{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T16:02:11Z","timestamp":1788278531709,"version":"build-2803163510"},"reference-count":49,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T00:00:00Z","timestamp":1664323200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Private Physiotherapy Education Fund","award":["349"],"award-info":[{"award-number":["349"]}]},{"name":"Private Physiotherapy Education Fund","award":["368"],"award-info":[{"award-number":["368"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Mild traumatic brain injury (mTBI or concussion) is receiving increased attention due to the incidence in contact sports and limitations with subjective (pen and paper) diagnostic approaches. If an mTBI is undiagnosed and the athlete prematurely returns to play, it can result in serious short-term and\/or long-term health complications. This demonstrates the importance of providing more reliable mTBI diagnostic tools to mitigate misdiagnosis. Accordingly, there is a need to develop reliable and efficient objective approaches with computationally robust diagnostic methods. Here in this pilot study, we propose the extraction of Mel Frequency Cepstral Coefficient (MFCC) features from audio recordings of speech that were collected from athletes engaging in rugby union who were diagnosed with an mTBI or not. These features were trained on our novel particle swarm optimised (PSO) bidirectional long short-term memory attention (Bi-LSTM-A) deep learning model. Little-to-no overfitting occurred during the training process, indicating strong reliability of the approach regarding the current test dataset classification results and future test data. Sensitivity and specificity to distinguish those with an mTBI were 94.7% and 86.2%, respectively, with an AUROC score of 0.904. This indicates a strong potential for the deep learning approach, with future improvements in classification results relying on more participant data and further innovations to the Bi-LSTM-A model to fully establish this approach as a pragmatic mTBI diagnostic tool.<\/jats:p>","DOI":"10.1371\/journal.pone.0274395","type":"journal-article","created":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T17:48:21Z","timestamp":1664387301000},"page":"e0274395","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":13,"title":["A deep learning-based approach to diagnose mild traumatic brain injury using audio classification"],"prefix":"10.1371","volume":"17","author":[{"given":"Conor","family":"Wall","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dylan","family":"Powell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fraser","family":"Young","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0663-7320","authenticated-orcid":true,"given":"Aaron J.","family":"Zynda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sam","family":"Stuart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tracey","family":"Covassin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4049-9291","authenticated-orcid":true,"given":"Alan","family":"Godfrey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2022,9,28]]},"reference":[{"issue":"no. 4","key":"pone.0274395.ref001","doi-asserted-by":"crossref","first-page":"1080","DOI":"10.3171\/2017.10.JNS17352","article-title":"Estimating the global incidence of traumatic brain injury","volume":"vol. 130","author":"M. C. Dewan","year":"2019","journal-title":"Journal of Neurosurgery"},{"issue":"no. 11","key":"pone.0274395.ref002","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1503\/cmaj.120039","article-title":"Concussions and their consequences: current diagnosis, management and prevention","volume":"vol. 185","author":"C. H. Tator","year":"2013","journal-title":"CMAJ"},{"issue":"no. 10","key":"pone.0274395.ref003","doi-asserted-by":"crossref","DOI":"10.1001\/archneurol.2011.3747","article-title":"Dementia Resulting From Traumatic Brain Injury: What Is the Pathology?","volume":"vol. 69","author":"S. Shively","year":"2012","journal-title":"Arch Neurol"},{"key":"pone.0274395.ref004","doi-asserted-by":"crossref","unstructured":"\u2018Sport concussion assessment tool\u20145th edition\u2019, Br J Sports Med, p. bjsports-2017-097506SCAT5, Apr. 2017.","DOI":"10.1136\/bjsports-2017-097506SCAT5"},{"issue":"164","key":"pone.0274395.ref005","article-title":"Sports related concussion: An emerging era in digital sports technology","volume":"vol. 4","author":"D Powell","year":"2021","journal-title":"npj Digital Medicine"},{"issue":"no. 7","key":"pone.0274395.ref006","first-page":"426","article-title":"Current Concepts in Concussion: Initial Evaluation and Management","volume":"vol. 99","author":"K. A. Scorza","year":"2019","journal-title":"Am Fam Physician"},{"issue":"3","key":"pone.0274395.ref007","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/j.jshs.2017.03.009","article-title":"Concussion in contact sport: A challenging area to tackle","volume":"6","author":"S. Stuart","year":"2017","journal-title":"Journal of Sport and Health Science"},{"issue":"no. 1","key":"pone.0274395.ref008","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1186\/s40798-019-0187-y","article-title":"Objective Classification of mTBI Using Machine Learning on a Combination of Frontopolar Electroencephalography Measurements and Self-reported Symptoms","volume":"vol. 5","author":"M. W. McNerney","year":"2019","journal-title":"Sports Med\u2014Open"},{"issue":"no. 2","key":"pone.0274395.ref009","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1109\/JBHI.2016.2633509","article-title":"Portable mTBI Assessment Using Temporal and Frequency Analysis of Speech","volume":"vol. 21","author":"L. Daudet","year":"2017","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"pone.0274395.ref010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2021\/6635964","article-title":"Comparative Analysis of CNN and RNN for Voice Pathology Detection","volume":"2021","author":"S. Syed","year":"2021","journal-title":"BioMed Research International"},{"key":"pone.0274395.ref011","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1016\/j.neucom.2020.07.053","article-title":"Survey on Deep Neural Networks in Speech and Vision Systems","volume":"417","author":"M. Alam","year":"2020","journal-title":"Neurocomputing"},{"issue":"10","key":"pone.0274395.ref012","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1136\/bjsports-2020-102072","article-title":"Use of the Sport Concussion Assessment Tool 5 (SCAT5) in professional hockey, part 2: which components differentiate concussed and non-concussed players?","volume":"55","author":"J. Bruce","year":"2020","journal-title":"British Journal of Sports Medicine"},{"issue":"12","key":"pone.0274395.ref013","doi-asserted-by":"crossref","first-page":"e0189583","DOI":"10.1371\/journal.pone.0189583","article-title":"Towards the identification of Idiopathic Parkinson\u2019s Disease from the speech. New articulatory kinetic biomarkers","volume":"12","author":"J. Godino-Llorente","year":"2017","journal-title":"PLOS ONE"},{"issue":"2","key":"pone.0274395.ref014","doi-asserted-by":"crossref","first-page":"130","DOI":"10.2174\/1567205014666171121114930","article-title":"A Speech Recognition-based Solution for the Automatic Detection of Mild Cognitive Impairment from Spontaneous Speech","volume":"15","author":"L. Toth","year":"2018","journal-title":"Current Alzheimer Research"},{"issue":"4","key":"pone.0274395.ref015","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1109\/TBME.2008.2005954","article-title":"Suitability of Dysphonia Measurements for Telemonitoring of Parkinson\u2019s Disease","volume":"56","author":"M. Little","year":"2009","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"pone.0274395.ref016","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1109\/ACCESS.2015.2457392","article-title":"Challenges in Concussion Detection Using Vocal Acoustic Biomarkers","volume":"3","author":"C. Poellabauer","year":"2015","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0274395.ref017","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/MASSP.1986.1165342","article-title":"An introduction to hidden Markov models","volume":"3","author":"L. Rabiner","year":"1986","journal-title":"ieee assp magazine"},{"key":"pone.0274395.ref018","doi-asserted-by":"crossref","first-page":"4","DOI":"10.3389\/frai.2020.00004","article-title":"An Introductory Review of Deep Learning for Prediction Models With Big Data","volume":"vol. 3","author":"F. Emmert-Streib","year":"2020","journal-title":"Front. Artif. Intell."},{"key":"pone.0274395.ref019","doi-asserted-by":"crossref","unstructured":"C. Wall, L. Zhang, Y. Yu, and K. Mistry, \u2018Deep Recurrent Neural Networks with Attention Mechanisms for Respiratory Anomaly Classification\u2019, in 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China, Jul. 2021, pp. 1\u20138.","DOI":"10.1109\/IJCNN52387.2021.9533966"},{"key":"pone.0274395.ref020","doi-asserted-by":"crossref","unstructured":"T. Talkar et al., \u2018Detection of Subclinical Mild Traumatic Brain Injury (mTBI) Through Speech and Gait\u2019, in Interspeech 2020, Oct. 2020, pp. 135\u2013139.","DOI":"10.21437\/Interspeech.2020-2651"},{"key":"pone.0274395.ref021","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1007\/978-0-387-73003-5_196","volume-title":"Encyclopedia of Biometrics","author":"D. Reynolds","year":"2009"},{"issue":"no. 1","key":"pone.0274395.ref022","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: concepts, CNN architectures, challenges, applications, future directions","volume":"vol. 8","author":"L. Alzubaidi","year":"2021","journal-title":"J Big Data"},{"issue":"11","key":"pone.0274395.ref023","doi-asserted-by":"crossref","first-page":"99","DOI":"10.14257\/ijsip.2016.9.11.10","article-title":"A Comparison and Contrast of the Various Feature Extraction Techniques in Speaker Recognition","volume":"9","author":"J. Joshy","year":"2016","journal-title":"International Journal of Signal Processing, Image Processing and Pattern Recognition"},{"key":"pone.0274395.ref024","doi-asserted-by":"crossref","unstructured":"Kamarulafizam, I., Salleh, S., Najeb, J., Ariff, A. and Chowdhury, A., 2007. Heart Sound Analysis Using MFCC and Time Frequency Distribution. 3rd Kuala Lumpur International Conference on Biomedical Engineering 2006, pp.402\u2013405.","DOI":"10.1007\/978-3-540-68017-8_102"},{"issue":"6","key":"pone.0274395.ref025","first-page":"1","article-title":"Feature extraction methods LPC, PLP and MFCC in speech recognition","volume":"1","author":"N. Dave","year":"2013","journal-title":"International journal for advance research in engineering and technology"},{"key":"pone.0274395.ref026","volume-title":"Speech communication: human and machine","author":"D. O\u2019Shaughnessy","year":"1987"},{"key":"pone.0274395.ref027","doi-asserted-by":"crossref","unstructured":"S. Braun, \u2018WINDOWS\u2019, in Encyclopedia of Vibration, Elsevier, 2001, pp. 1587\u20131595.","DOI":"10.1006\/rwvb.2001.0052"},{"key":"pone.0274395.ref028","doi-asserted-by":"crossref","first-page":"19143","DOI":"10.1109\/ACCESS.2019.2896880","article-title":"Speech Recognition Using Deep Neural Networks: A Systematic Review","volume":"vol. 7","author":"A. B. Nassif","year":"2019","journal-title":"IEEE Access"},{"issue":"8","key":"pone.0274395.ref029","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"S. Hochreiter","year":"1997","journal-title":"Neural computation"},{"key":"pone.0274395.ref030","doi-asserted-by":"crossref","unstructured":"Swedia, E., Mutiara, A., Subali, M. and Ernastuti, 2018. Deep Learning Long-Short Term Memory (LSTM) for Indonesian Speech Digit Recognition using LPC and MFCC Feature. 2018 Third International Conference on Informatics and Computing (ICIC).","DOI":"10.1109\/IAC.2018.8780566"},{"issue":"no. 17","key":"pone.0274395.ref031","doi-asserted-by":"crossref","first-page":"3470","DOI":"10.3390\/app9173470","article-title":"Bidirectional Long Short-Term Memory Neural Networks for Linear Sum Assignment Problems","volume":"vol. 9","author":"N. Minh-Tuan","year":"2019","journal-title":"Applied Sciences"},{"issue":"no. 8","key":"pone.0274395.ref032","doi-asserted-by":"crossref","first-page":"1539","DOI":"10.3390\/app9081539","article-title":"Attention-Based LSTM Algorithm for Audio Replay Detection in Noisy Environments","volume":"vol. 9","author":"J. Li","year":"2019","journal-title":"Applied Sciences"},{"key":"pone.0274395.ref033","doi-asserted-by":"crossref","first-page":"896","DOI":"10.1016\/j.neucom.2020.08.069","article-title":"Attention based convolutional recurrent neural network for environmental sound classification","volume":"vol. 453","author":"Z. Zhang","year":"2021","journal-title":"Neurocomputing"},{"key":"pone.0274395.ref034","doi-asserted-by":"crossref","unstructured":"K.J. Piczak, \u201cESC: Dataset for Environmental Sound Classification\u201d, In Proceedings of the 23rd ACM international conference on Multimedia (pp. 1015\u20131018). 2015.","DOI":"10.1145\/2733373.2806390"},{"issue":"12","key":"pone.0274395.ref035","doi-asserted-by":"crossref","first-page":"e0261616","DOI":"10.1371\/journal.pone.0261616","article-title":"Wearables in rugby union: A protocol for multimodal digital sports-related concussion assessment","volume":"16","author":"D. Powell","year":"2021","journal-title":"PLOS ONE"},{"key":"pone.0274395.ref036","unstructured":"Speechtools.co. 2022. Speech Tools. [online] <https:\/\/speechtools.co\/voice-analyst> [Accessed 10 January 2022]."},{"key":"pone.0274395.ref037","doi-asserted-by":"crossref","unstructured":"B. McFee et al., \u2018librosa: Audio and Music Signal Analysis in Python\u2019, Austin, Texas, 2015, pp. 18\u201324.","DOI":"10.25080\/Majora-7b98e3ed-003"},{"issue":"14","key":"pone.0274395.ref038","doi-asserted-by":"crossref","first-page":"5469","DOI":"10.1007\/s00500-018-3199-5","article-title":"PSO-based improved multi-flocks migrating birds optimization (IMFMBO) algorithm for solution of discrete problems","volume":"23","author":"V. Tongur","year":"2019","journal-title":"Soft Computing"},{"issue":"5","key":"pone.0274395.ref039","doi-asserted-by":"crossref","first-page":"e0122827","DOI":"10.1371\/journal.pone.0122827","article-title":"A Comprehensive Review of Swarm Optimization Algorithms","volume":"10","author":"M. Ab Wahab","year":"2015","journal-title":"PLOS ONE"},{"key":"pone.0274395.ref040","doi-asserted-by":"crossref","unstructured":"B. Qolomany, M. Maabreh, A. Al-Fuqaha, A. Gupta, and D. Benhaddou, \u2018Parameters optimization of deep learning models using Particle swarm optimization\u2019, in 2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC), Valencia, Spain, Jun. 2017, pp. 1285\u20131290.","DOI":"10.1109\/IWCMC.2017.7986470"},{"issue":"No. 4","key":"pone.0274395.ref041","doi-asserted-by":"crossref","first-page":"79","DOI":"10.3390\/informatics8040079","article-title":"Hyperparameter tuning for machine learning algorithms used for arabic sentiment analysis","volume":"Vol. 8","author":"E. Elgeldawi","year":"2021","journal-title":"Informatics"},{"issue":"1","key":"pone.0274395.ref042","doi-asserted-by":"crossref","first-page":"148","DOI":"10.5539\/mas.v12n1p148","article-title":"Movement Particle Swarm Optimization Algorithm","volume":"12","author":"A. Hudaib","year":"2017","journal-title":"Modern Applied Science"},{"issue":"no. 56","key":"pone.0274395.ref043","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks from Overfitting","volume":"vol. 15","author":"N. Srivastava","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"pone.0274395.ref044","unstructured":"L. Prechelt, \u2018Early Stopping\u2014But When?\u2019, Mar. 2000."},{"issue":"no. 4","key":"pone.0274395.ref045","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1007\/s13244-018-0639-9","article-title":"Convolutional neural networks: an overview and application in radiology","volume":"vol. 9","author":"R. Yamashita","year":"2018","journal-title":"Insights Imaging"},{"key":"pone.0274395.ref046","doi-asserted-by":"crossref","unstructured":"Ying, X., 2019. An Overview of Overfitting and its Solutions. Journal of Physics: Conference Series, 1168, p.022022.","DOI":"10.1088\/1742-6596\/1168\/2\/022022"},{"key":"pone.0274395.ref047","doi-asserted-by":"crossref","unstructured":"Hosmer Jr, D.W., Lemeshow, S. and Sturdivant, R.X., 2013. Applied logistic regression (Vol. 398). John Wiley & Sons.","DOI":"10.1002\/9781118548387"},{"issue":"1","key":"pone.0274395.ref048","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13049-018-0495-0","article-title":"The epidemiology of mild traumatic brain injury: the Trondheim MTBI follow-up study","volume":"26","author":"T. Skandsen","year":"2018","journal-title":"Scandinavian journal of trauma, resuscitation and emergency medicine"},{"issue":"no. 10\u201311","key":"pone.0274395.ref049","doi-asserted-by":"crossref","first-page":"763","DOI":"10.1016\/j.specom.2007.02.006","article-title":"Automatic speech recognition and speech variability: A review","volume":"vol. 49","author":"M. Benzeghiba","year":"2007","journal-title":"Speech Communication"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0274395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T17:49:15Z","timestamp":1664387355000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0274395"}},"subtitle":[],"editor":[{"given":"Omar A.","family":"Alzubi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2022,9,28]]},"references-count":49,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2022,9,28]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0274395","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,28]]}}}