Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Abstract
Audio signals generated by the human body (e.g., sighs, breathing, heart, digestion, vibration sounds) have routinely been used by clinicians as indicators to diagnose disease or assess disease progression. Until recently, such signals were usually collected through manual auscultation at scheduled visits. Research has now started to use digital technology to gather bodily sounds (e.g., from digital stethoscopes) for cardiovascular or respiratory examination, which could then be used for automatic analysis. Some initial work shows promise in detecting diagnostic signals of COVID-19 from voice and coughs. In this paper we describe our data analysis over a large-scale crowdsourced dataset of respiratory sounds collected to aid diagnosis of COVID-19. We use coughs and breathing to understand how discernible COVID-19 sounds are from those in asthma or healthy controls. Our results show that even a simple binary machine learning classifier is able to classify correctly healthy and COVID-19 sounds. We also show how we distinguish a user who tested positive for COVID-19 and has a cough from a healthy user with a cough, and users who tested positive for COVID-19 and have a cough from users with asthma and a cough. Our models achieve an AUC of above 80% across all tasks. These results are preliminary and only scratch the surface of the potential of this type of data and audio-based machine learning. This work opens the door to further investigation of how automatically analysed respiratory patterns could be used as pre-screening signals to aid COVID-19 diagnosis.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures








Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“COVID-19 has been studied using different audio sounds, including voice, breathing and cough sounds [10,29,79,80].”
From Human-centred artificial intelligence for mobile health sensing: challenges and opportunities (2023) · cites this paper as [79]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Davis, S., & Mermelstein, P. (1980) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/tassp.1980.1163420 · Cited by 5,465 · cited 1×
“ents obtained from the short-term power spectrum, based on a linear cosine transform of the log power spectrum on a nonlinear Mel scale. MFCCs are amongst the most common features in audio processing [9]. We use the first 13 components. • ∆-MFCC: the temporal differential (delta) of the MFCC [1]. ∆2-MFCC: the differen…”
Backgroundlibrosa: Audio and Music Signal Analysis in Python
McFee, B., Raffel, C., Liang, D., Ellis, D., McVicar, M., Battenberg, E., & Nieto, O. (2015) · Proceedings of the Python in Science Conference · doi:10.25080/majora-7b98e3ed-003 · Cited by 3,033 · cited 1×
“ustrates the data processing pipelines. 4.1 Feature extraction HandcraftedFeatures.The raw sound waveform recorded by the apps is resampled to 22kHz, a standard value for audio tasks. We used librosa [20] as our audio processing library. From the resampled audio various handcrafted features are extracted at the frame…”
MethodInfluentialCNN architectures for large-scale audio classification
Hershey, S., Chaudhuri, S., Ellis, D. P. W., Gemmeke, J. F., Jansen, A., Moore, R. C., Plakal, M., Platt, D., Saurous, R. A., Seybold, B., et al. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952132 · Cited by 2,023
(2010) · doi:10.5555/1756006.1859921 · Cited by 1,924
Real-time tracking of self-reported symptoms to predict potential COVID-19
Menni, C., Valdes, A. M., Freidin, M. B., Sudre, C. H., Nguyen, L. H., Drew, D. A., Ganesh, S., Varsavsky, T., Cardoso, M. J., El-Sayed Moustafa, J. S., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0916-2 · Cited by 1,517
KERNEL METHODS IN MACHINE LEARNING
Hofmann, T., Schölkopf, B., & Smola, A. J. (2008) · Cited by 1,408
AI4COVID-19: AI enabled preliminary diagnosis for COVID-19 from cough samples via an app
Imran, A., Posokhova, I., Qureshi, H. N., Masood, U., Riaz, M. S., Ali, K., John, C. N., Hussain, M. I., & Nabeel, M. (2020) · Informatics in Medicine Unlocked · doi:10.1016/j.imu.2020.100378 · Cited by 621 · cited 2×
“In [17] a study of detection of coughs related to COVID-19 is presented using a cohort of 48 COVID-19 tested patients versus other pathology coughs on which an AI model is trained.”
MethodEmotionSense: a mobile phones based adaptive platform for experimental social psychology research
Rachuri, K. K., Musolesi, M., Mascolo, C., Rentfrow, P. J., Longworth, C., & Aucinas, A. (2010) · Proceedings of the 12th ACM international conference on Ubiquitous computing · doi:10.1145/1864349.1864393 · Cited by 508 · cited 1×
“In Emotionsense [26], the phone microphone is used as a sensor for users’ emotion detection in-thewild through Gaussian mixture models.”
MethodProceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012
Gouyon, F., Herrera, P., Martins, L. G., & Müller, M. A. (2012) · Cited by 446
Beat Tracking by Dynamic Programming
Ellis, D. P. W. (2007) · Journal of New Music Research · doi:10.1080/09298210701653344 · Cited by 391 · cited 1×
“• Tempo : the beats of the signals by measuring the onset strength, commonly used in music information retrieval [11].”
Cited by
Items 101–200 of 493
Glangetas, A., Hartley, M., Cantais, A., Courvoisier, D. S., Rivollet, D., Shama, D. M., Perez, A., Spechbach, H., Trombert, V., Bourquin, S., et al. (2021) · BMC Pulmonary Medicine · doi:10.1186/s12890-021-01467-w · Cited by 32
“For instance, the application of simple models such as logistic regression and support vector machine (SVM) were able to predict the diagnosis of COVID-19 from breath and cough sounds crudely collected on a mobile application with an area under the curve (AUC) of around 70% [20].”
MethodKhriji, L., Ammari, A. C., Messaoud, S., Bouaafia, S., Maraoui, A., & Machhout, M. (2021) · Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct52173.2021.9435454 · Cited by 29
“1 respiratory sounds with an area Under Curve exceeding 0.80 [23].”
BackgroundInfluentialAutomated COVID-19 and Heart Failure Detection Using DNA Pattern Technique with Cough Sounds
Kobat, M. A., Kıvrak, T., Barua, P. D., Tuncer, T., Doğan, Ş., Tan, R., Ciaccio, E. J., & Acharya, U. R. (2021) · Diagnostics · doi:10.3390/diagnostics11111962 · Cited by 28
“[68] Convolutional neural networks Convolutional neural networks Coswara [63], Cambridge [58], CoughVid [69] dataset.”
BackgroundChang, Y., Jing, X., Ren, Z. X., & Schuller, B. W. (2022) · Frontiers in Digital Health · doi:10.3389/fdgth.2021.799067 · Cited by 33
“Brown et al. ( 15) discovered that VGGish pre-trained on a large-scale YouTube dataset was utilised to extract audio features from raw audio samples for COVID-19 diagnosis.”
BackgroundMethodInfluentialVisual Detection of COVID-19 from Materials Aspect
Wang, G., Wang, L., Meng, Z., Su, X., Jia, C., Qiao, X., Pan, S., Chen, Y., Cheng, Y., & Zhu, M. (2022) · Advanced Fiber Materials · doi:10.1007/s42765-022-00179-y · Cited by 28
Review on Emerging Internet of Things Technologies to Fight the COVID-19
Manavi, S. Y., Nekkanti, V., Choudhary, R. S., & Jayapandian, N. (2020) · International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN) · doi:10.1109/icrcicn50933.2020.9296161 · Cited by 30
“Their work allows potential tracking and surveillance of the COVID-19 progression [15].”
BackgroundMachine Learning based COVID-19 Cough Classification Models - A Comparative Analysis
Vrindavanam, J., V, Srinath, R., Shankar, H. H., & Nagesh, G. (2021) · International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc51019.2021.9418358 · Cited by 27
“non-COVID-19 cough using VGGish is 82% [10].”
A Multi-Branch Deep Learning Network for Automated Detection of COVID-19
Fakhry, A., Jiang, X., Xiao, J., Chaudhari, G., & Han, A. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-378 · Cited by 28
“Furthermore, research has been conducted to train cough-based machine learning models to detect COVID-19 [8, 10, 11, 12, 13].”
MethodInfluentialMSCCov19Net: multi-branch deep learning model for COVID-19 detection from cough sounds
Ulukaya, S., Sarıca, A. A., Erdem, O., & Karaali, A. (2023) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-023-02803-4 · Cited by 29
“Several works using automatic deep learning algorithms on CT scans [6–10] and machine learning algorithms on cough sounds [11– 22] are proposed in literature.”
MethodInfluentialBreathPro: Monitoring Breathing Mode during Running with Earables
Hu, C., Kandappu, T., Liu, Y., Mascolo, C., & Ma, D. (2024) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3659607 · Cited by 35
“…including (i) statistical features such as mean, median, root-meansquare, maximum, minimum, 1st and 3rd quartile, interquartile range, standard deviation, skewness, and kurtosis [14] ; (ii) Linear-Frequency Cepstral Coefficients (LFCC) [76]; and (iii) Constant-Q Cepstral Coefficients (CQCC) [65].”
Self-citationVirufy: A Multi-Branch Deep Learning Network for Automated Detection of COVID-19Preprint
Fakhry, A., Jiang, X., Xiao, J., Chaudhari, G., Han, A., & Khanzada, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.01806 · Cited by 29
“Researchers have successfully presented models for detecting COVID-19 infection status using audio samples recorded in clinical settings [5, 15], suggesting that audio-based Artificial Intelligence models can be used to identify COVID-19.”
BackgroundMethodInfluentialIdentifying unique spectral fingerprints in cough sounds for diagnosing respiratory ailments
Ghrabli, S., Elgendi, M., & Menon, C. (2024) · Scientific Reports · doi:10.1038/s41598-023-50371-2 · Cited by 27
IATos: AI-powered pre-screening tool for COVID-19 from cough audio samplesPreprint
Pizzo, D. T., & Esteban, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.13247 · Cited by 30
Akman, A., Coppock, H., Gaskell, A., Tzirakis, P., Jones, L. I., & Schuller, B. W. (2022) · Frontiers in Digital Health · doi:10.3389/fdgth.2022.789980 · Cited by 27
“[13] and [14] demonstrate that simple machine learning models perform well in these relatively small datasets.”
Online Data Valuation and Pricing for Machine Learning Tasks in Mobile Health
Xu, A., Zheng, Z., Wu, F., & Chen, G. (2022) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom48880.2022.9796669 · Cited by 25
“Recently, researchers are making recent progress in COVID19 [43].”
BackgroundChest X ray and cough sample based deep learning framework for accurate diagnosis of COVID-19
Kumar, S., Nagar, R., Bhatnagar, S., Vaddi, R., Gupta, S. K., Rashid, M. U., Bashir, A. K., & Alkhalifah, T. (2022) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2022.108391 · Cited by 27
“5 [4] 2019 CXR 125 200 DNET ML SP 98% [5] 2020 X-ray 230 DL CON SP SP 90% [6] 2022 B BB 220 MFCCS DL Low-D 70% [7] 2022 Sound 200 Chest HSR SFs CNN 70% [15] 2020 cough 4352 SP MFCC DL CNN 80% [16] 2020 Web Cough COD 5320 DL R2 97.”
An Overview on Sound Features in Time and Frequency Domain
Constantinescu, C., & Brad, R. (2023) · International Journal of Advanced Statistics and IT&C for Economics and Life Sciences · doi:10.2478/ijasitels-2023-0006 · Cited by 25
A comprehensive review of COVID-19 detection techniques: From laboratory systems to wearable devices
Alyafei, K. A., Ahmed, R., Abir, F. F., Chowdhury, M. E. H., & Naji, K. K. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106070 · Cited by 25
“collected both cough and breathing sounds, then investigated how such data can aid with COVID-19 diagnosis [132].”
BackgroundVerde, L., Pietro, G. D., & Sannino, G. (2021) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-021-06041-4 · Cited by 24
“Respiratory signals [5,18,48] or coughing sounds [4,7,23,27,36,37,47] constitute the main vocal signals for the detection of the effects of COVID-19.”
BackgroundWavelet-Based Cough Signal Decomposition for Multimodal Classification
Agbley, B. L. Y., Li, J., Haq, A., Cobbinah, B. M., Kulevome, D. K. B., Agbefu, P. A., & Eleeza, B. (2020) · International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) · doi:10.1109/iccwamtip51612.2020.9317337 · Cited by 24
“In a much more related work, Brown et al [9] proposed a multimodal machine learning pipeline that utilizes both cough and breath data in their analysis.”
BackgroundCovid-19 recognition from cough sounds using lightweight separable-quadratic convolutional network
Soltanian, M. R. K., & Borna, K. (2021) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2021.103333 · Cited by 25
“MFCC + RF [31] 76.1 VGGsih/MFCC + LR [29] 81.8 MFCC + CNN [24] 94.3 VGGish + SVM [29] 90.9 VGGish + GRU [46] 89. convolutional and fully connected layers, but is widely used in audio recognition applications.”
InfluentialIslam, R., Abdel‐Raheem, E., & Tarique, M. (2021) · doi:10.1109/icm52667.2021.9664931 · Cited by 24
Kaur, S., Larsen, E., Harper, J., Purandare, B., Uluer, A., Hasdianda, M. A., Umale, N. A., Killeen, J. P., Castillo, E., & Jariwala, S. P. (2023) · Journal of Medical Internet Research · doi:10.2196/44410 · Cited by 26
Nguyen, L. H., Pham, N. T., Do, V. H., Nguyen, L. T., Nguyen, T. T., Nguyen, V., Nguyen, N. D., Nguyen, T. T., Nguyen, S. D., Bhatti, A., et al. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119212 · Cited by 27
Ren, Z. X., Chang, Y., Bartl-Pokorny, K. D., Pokorny, F. B., & Schuller, B. W. (2022) · Journal of Voice · doi:10.1016/j.jvoice.2022.06.011 · Cited by 26
“Although the classification performance of the SVM used in our study is significantly better than chance level, there are studies reporting better performances for COVID19 detection based on cough sounds.(11,57) Brown and colleagues(11) studied three classification tasks: COVID-19/nonCOVID, COVID-19 with cough/non-COV…”
InfluentialRapid and Scalable COVID-19 Screening using Speech, Breath, and Cough Recordings
Grant, D., McLane, I. M., & West, J. E. (2021) · IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...) · doi:10.1109/bhi50953.2021.9508482 · Cited by 25
Environment Knowledge-Driven Generic Models to Detect Coughs From Audio Recordings
Vhaduri, S., Dibbo, S. V., & Kim, Y. (2023) · IEEE Open Journal of Engineering in Medicine and Biology · doi:10.1109/ojemb.2023.3271457 · Cited by 31
“Due to the aforementioned limitations, researchers have been using audio recordings to detect cough and different diseases [12], [13], [14], [29], [40], [41], [42].”
BackgroundChowdhury, M. E. H., Ibtehaz, N., Rahman, T., Mekki, Y. M. S., Qibalwey, Y., Mahmud, S., Ezeddin, M., Zughaier, S. M., & Al-Maadeed, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.12063 · Cited by 24
“Cambridge dataset: The Cambridge dataset was designed for developing a diagnostic tool for COVID-19 based on cough and breath sounds [55].”
BackgroundMethodInfluentialUsing Deep Learning with Large Aggregated Datasets for COVID-19 Classification from CoughPreprint
Haritaoglu, E. D., Rasmussen, N., Tan, D. C. H., Jennifer Ranjani, J., Xiao, J., Chaudhari, G., Rajput, A., Govindan, P., Canham, C., Chen, W., et al. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2201.01669 · Cited by 21
“In [11], the authors have demonstrated that a binary machine learning classifier is sufficient to identify COVID-19 cough and breath signals from healthy individuals or asthmatic patients.”
BackgroundUncertainty-Aware COVID-19 Detection from Imbalanced Sound Data
Xia, T., Han, J., Qendro, L., Dang, T., & Mascolo, C. (2021) · Interspeech 2021 · doi:10.21437/interspeech.2021-1320 · Cited by 20
Self-citationAudio Feature Ranking for Sound-Based COVID-19 Patient Detection
Meister, J. A., Nguyen, K. A., & Luo, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16474-3_13 · Cited by 23
“(9) shows the signal’s transformation. s ( k ) is the log energy of the k -th of K coefficients at frame n [3].”
BackgroundMethodInfluentialAutomated Time Synchronization of Cough Events from Multimodal Sensors in Mobile Devices
Ahmed, T., Ahmed, M. Y., Rahman, M. M., Nemati, E., Islam, B., Vatanparvar, K., Nathan, V., McCaffrey, D., Kuang, J., & Gao, J. A. (2020) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3382507.3418855 · Cited by 20
“Such technology could have been vital in the remote monitoring of the ongoing pandemic COVID-19, as it can be used for pre-screening [4] and disease monitoring [16].”
BackgroundChallenges and Opportunities in Deploying COVID-19 Cough AI Systems
Khanzada, A., Hegde, S., Sreeram, S., Bower, G., Wang, W. Y., Mediratta, R. P., Meister, K. D., & Rameau, A. (2021) · Journal of Voice · doi:10.1016/j.jvoice.2021.08.009 · Cited by 21
“3,4,7,8 These groups have been able to obtain thousands of labeled cough sound samples, as well as user-reported polymerase chain reaction (PCR) results via app-based collection tools.”
COVID-19 Detection Model with Acoustic Features from Cough Sound and Its Application
Kim, S., Baek, J., & Lee, S.-P. (2023) · Applied Sciences · doi:10.3390/app13042378 · Cited by 21
A deep convolutional neural network approach using medical image classification
Mousavi, M., & Hosseini, S. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02646-5 · Cited by 21
Chen, X., Zhu, Q., Zhang, J., & Dai, L.-R. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746205 · Cited by 19
Avasthi, S., Chauhan, R., Tripathi, S. L., & Sanwal, T. (2022) · Elsevier eBooks · doi:10.1016/b978-0-323-85174-9.00008-x · Cited by 18
Transfer learning for the efficient detection of COVID-19 from smartphone audio data
Campana, M. G., Delmastro, F., & Pagani, E. (2023) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2023.101754 · Cited by 19
An AI-Enabled Bias-Free Respiratory Disease Diagnosis Model Using Cough Audio
Saeed, T., Ijaz, A., Sadiq, I., Qureshi, H. N., Rizwan, A., & Imran, A. (2024) · Bioengineering · doi:10.3390/bioengineering11010055 · Cited by 18
“In the rapidly advancing field of AI-enabled automated cough sound monitoring and digital disease diagnosis, remarkable performance metrics have been achieved, as evidenced by several notable studies [8,10,14,32–36].”
BackgroundLella, K. K., Jagadeesh, M. S., & Alphonse, P. J. A. (2024) · Health Information Science and Systems · doi:10.1007/s13755-024-00283-w · Cited by 19
“The dataset was prepared by collecting the various respiratory disease databases [41–45].”
Digital Citizen Science for Responding to COVID-19 Crisis: Experiences from Iran
Vahidi, H., Taleai, M., Yan, W., & Shaw, R. (2021) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph18189666 · Cited by 18
“For instance, online citizen science has been used for identification and mapping of suspected COVID-19 cases [36], tracing close contact with positive cases of COVID-19 [37], collecting respiratory sounds to aid diagnosis of COVID-19 [38], and studying risk factors for COVID-19 infection in a large, geographically he…”
MethodSpeech as a Biomarker for COVID-19 Detection Using Machine Learning
Usman, M. J., Gunjan, V. K., Wajid, M., Zubair, M., & Siddiquee, K. N. E. A. (2022) · Computational Intelligence and Neuroscience · doi:10.1155/2022/6093613 · Cited by 21
“Cough and respiratory sounds are used to classify COVID19 and non-COVID-19 individuals in [73].”
BackgroundAlbalawi, U., & Mustafa, M. E. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph19105901 · Cited by 24
“Detection of COVID-19 has also been attempted through the cough sound [55,63,69–72].”
BackgroundA summary of the ComParE COVID-19 challenges
Coppock, H., Akman, A., Bergler, C., Gerczuk, M., Brown, C., Chauhan, J., Grammenos, A., Hasthanasombat, A., Spathis, D., Xia, T., et al. (2023) · Frontiers in Digital Health · doi:10.3389/fdgth.2023.1058163 · Cited by 18
“The datasets used in these challenges are two curated subsets of the crowd sourced Cambridge COVID-19 Sounds database (1, 21).”
Self-citationRecent Advances in Computer Audition for Diagnosing COVID-19: An Overview
Qian, K., Schuller, B. W., & Yamamoto, Y. (2021) · IEEE Global Conference on Life Sciences and Technologies (LifeTech) · doi:10.1109/lifetech52111.2021.9391791 · Cited by 19
“In the past eight months, we have seen an increasing number of literature focusing on CA methods for fighting the COVID-19 pandemic [4]–[8].”
BackgroundVahedian‐Azimi, A., Keramatfar, A., Asiaee, M., Atashi, S. S., & Nourbakhsh, M. (2021) · The Journal of the Acoustical Society of America · doi:10.1121/10.0006104 · Cited by 18
Voice Sequelae Following Recovery From COVID-19
Arias, T. R., & Betancort, M. (2022) · Journal of Voice · doi:10.1016/j.jvoice.2022.06.033 · Cited by 17
Swinney, C. J., & Woods, J. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3202011 · Cited by 19
“The diagnosis of COVID-19 has also benefited from the use of transfer learning with CNN feature extraction following by machine learning classification using logistic regression [52], random forest [53] and support vector machine [54].”
MethodProductive and Non-Productive Cough Classification Using Biologically Inspired Techniques
Sharan, R. V. (2022) · IEEE Access · doi:10.1109/access.2022.3231640 · Cited by 17
“and a set of transfer learning-driven features [47] are engineered and populated in each segmented signal.”
BackgroundGul, K., Fasih, S. T., Morandé, S., & Ramish, M. S. (2024) · Sustainability · doi:10.3390/su16166956 · Cited by 18
“More broadly, integrating machine and human intelligence requires considered design to preserve the participatory ethics of photovoice [60] (Brown et al., 2021).”
Detecting COVID-19 from Audio Recording of Coughs Using Random Forests and Support Vector Machines
Södergren, I., Nodeh, M. P., Chhipa, P. C., Nikolaidou, K., & Kovács, G. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-2191 · Cited by 19
“An overview of some of these works [19] with results from nine articles (as well as our review of the literature) shows that most studies so far have used MFCC-features [17, 20], spectrograms, and a few [21] used handcrafted features.”
BackgroundTransfer Learning-Based Cough Representations for Automatic Detection of COVID-19
Solera-Ureña, R., Botelho, C., Teixeira, F., Rolland, T., Abad, A., & Trancoso, I. M. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1702 · Cited by 17
“The COVID-19 COUGH (C19C) corpus [3, 9] is provided in the ComParE 2021 COVID-19 Cough Sub-Challenge as a test-bed for the evaluation of the systems presented by the participants.”
BackgroundMethodInfluentialCasanova, E., Cândido, A., Fernandes, R. C., Finger, M., Gris, L. R. S., Ponti, M. A., & da Silva, D. P. P. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1798 · Cited by 27
“The datasets for the sub-challenges were extracted from the COVID-19 Sound database [12, 13, 14].”
MethodSharded Blockchain-based Online Diagnostic System for Suspected Patients During Pandemics
Omran, A., Abouyoussef, M. S., Ismail, M., & Bhatia, S. (2022) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc51071.2022.9771790 · Cited by 16
“In literature, coughing signals proved to successfully identify if the suspected patient is infected with COVID-19 or not [13].”
BackgroundUbi-Asthma: Toward Ubiquitous Asthma Detection Using the Smartwatch
Wu, Y. L., Zhang, J., Chen, Y., Wang, J., Shi, W., & Zhang, Q. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3243188 · Cited by 16
“Previous research either asks users to continuously monitor cough [10], [11], which is prone to bring privacy issues to users and susceptible to environmental noise or requires users to actively record cough signals [18], [19], which may weaken the user’s adherence.”
BackgroundMethodInfluentialPopadina, A. O., Salah, A.-M., & Karam, J. (2021) · IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering · doi:10.1109/elconrus51938.2021.9396367 · Cited by 16
“Voice analysis can be a diagnostic method for asthma-COVID-19 detection, because both asthma and COVID-19 causes significant voice changes [1-10].”
BackgroundMethodValdés, J. J., Xi, P., Cohen-McFarlane, M., Wallace, B., Goubran, R. A., & Knoefel, F. D. (2021) · IEEE International Symposium on Medical Measurements and Applications (MeMeA) · doi:10.1109/memea52024.2021.9478714 · Cited by 16
COVID-19 Diagnosis from Crowdsourced Cough Sound Data
Son, M.-J., & Lee, S.-P. (2022) · Applied Sciences · doi:10.3390/app12041795 · Cited by 17
“(a) [21] MFCC LSTM 62% 60% 62% (b) [12] MFCC LSTM 71% 77% 65% (c) [20] MFCC LSTM 73% 71% 76% (d) [21] Spectrogram ResNet-50 88% 90% 88% (e) [21] MFCC + spectrogram ResNet-50 + DNN 89% 93% 86%”
BackgroundMethodInfluentialAbayomi‐Alli, O., Damaševičius, R., Abbasi, A. A., & Maskeliūnas, R. (2022) · Electronics · doi:10.3390/electronics11162520 · Cited by 17
“[48] presented ML algorithms such as Logistic Regression (LR), Gradient Boosting Trees, and Support Vector Machines in the detection of COVID-19.”
MethodCough Audio Analysis for COVID-19 Diagnosis
Kapoor, T., Pandhi, T., & Gupta, B. (2022) · SN Computer Science · doi:10.1007/s42979-022-01522-1 · Cited by 16
Blockchain-Enabled Online Diagnostic Platform of Suspected Patients of COVID-19 Like Pandemics
Abouyoussef, M. S., Bhatia, S., Chaudhary, P., Sharma, S., & Ismail, M. F. (2021) · IEEE Internet of Things Magazine · doi:10.1109/iotm.1001.2100046 · Cited by 15
A Review on the Use of Machine Learning Against the Covid-19 Pandemic
Biabani, S. A. A., & Tayyib, N. (2022) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.4628 · Cited by 16
“The authors of [55] built binary classifiers for distinguishing Covid-19 positive patients from other respiratory diseases.”
BackgroundFischer, A., Elbéji, A., Aguayo, G., & Fagherazzi, G. (2022) · Interactive Journal of Medical Research · doi:10.2196/40655 · Cited by 16
“The validity of the data set can also be a concern, as the COVID-19 status may be self-reported [33] and may induce some mislabeling of the audio.”
Deep-Learning-Based COVID-19 Detection: Challenges and Future Directions
Arshad, Q., Khan, W. Z., Azam, F., & Khan, M. K. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3224097 · Cited by 20
Coronavirus diagnosis using cough sounds: Artificial intelligence approaches
Nasab, K. A., Mirzaei, J., Zali, A., Gholizadeh, S., & Akhlaghdoust, M. (2023) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2023.1100112 · Cited by 16
“It has been reported that simple machine learning tools, such as binary classifiers, can distinguish COVID-19 breath sounds from healthy counterparts with an area under the ROC curve (AUC)>0.80 (Brown et al., 2020).”
BackgroundInfluentialOutlining Big Data Analytics in Health Sector with Special Reference to Covid-19
Biswas, R. (2021) · Wireless Personal Communications · doi:10.1007/s11277-021-09446-4 · Cited by 17
“…b a s e s [ 28 ] Y e s Y e s D e m a r ca ti on o f C O V I D - 19 c ough s ound fr o m C r o w d s ou r ce d R e s p i r a t o r y S ound D a t a [ 29 ] Y e s Y e s E v a l u a ti ng i m p ac t o f C OV I D - 19 on m e n t a l h ea lt h a nd w e ll b e i ng [ 30 ] Y e s Y e s D e s i gn i ng m…”
Transfer Learning for Depression Screening from Follow-Up Clinical Interview Questions
Flores, R., Tlachac, M., Toto, E., & Rundensteiner, E. A. (2022) · Advances in intelligent systems and computing · doi:10.1007/978-981-19-6153-3_3 · Cited by 18
Zarkogianni, K., Dervakos, E., Filandrianos, G., Ganitidis, T., Gkatzou, V., Sakagianni, A., Raghavendra, R., Nikias, C. L. M., Stamou, G. B., & Nikita, K. S. (2023) · Scientific Data · doi:10.1038/s41597-023-02646-6 · Cited by 15
“Furthermore, this additional information can be utilized for post hoc explainability and analysis of black-box classifiers, which is particularly useful since opaque deep learning models are usually applied towards detecting COVID-19 from audio recordings 11–13 .”
BackgroundMallol-Ragolta, A., Cuesta, H., Gómez, E., & Schuller, B. W. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-1052 · Cited by 14
“The signals considered include breaths [15, 16], coughs [17, 18], and even speech [19, 20].”
BackgroundJiao, N. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17613-x · Cited by 17
“The framework achieved superior results which exceed 70% for accuracy measure compared with other classification models [23].”
Developing a multi-feature fusion model for exacerbation classification in asthma and COPD
Yan, Y., van Bemmel, L., Franssen, F. M. E., Simons, S. O., & Urovi, V. (2025) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.108796 · Cited by 16
Visual Transformers for Primates Classification and Covid Detection
Illium, S., Müller, R., Sedlmeier, A., & Popien, C.-L. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-273 · Cited by 15
“For further introductory explanation please refer to [3, 5].”
BackgroundMethodHusain, M., Simpkin, A. J., Gibbons, C., Talkar, T., Low, D. M., Bonato, P., Ghosh, S., Quatieri, T. F., & O'Keeffe, D. T. (2022) · IEEE Open Journal of Engineering in Medicine and Biology · doi:10.1109/ojemb.2022.3143688 · Cited by 15
“Nevertheless, 3 Apps required participants to fill in a medical questionnaire on the basis of recent medical history or any previous underlying condition to complete the data collection process [36], [37], [42].”
BackgroundInfluentialPourreza, S., Faezipour, M., & Faezipour, M. (2022) · Sustainability · doi:10.3390/su14148876 · Cited by 15
Chakraborty, C., Dash, T. K., Panda, G., & Solanki, S. S. (2022) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3563944 · Cited by 14
“The diferent statistical parameters used are: mean, median, root-mean-square, maximum, minimum, 1st and 3rd quartile, interquartile range, standard deviation, skewness, and kurtosis [7].”
MethodEffati, M., & Nejat, G. (2023) · Computers · doi:10.3390/computers12020044 · Cited by 16
Towards Multimodal Equipment to Help in the Diagnosis of COVID-19 Using Machine Learning Algorithms
Villa-Parra, A. C., Criollo, I., Valadão, C., Silva, L., Coelho, Y., Lampier, L., Rangel, L., Sharma, G., Delisle-Rodríguez, D., Calle-Sigüencia, J., et al. (2022) · Sensors · doi:10.3390/s22124341 · Cited by 15
Aljbawi, W., Simons, S. O., & Urovi, V. (2022) · European Respiratory Journal · doi:10.1183/13993003.congress-2022.1062 · Cited by 14
COVID-19 respiratory sound analysis and classification using audio textures
Silva, L. R., Valadão, C., Lampier, L., Delisle-Rodríguez, D., Caldeira, E. M. D. O., Bastos-Filho, T., & Krishnan, S. (2022) · Frontiers in Signal Processing · doi:10.3389/frsip.2022.986293 · Cited by 13
“However, as in the study by Brown et al. (2020), only cough and breathing sounds were used in our study.”
BackgroundMethodInfluentialImproving Misfire Fault Diagnosis with Cascading Architectures via Acoustic Vehicle Characterization
Terwilliger, A. M., & Siegel, J. E. (2022) · Sensors · doi:10.3390/s22207736 · Cited by 17
Leite, G. S., Albuquerque, A. B., & Pinheiro, P. R. (2021) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph182010765 · Cited by 13
COVID-19 Diagnosis from Cough Acoustics using ConvNets and Data Augmentation
Mahanta, S. K., Kaushik, D., Truong, H. V., Jain, S., & Guha, K. (2021) · International Conference on Advances in Computing and Future Communication Technologies (ICACFCT) · doi:10.1109/icacfct53978.2021.9837350 · Cited by 16
A residual network-based deep learning model for the detection of COVID-19 using cough sounds
Banerjee, A., & Nilhani, A. (2022) · Institute of Physics eBooks · doi:10.1088/978-0-7503-3795-3ch6 · Cited by 13
“Whereas, the model in [18] outperforms in terms of specificity and precision.”
A comprehensive survey on the biomedical signal processing methods for the detection of COVID-19
Anand, S., Sharma, V., Pourush, R., & Jaiswal, S. (2022) · Annals of Medicine and Surgery · doi:10.1016/j.amsu.2022.103519 · Cited by 17
Lella, K. K., & Alphonse, P. J. A. (2022) · The European Physical Journal Special Topics · doi:10.1140/epjs/s11734-022-00649-9 · Cited by 13
“[40, 47, 48] suggested web-based, iOS, and Android applications to record pulmonary COVID-19 sound data (KDD-data, ComParE2021CCS-CSS-Data, and NeurlPs2021-data) from crowdsourcing sound data of around 2 k COVID-19-positive cases (with different variants) from about 36 k unique users.”
BackgroundMethodInfluentialA transfer learning-based deep learning approach for automated COVID-19 diagnosis with audio data
Akgün, D., Kabakuş, A. T., Şentürk, Z. K., Şentürk, A., & Küçükkülahlı, E. (2021) · TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES · doi:10.3906/elk-2105-64 · Cited by 14
“[21] that we previously called Cambridge data and provided an easier training process without compromising the classification accuracy.”
InfluentialAI Hears Your Health: Computer Audition for Health Monitoring
Amiriparian, S., & Schuller, B. W. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-94209-0_20 · Cited by 12
Nallakaruppan, M. K., Ramalingam, S., Somayaji, S. R. K., & Prathiba, S. B. (2022) · Biomedicines · doi:10.3390/biomedicines10112791 · Cited by 14
“Brown Chloe et al. [5] suggested developing Android or iOS applications in order to gather coronavirus sound data over the publicly available sound breathing pattern of around 200 coronavirus benefits out of 7000 new clients.”
BackgroundOrlova, Y. A., Gorobtsov, A., Александрович, С. О., Розалиев, В. Л., Zubkov, A. V., & Donsckaia, A. (2023) · Algorithms · doi:10.3390/a16050249 · Cited by 12
COVID-19 symptom identification using Deep Learning and hardware emulated systems
Liyanarachchi, R. K., Wijekoon, J., Premathilaka, M., & Vidhanaarachchi, S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106709 · Cited by 13
“Other than that, there are researches conducted which have developed mobile applications as pre-screening methods by analyzing cough sounds (20)(21)(22)(23)(48)(49)(50).”
Renjini, A., Swapna, M. S., Raj, V., & Sankararaman, S. I. (2021) · Journal of Complex Networks · doi:10.1093/comnet/cnab039 · Cited by 12
“Cough signal inputs of 69 WE and 46 DE sourced from the ‘COVID 19 SOUNDS APP’ provided by the University of Cambridge [22], on a data access agreement, are studied in this work to inquire into the airflow dynamics in the respiratory tract during coughing.”
Depression Screening Using Deep Learning on Follow-up Questions in Clinical Interviews
Flores, R., Tlachac, M., Toto, E., & Rundensteiner, E. A. (2021) · International Conference on Machine Learning and Applications · doi:10.1109/icmla52953.2021.00099 · Cited by 17
Combating COVID-19 Crisis using Artificial Intelligence (AI) Based Approach: Systematic Review
Singh, K., Kaur, N., & Prabhu, A. A. (2024) · Current Topics in Medicinal Chemistry · doi:10.2174/0115680266282179240124072121 · Cited by 11
Shamma, A. L., Vekkot, S., Gupta, D., Zakariah, M., & Alotaibi, Y. A. (2024) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-219387 · Cited by 13
Sharma, N. K., Muguli, A., Krishnan, P., Kumar, R. V., Chetupalli, S. R., & Ganapathy, S. (2021) · Computer Speech & Language · doi:10.1016/j.csl.2021.101320 · Cited by 13
“[9] used cough and breathing sounds jointly and attempted a binary classification task of separating COVID-19 infected individuals from healthy.”
BackgroundFurman, G. B., Фурман, Е. Г., Charushin, A. O., Eirikh, E., Malinin, S., Степанович, Ш. В., Sokolovsky, V., & Shtivelman, D. (2022) · JMIR Formative Research · doi:10.2196/31200 · Cited by 11
“Brown et al [19] used the exploring automatic diagnostics of COVID-19 from crowdsourced respiratory sound data.”
MethodResultDeep Learning against COVID-19: Respiratory Insufficiency Detection in Brazilian Portuguese Speech
Casanova, E., Gris, L. R. S., de Camargo, A. C., Silva, D., Gazzola, M. G., Sabino, É. C., Levin, A. S., Cândido, A., Aluísio, S. M., & Finger, M. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.55 · Cited by 20
Diagnosis of COVID-19 Using Auditory Acoustic Cues
Das, R. K., Madhavi, M. C., & Li, H. (2021) · Interspeech (USB) · doi:10.21437/interspeech.2021-497 · Cited by 10
“Inspired by the success of various acoustic features for detecting COVID-19 from cough or speech [11–13], we focused on exploring a few novel auditory acoustic features during our participation in DiCOVA challenge.”
BackgroundMethodLiu, S., Mallol-Ragolta, A., & Schuller, B. W. (2021) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc46164.2021.9630050 · Cited by 10
“dataset [10], as different validation strategies and data splits are chosen to assess the performance of the models trained.”
Tawfik, M., Nimbhore, S., Al-Zidi, N. M., Ahmed, Z. A. T., & Al-madani, A. M. (2022) · International Conference on Smart Systems and Inventive Technology (ICSSIT) · doi:10.1109/icssit53264.2022.9716529 · Cited by 14
“For the last year, clinical scientists and researchers have noticed the issue of respiratory sound classification and diagnosis of COVID-19 disease[4].”
Background
Metadata
- Authors
- Brown, C., Chauhan, J., Grammenos, A., Han, J., Hasthanasombat, A., Spathis, D., Xia, T., Cicuta, P., & Mascolo, C.
- Affiliations
- University of Cambridge (GB)
- University of Cambridge, Cambridge, United Kingdom
- ORCID
- Venue
- Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
- Publisher
- ACM
- Published
- 2020-08-20
- Pages
- 3474-3484
- OpenAlex
- W3035378948
- Cited by
- 447
- References
- 34
- Citations by year
- 2026: 17 · 2025: 26 · 2024: 49 · 2023: 78 · 2022: 124 · 2021: 136 · 2020: 15
- FWCI
- 253.82
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Cambridge University Engineering Department Publications Database (submittedVersion)
- Apollo (University of Cambridge) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Apollo (cc-by)
- Funders
- Cystic Fibrosis Trust
- European Research Council (833296)
- Topics
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Phonocardiography and Auscultation Techniques
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › COVID-19 diagnosis using AI
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- COVID-19 diagnosis, lung sounds, cough, digital stethoscope, asthma, binary classification, prescreening
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.