Diagnosis of COVID-19 via acoustic analysis and artificial intelligence by monitoring breath sounds on smartphones

Chen, Zhiang; Li, Muyun; Wang, Ruoyu; Sun, Wenzhuo; Liu, Jiayi; Li, Haiyang; Wang, Tianxin; Lian, Yuan; Zhang, Jiaqian; Wang, Xinheng

doi:10.1016/j.jbi.2022.104078

Cited by 17 publications

(12 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the results as per accuracy are not too high. In another study [14], Covid-19 infection was diagnosed using KNN and CNN machine learning models using acoustic analysis of breath sounds. The dataset, the authors used consists of 107 Covid-19 positive patients, 1107 healthy controls, and 48 patients with other respiratory diseases.…”

Section: Machine Learning Model-wise Comparison Of the Resultsmentioning

confidence: 99%

See 1 more Smart Citation

The IOMT-Based Risk-Free Approach to Lung Disorders Detection from Exhaled Breath Examination

Ghani¹,

Gilanie²

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

The lungs are the main fundamental part of the human respiratory system and are among the major organs of the human body. Lung disorders, including Coronavirus , are among the world's deadliest and most life-threatening diseases. Early and social distance-based detection and treatment can save lives as well as protect the rest of humanity. Even though X-rays or Computed Tomography (CT) scans are the imaging techniques to analyze lungrelated disorders, medical practitioners still find it challenging to analyze and identify lung cancer from scanned images. unless COVID-19 reaches the lungs, it is unable to be diagnosed. through these modalities. So, the Internet of Medical Things (IoMT) and machine learning-based computer-assisted approaches have been developed and applied to automate these diagnostic procedures. This study also aims at investigating an automated approach for the detection of COVID-19 and lung disorders other than COVID-19 infection in a non-invasive manner at their early stages through the analysis of human breath. Human breath contains several volatile organic compounds, i.e., water vapor (5.0%-6.3%), nitrogen (79%), oxygen (13.6%-16.0%), carbon dioxide (4.0%-5.3%), argon (1%), hydrogen (1 ppm) (parts per million), carbon monoxide (1%), proteins (1%), isoprene (1%), acetone (1%), and ammonia (1%). Beyond these limits, the presence of a certain volatile organic compound (VOC) may indicate a disease. The proposed research not only aims to increase the accuracy of lung disorder detection from breath analysis but also to deploy the model in a real-time environment as a home appliance. Different sensors detect VOC; microcontrollers and machine learning models have been used to detect these lung disorders. Overall, the suggested methodology is accurate, efficient, and non-invasive. The proposed method obtained an accuracy of 93.59%, a sensitivity of 89.59%, a specificity of 94.87%, and an AUC-Value of 0.96.

show abstract

Section: Machine Learning Model-wise Comparison Of the Resultsmentioning

confidence: 99%

“…In this paper [14], the authors performed an acoustic analysis of breath sounds for the diagnosis of the infection of Covid-19. They used the Coswara dataset, which is a freely accessible dataset of breath sounds used for research and experiments.…”

Section: Literature Reviewmentioning

confidence: 99%

The IOMT-Based Risk-Free Approach to Lung Disorders Detection from Exhaled Breath Examination

Ghani¹,

Gilanie²

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

show abstract

“…20 Audio-based technologies using cough sounds have also been deployed on a smartphone app for COVID-19 detection. 21,22,23,24,25 Additionally, COVID-19 patients have unique time and frequency domain patterns in breath sounds that may empower CNN models. 26 In a dynamic pandemic such as COVID-19, crowdsourced datasets allow for continuous and focused sample collection.…”

Section: Ai For Covid-19 Testingmentioning

confidence: 99%

“…A CNN-based model trained on forced-cough recordings in limited numbers of patients with and without COVID-19 was able to recognize COVID-19 with high sensitivity, even in otherwise asymptomatic subjects 18 . Audio-based technologies using cough sounds have also been deployed on a smartphone app for COVID-19 detection 19,20,21,22,23 . A binary classifier was able to differentiate COVID-19 speech from normal speech based on scripted telephone data 24 .…”

Section: Related Workmentioning

confidence: 99%

“…YouTube audio, visual, and search-history data have also successfully detected mental illnesses including depression and OCD 18 . Audio-based technologies using cough sounds have also been deployed on a smartphone app for COVID-19 detection 19,20,21,22,23 . A binary classifier was able to differentiate COVID-19 speech from normal speech based on scripted telephone data 24 .…”

Section: Social Media Data For Clinical Tasksmentioning

confidence: 99%

See 1 more Smart Citation

Omicron detection with large language models and YouTube audio data

Anibal

Landa

Nguyen

et al. 2022

Preprint

View full text Add to dashboard Cite

Social media data can boost artificial intelligence (AI) systems designed for clinical applications by expanding data sources that are otherwise limited in size. Currently, deep learning methods applied to large social media datasets are used for a variety of biomedical tasks, including forecasting the onset of mental illness and detecting outbreaks of new diseases. However, exploration of online data as a training component for diagnostics tools remains rare, despite the deluge of information that is available through various APIs. In this study, data from YouTube was used to train a model to detect the Omicron variants of SARS-CoV-2 from changes in the human voice. According to the ZOE Health Study, laryngitis and hoarse voice were among the most common symptoms of the Omicron variant, regardless of vaccination status.1 Omicron is characterized by pre-symptomatic transmission as well as mild or absent symptoms. Therefore, impactful screening methodologies may benefit from speed, convenience, and non-invasive ergonomics. We mined YouTube to collect voice data from individuals with self-declared positive COVID-19 tests during time periods where the Omicron variant (or sub-variants, including BA.4/5) consisted of more than 95% of cases.2,3,4 Our dataset contained 183 distinct Omicron samples (28.39 hours), 192 healthy samples (33.90 hours), 138 samples from other upper respiratory infections (8.09 hours), and 133 samples from non-Omicron variants of COVID-19 (22.84 hours). We used a flexible data collection protocol and implemented a simple augmentation strategy that leveraged intra-sample variance arising from the diversity of unscripted speech (different words, phrases, and tones). This approach led to enhanced model generalization despite a relatively small number of samples. We trained a DenseNet model to detect Omicron in subjects with self-declared positive COVID-19 tests. Our model achieved 86% sensitivity and 81% specificity when detecting healthy voices (asymptomatic negative vs. all positive). We also achieved 76% sensitivity and 70% specificity separating between symptomatic negative samples and all positive samples. This result showed that social media data may be used to counterbalance the limited amount of well-curated data commonly available for deep learning tasks in clinical medicine. Our work demonstrates the potential of digital, non-invasive diagnostic methods trained with public online data and explores novel design paradigms for diagnostic tools that rely on audio data.

show abstract

Insights into Materials, Physics, and Applications in Flexible and Wearable Acoustic Sensing Technology

Lin,

Duan,

Liu

et al. 2023

Advanced Materials

View full text Add to dashboard Cite

Sound plays a crucial role in the perception of the world. It allows to communicate, learn, and detect potential dangers, diagnose diseases, and much more. However, traditional acoustic sensors are limited in their form factors, being rigid and cumbersome, which restricts their potential applications. Recently, acoustic sensors have made significant advancements, transitioning from rudimentary forms to wearable devices and smart everyday clothing that can conform to soft, curved, and deformable surfaces or surroundings. In this review, the latest scientific and technological breakthroughs with insightful analysis in materials, physics, design principles, fabrication strategies, functions, and applications of flexible and wearable acoustic sensing technology are comprehensively explored. The new generation of acoustic sensors that can recognize voice, interact with machines, control robots, enable marine positioning and localization, monitor structural health, diagnose human vital signs in deep tissues, and perform organ imaging is highlighted. These innovations offer unique solutions to significant challenges in fields such as healthcare, biomedicine, wearables, robotics, and metaverse. Finally, the existing challenges and future opportunities in the field are addressed, providing strategies to advance acoustic sensing technologies for intriguing real‐world applications and inspire new research directions.

show abstract

Diagnosis of COVID-19 via acoustic analysis and artificial intelligence by monitoring breath sounds on smartphones

Cited by 17 publications

References 32 publications

The IOMT-Based Risk-Free Approach to Lung Disorders Detection from Exhaled Breath Examination

The IOMT-Based Risk-Free Approach to Lung Disorders Detection from Exhaled Breath Examination

Omicron detection with large language models and YouTube audio data

Insights into Materials, Physics, and Applications in Flexible and Wearable Acoustic Sensing Technology

Contact Info

Product

Resources

About