COVID-19 (coronavirus disease 2019) pandemic caused by SARS-CoV-2 has led to a treacherous and devastating catastrophe for humanity. At the time of writing, no specific antivirus drugs or vaccines are recommended to control infection transmission and spread. The current diagnosis of COVID-19 is done by Reverse-Transcription Polymer Chain Reaction (RT-PCR) testing. However, this method is expensive, time-consuming, and not easily available in straitened regions. An interpretable and COVID-19 diagnosis AI framework is devised and developed based on the cough sounds features and symptoms metadata to overcome these limitations. The proposed framework's performance was evaluated using a medical dataset containing Symptoms and Demographic data of 30000 audio segments, 328 cough sounds from 150 patients with four cough classes ( COVID-19, Asthma, Bronchitis, and Healthy). Experiments' results show that the model captures the better and robust feature embedding to distinguish between COVID-19 patient coughs and several types of non-COVID-19 coughs with higher specificity and accuracy of 95.04 $\pm$ 0.18% and 96.83$\pm$ 0.18% respectively, all the while maintaining interpretability.
CoughTrigger: Earbuds IMU Based Cough Detection Activator Using An Energy-efficient Sensitivity-prioritized Time Series Classifier
Northwestern University(西北大学);Samsung Research America(三星美国研究院);Samsung Design Innovation Center(三星设计创新中心)
持续性咳嗽是泌尿系统相关疾病的主要症状。越来越多的研究关注使用可穿戴设备检测咳嗽,尤其是在COVID-19大流行期间。在所使用的所有类型的传感器中,麦克风最广泛地用于检测咳嗽。然而,处理音频信号所需的高功耗阻碍了在电池有限的商用可穿戴产品(例如耳塞)上进行连续的基于音频的咳嗽检测。我们提出了CoughTrigger,它利用耳塞中的低功耗传感器,惯性测量单元(IMU)作为咳嗽检测激活器,以触发用于音频处理和分类的高功率传感器。它能够以最小的电池消耗一直作为备用服务运行,并在从IMU检测到候选咳嗽时触发基于音频的咳嗽检测。此外,IMU的使用带来了改善咳嗽检测特异性的益处。在45名受试者上进行了实验,我们的基于IMU的模型在leave one subject out评价下获得了0.77的AUC得分。我们还验证了其在自由生活数据和设备上实施的有效性。
我们提出了一个基于深度学习的自动咳嗽分类器,可以区分结核病(TB)咳嗽与COVID-19咳嗽和健康咳嗽。结核病和COVID-19都是呼吸道疾病,具有传染性,咳嗽是主要症状,每年夺去数千人的生命。咳嗽音频记录是在室内和室外环境下收集的,并且还使用来自全球各地的受试者的智能手机上传,因此包含各种级别的噪音。该咳嗽数据包括来自47名TB患者、229名COVID-19患者和1498名健康患者的1.68小时的TB咳嗽、18.54分钟的COVID-19咳嗽和1.69小时的健康咳嗽,并用于训练和评估CNN、LSTM和Resnet 50。这三个深度架构也在2.14小时的喷嚏,2.91小时的语音和2.79小时的噪音上进行了预训练,以提高性能。通过使用SMOTE数据平衡技术和使用F1评分和AUC等性能指标来解决数据集中的类不平衡问题。我们的研究表明,对于两类(TB vs COVID-19)和三类(TB vs COVID-19 vs健康)咳嗽分类任务,预训练的Resnet 50分别实现了0.9259和0.8631的最高F1分数。深度迁移学习的应用提高了分类器的性能,并使它们更鲁棒,因为它们在交叉验证折叠上更好地泛化。其性能超过了世界卫生组织(WHO)制定的结核病分诊测试要求。产生最佳性能的特征包含更高阶的MFCC,这表明人耳无法感知TB和COVID-19咳嗽之间的差异。这种类型的咳嗽音频分类是非接触式的…
AI4COVID-19: AI Enabled Preliminary Diagnosis for COVID-19 from Cough Samples via an App
University of Oklahoma(俄克拉荷马大学);AI4Lyf LLC(AI4Lyf有限责任公司);Kharkiv National Medical University(哈尔科夫国立医科大学);Michigan State University(密歇根州立大学);Allergy, Asthma & Immunology Center PC(过敏、哮喘与免疫学中心PC)
Coswara: A website application enabling COVID-19 screening by analysing respiratory sound samples and health symptoms
Indian Institute of Science(印度科学学院);Ramaiah Medical College Hospital(拉马亚医学院医院);General Hospital, Hoskote(霍斯考特综合医院);PSG Institute of Medical Sciences and Research(PSG医学科学与研究院)
Coswara: A respiratory sounds and symptoms dataset for remote screening of SARS-CoV-2 infection
Indian Institute of Science(印度科学学院);Fraunhofer Institute of Integrated Circuits(弗劳恩霍夫集成电路研究所);Ramaiah Medical College Hospital(拉马亚医学院医院);General Hospital, Hoskote(霍斯科特综合医院);PSG Institute of Medical Sciences and Research(PSG医学科学与研究学院)
A large-scale and PCR-referenced vocal audio dataset for COVID-19
London Centre for Nanotechnology, University College London(伦敦纳米技术中心,伦敦大学学院);Division of Medicine, University College London(医学系,伦敦大学学院);King's College London, UK(伦敦国王学院);The Alan Turing Institute, UK(阿兰·图灵研究所);Imperial College London, UK(帝国理工学院);UK Health Security Agency, UK(英国卫生安全局);Institute of Health Informatics, University College London, UK(健康信息学研究所,伦敦大学学院);Centre for Stress and Age-Related Disease, School of Applied Sciences, University of Brighton, UK(布莱顿大学应用科学学院压力与年龄相关疾病中心);University of Oxford, UK(牛津大学);University of Surrey, UK(萨里大学);University of Lancaster, UK(兰卡斯特大学);University of Cambridge, UK(剑桥大学);University of Augsburg, Germany(奥格斯堡大学);University of Nottingham, UK(诺丁汉大学)
Telehealthcare and Telepathology in Pandemic: A Noninvasive, Low-Cost Micro-Invasive and Multimodal Real-Time Online Application for Early Diagnosis of COVID-19 Infection
University of Toronto(多伦多大学);Khulna University of Engineering and Technology(库尔纳工程技术大学);Islamic University of Technology(伊斯兰技术大学);Bangladesh University of Business and Technology(孟加拉国商业与技术大学)
COVID-19 diagnosis by routine blood tests using machine learning
Smart Blood Analytics Swiss SA(智能血液分析瑞士公司);Faculty of Computer and Information Science, University of Ljubljana(卢布尔雅那大学计算机与信息科学学院);Faculty of Chemistry and Chemical Technology, University of Ljubljana(卢布尔雅那大学化学与化学技术学院);University Medical Centre Ljubljana(卢布尔雅那大学医学中心)