Abstract
The sudden spike in Coronavirus disease 2019 (COVID-19) cases reported by China recently suggests the possible threat of the pandemic’s resurgence. Due to the extremely contagious nature of the virus COVID-19 has already made its presence felt in countries all over the world, since it was reported first in 2019. The delay in detection of the infection resulted in daunting figures of infected patients and over six million fatal casualties have been reported to date. Necessitated by the urgent need for early detection of the disease to contain its spread, and the cost and time implication of the existing testing options, researchers have tried to provide AI-based systems which majorly exploit chest X-ray and Computed Tomography (CT) scan images. Our work explores the possibility of a real-time non-invasive screening tool for early detection of the disease through audio data like cough, resulting from respiratory tract infection which is an early symptom of COVID-19. In this paper, we have proposed a Long Short-Term Memory (LSTM)-based Deep Learning approach for the detection of COVID-19, using the Pfizer Digital Medicine Challenge dataset which contains audio signals of sneezing, coughing, and breath, classified as sick or not sick. Our proposed model obtained a training accuracy of 96.74% with a binary cross-entropy loss of 8.04%. The experimental results show an accuracy of 96.24% which is significantly higher than the previous study on the same dataset which resulted in an accuracy of 80.26%, suggesting that the proposed model is better in terms of classification efficiency.
Similar content being viewed by others
Data availability
The dataset that supports the findings of this work is available on the “OSFHOME” open-access platform at https://osf.io/tmkud/.
References
Rahman T, Ibtehaz N, Khandakar A, Hossain MSA, Mekki YMS, Ezeddin M, Bhuiyan EH, Ayari MA, Tahir A, Qiblawey Y, Mahmud S, Zughaier SM, Abbas T, Al-Maadeed S, Chowdhury MEH. QUCoughScope: An intelligent application to detect COVID-19 patients using cough and breath sounds. MDPI. 2022. Retrieved April 7, 2022, from https://www.mdpi.com/2075-4418/12/4/920
Laguarta J, Hueto F, Subirana B. Covid-19 artificial intelligence diagnosis using only cough recordings. IEEE Open J Eng Med Biol. 2020;1:275–81. https://doi.org/10.1109/ojemb.2020.3026928.
Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9(8):1735–80. https://doi.org/10.1162/neco.1997.9.8.1735.
Elpeltagy M, Sallam H. Automatic prediction of COVID− 19 from chest images using modified Resnet50. Multimed Tools Appl. 2021. https://doi.org/10.1007/s11042-021-10783-6.
Jaiswal A, Gianchandani N, Singh D, Kumar V, Kaur M. Classification of the COVID-19 infected patients using DENSENET201 based deep transfer learning. J Biomol Struct Dyn. 2020;39(15):5682–9. https://doi.org/10.1080/07391102.2020.1788642.
Acar E, Yilmaz İ. Covid-19 detection on IBM quantum computer with classical-quantum transfer learning. Turk J Electr Eng Comput Sci. 2021;29(1):46–61. https://doi.org/10.3906/elk-2006-94.
Kundu R, Singh PK, Ferrara M, Ahmadian A, Sarkar R. ET-net: an ensemble of transfer learning models for prediction of COVID-19 infection through chest CT-scan images. Multimed Tools Appl. 2021;81(1):31–50. https://doi.org/10.1007/s11042-021-11319-8.
Gifani P, Shalbaf A, Vafaeezadeh M. Automated detection of COVID-19 using ensemble of transfer learning with deep convolutional neural network based on CT scans. Int J Comput Assist Radiol Surg. 2020;16(1):115–23. https://doi.org/10.1007/s11548-020-02286-w.
Aslan MF, Unlersen MF, Sabanci K, Durdu A. CNN-based Transfer Learning–BILSTM network: a novel approach for COVID-19 infection detection. Appl Soft Comput. 2021;98:106912. https://doi.org/10.1016/j.asoc.2020.106912.
Chakraborty S, Paul S, Hasan KM. A transfer learning-based approach with deep CNN for Covid-19- and pneumonia-affected chest X-ray image classification. SN Comput Sci. 2021. https://doi.org/10.1007/s42979-021-00881-5.
Rahman MDA, Hossain MS, Alrajeh NA, Gupta BB. A multimodal, multimedia point-of-care deep learning framework for covid-19 diagnosis. ACM Trans Multimed Comput Commun Appl. 2021;17(1s):1–24. https://doi.org/10.1145/3421725.
Elzeki OM, Shams M, Sarhan S, Abd Elfattah M, Hassanien AE. Covid-19: a new deep learning computer-aided model for classification. PeerJ Comput Sci. 2021. https://doi.org/10.7717/peerj-cs.358.
Momeny M, Neshat AA, Hussain MA, Kia S, Marhamati M, Jahanbakhshi A, Hamarneh G. Learning-to-augment strategy using noisy and denoised data: Improving generalizability of deep CNN for the detection of covid-19 in X-ray images. Comput Biol Med. 2021;136:104704. https://doi.org/10.1016/j.compbiomed.2021.104704.
Calderon-Ramirez S, Giri R, Yang S, Moemeni A, Umana M, Elizondo D, Torrents-Barrena J, Molina-Cabello MA. Dealing with scarce labelled data: semi-supervised deep learning with mix match for COVID-19 detection using chest X-ray images. 2020 25th Int Conf Pattern Recogn (ICPR). 2021. https://doi.org/10.1109/icpr48806.2021.9412946.
Higenbottam T. Chronic cough and the cough reflex in common lung diseases. Pulm Pharmacol Ther. 2002;15(3):241–7. https://doi.org/10.1006/pupt.2002.0341.
Windmon A, Minakshi M, Bharti P, Chellappan S, Johansson M, Jenkins BA, Athilingam PR. TussisWatch: a smart-phone system to identify cough episodes as early symptoms of chronic obstructive pulmonary disease and congestive heart failure. IEEE J Biomed Health Inform. 2019;23(4):1566–73. https://doi.org/10.1109/jbhi.2018.2872038.
Deshpande G, Batliner A, Schuller BW. AI-based human audio processing for COVID-19: a comprehensive overview. Pattern Recogn. 2022;122:108289. https://doi.org/10.1016/j.patcog.2021.108289.
Brown C, Chauhan J, Grammenos A, Han J, Hasthanasombat A, Spathis D, Xia T, Cicuta P, Mascolo C. Exploring automatic diagnosis of COVID-19 from crowdsourced respiratory sound data. Proc 26th ACM SIGKDD Int Conf Knowl Discov Data Min. 2020. https://doi.org/10.1145/3394486.3412865.
Pahar M, Klopper M, Warren R, Niesler T. Covid-19 cough classification using machine learning and Global smartphone recordings. Comput Biol Med. 2021;135:104572. https://doi.org/10.1016/j.compbiomed.2021.104572.
Khriji L, Ammari A, Messaoud S, Bouaafia S, Maraoui A, Machhout M. Covid-19 recognition based on patient’s coughing and breathing patterns analysis: deep learning approach. 2021 29th Conf Open Innov Assoc. 2021. https://doi.org/10.23919/fruct52173.2021.9435454.
Patel S, Rivas A, Psaltos D. Dataset of sounds of symptoms associated with respiratory sickness. OSF. 2002. Retrieved February 11, 2022, from https://osf.io/tmkud/
Nessiem MA, Mohamed MM, Coppock H, Gaskell A, Schuller BW. “Detecting COVID-19 from breathing and coughing sounds using deep neural networks.” Proceedings of the IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS). pp 183–188. https://doi.org/10.1109/CBMS52027.2021.00069
Chaudhari G, Jiang X, Fakhry A, Han A, Xiao J, Shen S, Khanzada A. Virufy: Global applicability of crowdsourced and clinical datasets for AI detection of covid-19 from cough. (2021) arXiv.org. Retrieved August 14, 2022, from https://arxiv.org/abs/2011.13320
Melek N. Responding to challenge call of machine learning model development in diagnosing respiratory disease sounds. DeepAI. 2021. https://doi.org/10.48550/arXiv.2111.14354.
McFee B, Raffel C, Liang D, Ellis D, McVicar M, Battenberg E, Nieto O. Librosa: Audio and Music Signal Analysis in python. Proceedings of the 14th Python in Science Conference. 2015. https://doi.org/10.25080/majora-7b98e3ed-003
Audio feature extraction—audio classification and keyword spotting. Coursera. (n.d.). Retrieved August 19, 2022, from https://www.coursera.org/lecture/introduction-to-embedded-machine-learning/audio-feature-extraction-VxDmo
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
On behalf of all the authors, the corresponding author states that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article is part of the topical collection “Research Trends in Computational Intelligence” guest edited by Anshul Verma, Pradeepika Verma, Vivek Kumar Singh and S. Karthikeyan.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Malviya, A., Dixit, R., Shukla, A. et al. Long Short-Term Memory-based Deep Learning Model for COVID-19 Detection using Coughing Sound. SN COMPUT. SCI. 4, 505 (2023). https://doi.org/10.1007/s42979-023-01934-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-023-01934-7