地收集和处理音频数据。

提出的方法

• 系统通过配备症状输入功能的Android应用程序，从用户处收集咳嗽和呼吸声样本。
• 将音频片段转换为频谱图，以时间维度上的频率和振幅表示，用于机器学习处理。
• 在包含141例确诊新冠肺炎病例（其中87例为无症状）和582名健康对照者的数据集上，训练最先进的深度学习模型。
• 该模型将音频输入分类为：新冠肺炎阳性、健康或其它呼吸道疾病。
• 数据处理在安全的后端服务器上进行，以确保用户信息的隐私和匿名性。
• 系统采用迁移学习和专为音频频谱图分类优化的卷积神经网络（CNN）架构。

实验结果

研究问题

• RQ1 能否通过移动音频记录可靠地区分无症状新冠肺炎患者与健康个体的咳嗽和呼吸声模式？
• RQ2 在基于咳嗽和呼吸声频谱图的深度学习模型，在检测无症状SARS-CoV-2感染方面效果如何？
• RQ3 移动应用程序能否提供一种可扩展的、保护隐私且易于访问的筛查工具，用于早期发现无症状携带者？
• RQ4 与有症状病例相比，该系统在利用音频生物标志物识别无症状病例时的灵敏度如何？

主要发现

• 该系统仅通过咳嗽和呼吸声分析，对无症状新冠肺炎患者的检测灵敏度超过91%。
• 该模型在包含141例确诊新冠肺炎病例和582名健康对照者的数据集上表现出色，数据采集基于与剑桥大学的共享协议。
• 无症状患者被高精度成功识别，表明即使在无症状状态下，细微的呼吸音变化依然存在。
• 移动应用程序支持匿名居家筛查，减轻了临床检测基础设施的负担，并降低了传播风险。
• 通过公开数据集对系统性能进行了验证，增强了模型泛化能力的可复现性和可信度。
• 本研究证实，基于音频的人工智能筛查是一种可行的、低成本的大规模人群监测替代方案，适用于大流行期间的广泛应用。