COVID-19 Artificial Intelligence Diagnosis Using Only Cough Recordings
Open accessThe DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Abstract
Goal:We hypothesized that COVID-19 subjects, especially including asymptomatics, could be accurately discriminated only from a forced-cough cell phone recording using Artificial Intelligence. To train our MIT Open Voice model we built a data collection pipeline of COVID-19 cough recordings through our website (opensigma.mit.edu) between April and May 2020 and created the largest audio COVID-19 cough balanced dataset reported to date with 5,320 subjects.Methods:We developed an AI speech processing framework that leverages acoustic biomarker feature extractors to pre-screen for COVID-19 from cough recordings, and provide a personalized patient saliency map to longitudinally monitor patients in real-time, non-invasively, and at essentially zero variable cost. Cough recordings are transformed with Mel Frequency Cepstral Coefficient and inputted into a Convolutional Neural Network (CNN) based architecture made up of one Poisson biomarker layer and 3 pre-trained ResNet50's in parallel, outputting a binary pre-screening diagnostic. Our CNN-based models have been trained on 4256 subjects and tested on the remaining 1064 subjects of our dataset. Transfer learning was used to learn biomarker features on larger datasets, previously successfully tested in our Lab on Alzheimer's, which significantly improves the COVID-19 discrimination accuracy of our architecture.Results:When validated with subjects diagnosed using an official test, the model achieves COVID-19 sensitivity of 98.5% with a specificity of 94.2% (AUC: 0.97). For asymptomatic subjects it achieves sensitivity of 100% with a specificity of 83.2%.Conclusions:AI techniques can produce a free, non-invasive, real-time, any-time, instantly distributable, large-scale COVID-19 asymptomatic screening tool to augment current approaches in containing the spread of COVID-19. Practical use cases could be for daily screening of students, workers, and public as schools, jobs, and transport reopen, or for pool testing to quickly alert of outbreaks in groups. General speech biomarkers may exist that cover several disease categories, as we demonstrated using the same ones for COVID-19 and Alzheimer's.
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
![Fig. 1. Overview architecture of the COVID-19 discriminator with cough recordings as input, and COVID-19 diagnosis and longitudinal saliency map as output. A similar architecture was used for Alzheimer's [11].](https://figures.cochat.ai/paper-figures/be9351a8db1c43b6804b74f29955652e/covid-19-artificial-intelligence-diagnosis-using-only-cough-recordings-figure-1.jpg)

![Fig. 3. A. The numbers on the x-axis describe the number of layers in the biomarker models fine-tuned to COVID-19. The fewer required to beat the baseline (which is the same architecture trained on COVID-19 discrimination without the pre-trained biomarker models) shows the relevance of each biomarker for COVID-19. “Complete: shows the final COVID-19 discriminator with all the biomarkers integrated. B. The white dotted part of the bar shows the performance gained when the Cough biomarker model is incorporated, while pre-trained denotes individually training the biomarker models for COVID-19 before integrating them into the multi-modal architecture on Fig. 1. C. shows the explainable saliency map derived from biomarker model predictions to longitudinally track patient progression and is analogous to the saliency map derived for Alzheimer's [11]. OVBM denotes the final model diagnostic. The BrainOS section shows the model aggregated prediction for 1-4 coughs of a subject. The COVID-19 progress factor calculates based on the 1-4 cough predictions, a possible degree of severity from the quantity of acoustic information required for a confident diagnostic. The voting confidence and salient factor indicate, based on the composite predictions of individual biomarker models, the aggregate confidence and salient discrimination for each subject.](https://figures.cochat.ai/paper-figures/8e2c75917b6d4a2aa907785657db3378/covid-19-artificial-intelligence-diagnosis-using-only-cough-recordings-figure-3.jpg)

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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Usando un algoritmo particular, la IA analiza el tono de voz del sujeto, el estado emocional y la frecuencia respiratoria, luego los compara con miles de sonidos emitidos al toser por pacientes con COVID-19 y sujetos sanos, y logra identificar individuos que son completamente asintomáticos, pero son positivos al virus, con una precisión diagnóstica del 98,5 al 100% (Laguarta, Hueto y Subirana, 202”
From One Health y las nuevas herramientas para promover la salud desde una perspectiva holística y medioambiental (2021) · cites this paper as Laguarta, Hueto y Subirana, 2020
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Los investigadores del MIT en Boston han desarrollado un sistema que es capaz de diagnosticar COVID-19 a partir de la tos.”
From One Health y las nuevas herramientas para promover la salud desde una perspectiva holística y medioambiental (2021) · cites this paper as Laguarta, Hueto y Subirana, 2020
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
“Librispeech: an ASR corpus based on public domain audio books,”
Panayotov, V., Chen, G., Povey, D., & Khudanpur, S. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178964 · Cited by 6,072
Li, L., Qin, L., Xu, Z., Yin, Y., Wang, X., Kong, B., Bai, J., Lu, Y., Fang, Z., Song, Q., et al. (2020) · Radiology · doi:10.1148/radiol.2020200905 · Cited by 1,927
Livingstone, S. R., & Russo, F. A. (2018) · PLOS ONE · doi:10.1371/journal.pone.0196391 · Cited by 1,883
Artificial intelligence–enabled rapid diagnosis of patients with COVID-19
Mei, X., Lee, H.-C., Diao, K.-Y., Huang, M., Lin, B., Liu, C., Xie, Z., Ma, Y., Robson, P. M., Chung, M., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-0931-3 · Cited by 1,084
Mao, L., Wang, M., Chen, S., He, Q., Chang, J., Hong, C., Zhou, Y., Wang, D., Li, Y., Jin, H., et al. (2020) · medRxiv · doi:10.1101/2020.02.22.20026500 · Cited by 875
Barro, R., Ursúa, J., & Weng, J. (2020) · National Bureau of Economic Research · doi:10.3386/w26866 · Cited by 800
Lechien, J. R., Chiesa‐Estomba, C. M., Place, S., Van Laethem, Y., Cabaraux, P., Mat, Q., Huet, K., Plzak, J., Horoi, M., Hans, S., et al. (2020) · Journal of Internal Medicine · doi:10.1111/joim.13089 · Cited by 800
Smell dysfunction: a biomarker for COVID‐19
Moein, S. T., Hashemian, S. M., Mansourafshar, B., Khorram‐Tousi, A., Tabarsi, P., & Doty, R. L. (2020) · International Forum of Allergy & Rhinology · doi:10.1002/alr.22587 · Cited by 794
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
SEMANTIC MEMORY LOSS IN DEMENTIA OF ALZHEIMER'S TYPE: WHAT DO VARIOUS MEASURES MEASURE?
CHERTKOW, H., & BUB, D. (1990) · Brain · doi:10.1093/brain/113.2.397 · Cited by 536
COVID-19 epidemic in Switzerland: on the importance of testing, contact tracing and isolation
Salathé, M., Althaus, C. L., Neher, R., Stringhini, S., Hodcroft, E., Fellay, J., Zwahlen, M., Senti, G., Battegay, M., Wilder-Smith, A., et al. (2020) · Swiss Medical Weekly · doi:10.4414/smw.2020.20225 · Cited by 481
La Marca, A., Capuzzo, M., Paglia, T., Roli, L., Trenti, T., & Nelson, S. M. (2020) · Reproductive BioMedicine Online · doi:10.1016/j.rbmo.2020.06.001 · Cited by 389
Fotuhi, M., Mian, A., Meysami, S., & Raji, C. A. (2020) · Journal of Alzheimer's Disease · doi:10.3233/jad-200581 · Cited by 388
Reed, W. J., & Hughes, B. D. (2002) · Physical Review E · doi:10.1103/physreve.66.067103 · Cited by 278
Rapid Scaling Up of Covid-19 Diagnostic Testing in the United States — The NIH RADx Initiative
Tromberg, B. J., Schwetz, T. A., Pérez-Stable, E. J., Hodes, R. J., Woychik, R. P., Bright, R. A., Fleurence, R. L., & Collins, F. S. (2020) · New England Journal of Medicine · doi:10.1056/nejmsr2022263 · Cited by 256
Chang, A., & Karnell, M. P. (2004) · Journal of Voice · doi:10.1016/j.jvoice.2004.01.004 · Cited by 203
Lung disease as a determinant of cognitive decline and dementia
Dodd, J. W. (2015) · Alzheimer's Research & Therapy · doi:10.1186/s13195-015-0116-3 · Cited by 192
Kavanagh, M. M., Erondu, N. A., Tomori, O., Dzau, V. J., Okiro, E. A., Maleche, A., Aniebo, I. C., Rugege, U., Holmes, C. B., & Gostin, L. O. (2020) · The Lancet · doi:10.1016/s0140-6736(20)31093-x · Cited by 167
Covid-19 and the Stiff Upper Lip — The Pandemic Response in the United Kingdom
Hunter, D. J. (2020) · New England Journal of Medicine · doi:10.1056/nejmp2005755 · Cited by 165
A Cough-Based Algorithm for Automatic Diagnosis of Pertussis
Pramono, R. X. A., Imtiaz, S. A., & Rodriguez–Villegas, E. (2016) · PLoS ONE · doi:10.1371/journal.pone.0162128 · Cited by 164
Porter, P., Abeyratne, U. R., Swarnkar, V. R., Tan, J., Ng, T.-W., Brisbane, J. M., Speldewinde, D., Choveaux, J., Sharan, R. V., Kosasih, K., et al. (2019) · Respiratory Research · doi:10.1186/s12931-019-1046-6 · Cited by 140
Detection of tuberculosis by automatic cough sound analysis
Botha, G. H. R., Theron, G., Warren, R. M., Klopper, M., Dheda, K. U. J., van Helden, P. D., & Niesler, T. (2018) · Physiological Measurement · doi:10.1088/1361-6579/aab6d0 · Cited by 136
da Costa, A. L. C., Bak, T. H., Caffarra, P., Caltagirone, C., Ceccaldi, M. P., Collette, F., Crutch, S. J., Sala, S. D., Démonet, J., Dubois, B., et al. (2017) · Alzheimer s Research & Therapy · doi:10.1186/s13195-017-0254-x · Cited by 122
Cough Sound Analysis Can Rapidly Diagnose Childhood Pneumonia
Abeyratne, U. R., Swarnkar, V. R., Setyati, A., & Triasih, R. (2013) · Annals of Biomedical Engineering · doi:10.1007/s10439-013-0836-0 · Cited by 109
Glottis narrowing in lung disease.
Higenbottam, T., & Payne, J. (1982) · PubMed · doi:10.1164/arrd.1982.125.6.746 · Cited by 98
A Framework for Biomarkers of COVID-19 Based on Coordination of Speech-Production Subsystems
Quatieri, T. F., Talkar, T., & Palmer, J. S. (2020) · IEEE Open Journal of Engineering in Medicine and Biology · doi:10.1109/ojemb.2020.2998051 · Cited by 97
Motor impairment in Alzheimer’s disease and transgenic Alzheimer’s disease mouse models
Wirths, O., & Bayer, T. A. (2008) · Genes Brain & Behavior · doi:10.1111/j.1601-183x.2007.00373.x · Cited by 90
Windmon, A., Minakshi, M., Bharti, P., Chellappan, S., Johansson, M., Jenkins, B. A., & Athilingam, P. R. (2018) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2018.2872038 · Cited by 79
Subirana, B., Hueto, F., Rajasekaran, P., Laguarta, J., Puig, S., Malvehy, J., Mitjà, J., Trilla, A., Moreno, C. I., Valle, J. F. M., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.06510 · Cited by 77
Self-citationLongitudinal Speech Biomarkers for Automated Alzheimer's Detection
Laguarta, J., Hueto, F., Rajasekaran, P., Sarma, S. E., & Subirana, B. (2021) · Frontiers in Computer Science · doi:10.3389/fcomp.2021.624694 · Cited by 60
Self-citationjameslyons/python_speech_features: release v0.6.1
Lyons, J., Wang, D. Y.-B., G., Shteingart, H., Mavrinac, E., Gaurkar, Y., Watcharawisetkul, W., Birch, S., Zhihe, L., Hölzl, J., et al. (2020) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.3607696 · Cited by 41
MobiCough: Real-Time Cough Detection and Monitoring Using Low-Cost Mobile Devices
Pham, C. (2016) · Lecture notes in computer science · doi:10.1007/978-3-662-49381-6_29 · Cited by 32
jameslyons/python_speech_features: release v0.6.1
Lyons, J., Wang, D. Y.-B., Gianluca, G., et al. (2020) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.3607820 · Cited by 32
Heckman, P. R. A., Blokland, A., & Prickaerts, J. (2017) · Advances in neurobiology · doi:10.1007/978-3-319-58811-7_6 · Cited by 31
Neuropsychological Assessment in the Diagnosis of Alzheimer's Disease
Baldwin, S., & Farias, S. T. (2009) · Current Protocols in Neuroscience · doi:10.1002/0471142301.ns1003s49 · Cited by 19
ON THE FORGETTING OF COLLEGE ACADEMICS: AT "EBBINGHAUS SPEED"?
Subirana, B., Bagiati, A., & Sarma, S. E. (2017) · EDULEARN proceedings · doi:10.21125/edulearn.2017.0672 · Cited by 7
Self-citation“Wake Neutrality” of Artificial Intelligence Devices
Subirana, B., Bivings, R., & Sarma, S. E. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108347846.010 · Cited by 7
Self-citationLongitudinal Speech Biomarkers for Automated Alzheimer's DetectionPreprint
Laguarta, J., Hueto, F., Rajasekaran, P., et al. (2020) · Research Square · doi:10.21203/rs.3.rs-56078/v1 · Cited by 7
Self-citationScreen and Intervene: The Importance of Early Detection and Treatment of Alzheimer's Disease
Galvin, J. E., Tariot, P. N., Parker, M. W., & Jicha, G. A. (2020) · Cited by 6
Córdoba, F. C., Sarma, S. E., & Subirana, B. (2017) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 4
Self-citationCall for a wake standard for artificial intelligence
Subirana, B. (2020) · Communications of the ACM · doi:10.1145/3402193 · Cited by 4
Self-citation
Research works printed but not linked: 2
- 10.1371/journal.pone.0162128 · DOI
- 10.2139/ssrn.3544840 · doi:10.2139/ssrn.3544840 · Paper page
Cited by
End-to-end design of wearable sensors
Ates, H. C., Nguyen, P. Q., Gonzalez-Macia, L., Morales-Narváez, E., Güder, F., Collins, J. J., & Dincer, C. (2022) · Nature Reviews Materials · doi:10.1038/s41578-022-00460-x · Cited by 1,306
COVID-19 cough classification using machine learning and global smartphone recordings
Pahar, M., Klopper, M., Warren, R., & Niesler, T. (2021) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2021.104572 · Cited by 290
Voice for Health: The Use of Vocal Biomarkers from Research to Clinical Practice
Fagherazzi, G., Fischer, A., Ismael, M., & Despotovic, V. (2021) · Digital Biomarkers · doi:10.1159/000515346 · Cited by 216
Robotics and artificial intelligence in healthcare during COVID-19 pandemic: a systematic review
Sarker, S., Jamal, L., Ahmed, S. F., & Irtisam, N. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103902 · Cited by 199
Umair, M., Cheema, M. A., Cheema, O., Li, H., & Lu, H. (2021) · Sensors · doi:10.3390/s21113838 · Cited by 192
Metadata
- Authors
- Laguarta, J., Hueto, F., & Subirana, B.
- Affiliations
- Massachusetts Institute of Technology (US)
- Harvard University (US)
- Corresponding author
- Subirana, Brian
- Venue
- IEEE Open Journal of Engineering in Medicine and Biology
- Published
- 2020
- Volume
- 1
- Pages
- 275-281
- ISSN
- 2644-1276 (ISSN-L)
- PMC
- PMC8545024
- OpenAlex
- W3091468319
- Cited by
- 589
- References
- 42
- Citations by year
- 2026: 21 · 2025: 42 · 2024: 74 · 2023: 102 · 2022: 168 · 2021: 164 · 2020: 16
- FWCI
- 63.42
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- public-domain
- creativecommons.org/licenses/by/4.0/legalcode (vor)
- Locations
- IEEE Open Journal of Engineering in Medicine and Biology (publishedVersion, public-domain)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc)
- 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 › Speech and Hearing › Voice and Speech Disorders
- Keywords
- COVID-19 pandemic, vocal biomarkers, acoustic biomarkers, asymptomatic screening, non-invasive diagnosis, Mel-frequency cepstral coefficients, convolutional neural networks, transfer learning, ResNet50, speech processing, COVID-19 datasets, group testing, outbreak detection, longitudinal patient monitoring
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.