{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T18:09:58Z","timestamp":1779214198677,"version":"3.51.4"},"reference-count":43,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","award":["HK23C0071"],"award-info":[{"award-number":["HK23C0071"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["2022R1C1C1006057"],"award-info":[{"award-number":["2022R1C1C1006057"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Needle electromyography (nEMG) is a valuable tool for diagnosing patients with neuromuscular diseases. However, it is labor-intensive and is prone to diagnostic inaccuracies stemming from human biases. To address these challenges, we validated an nEMG diagnosis-aiding system with minimal preprocessing using deep learning model to classify patients into three categories: normal, myopathy, and neuropathy. Using 376 nEMG signals from 57 patients from a tertiary university hospital database through nested k-fold cross validation, deep learning model surpassed the classification performance of six electromyographers. The median patient classification accuracy, precision, sensitivity, and specificity of the deep learning model was 0.70, 0.70, 0.70, and 0.85, respectively, whereas those of the physicians were 0.55, 0.60, 0.54, and 0.78, respectively. Model interpretability and failure analysis showed that the deep learning model classifies based on relevant signal features. Despite higher accuracy of DL model, the number of unanimously misclassified cases were higher in the DL model than physicians. Our study validates deep learning is a fast, accurate, and practical application to aid physicians in diagnosing patients using nEMG signals.<\/jats:p>","DOI":"10.1371\/journal.pone.0339691","type":"journal-article","created":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T17:38:16Z","timestamp":1779212296000},"page":"e0339691","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Learning outperforms physicians in myopathy and neuropathy classification based on Needle Electromyography Signal"],"prefix":"10.1371","volume":"21","author":[{"given":"Ilhan","family":"Yoo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaesung","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongmin","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ina","family":"Youn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyodong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michelle","family":"Youn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun Hee","family":"Won","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Woosup","family":"Cho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youho","family":"Myong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sehoon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ri","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sung-Min","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4586-5062","authenticated-orcid":true,"given":"Kwangsoo","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6817-5793","authenticated-orcid":true,"given":"Seung-Bo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6597-578X","authenticated-orcid":true,"given":"Keewon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,5,19]]},"reference":[{"issue":"2","key":"pone.0339691.ref001","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1002\/mus.21180","article-title":"Needle electromyography","volume":"39","author":"JR Daube","year":"2009","journal-title":"Muscle Nerve"},{"key":"pone.0339691.ref002","doi-asserted-by":"crossref","DOI":"10.1093\/med\/9780199738687.001.0001","volume-title":"Electrodiagnosis in diseases of nerve and muscle: principles and practice","author":"J Kimura","year":"2013"},{"key":"pone.0339691.ref003","article-title":"The basics of electromyography","author":"KR Mills","year":"2005","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"pone.0339691.ref004","volume-title":"Clinical electromyography: nerve conduction studies","author":"SJ Oh","year":"2003"},{"key":"pone.0339691.ref005","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/B978-0-444-64032-1.00016-3","article-title":"Needle electromyography: Basic concepts","volume":"160","author":"DI Rubin","year":"2019","journal-title":"Handb Clin Neurol"},{"issue":"3","key":"pone.0339691.ref006","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1136\/practneurol-2011-000198","article-title":"The fundamentals of electromyography","volume":"12","author":"RG Whittaker","year":"2012","journal-title":"Pract Neurol"},{"issue":"10","key":"pone.0339691.ref007","doi-asserted-by":"crossref","first-page":"1514","DOI":"10.1212\/WNL.35.10.1514","article-title":"Electrophysiologic evaluation of lumbosacral radiculopathies: electromyography, late responses, and somatosensory evoked potentials","volume":"35","author":"MJ Aminoff","year":"1985","journal-title":"Neurology"},{"issue":"2","key":"pone.0339691.ref008","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1002\/mus.26718","article-title":"The motor unit and quantitative electromyography","volume":"61","author":"MB Bromberg","year":"2020","journal-title":"Muscle Nerve"},{"issue":"4","key":"pone.0339691.ref009","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/j.reumae.2011.10.004","article-title":"Use of electromyography in the diagnosis of inflammatory myopathies","volume":"8","author":"G Guti\u00e9rrez Guti\u00e9rrez","year":"2012","journal-title":"Reumatolog\u00eda Cl\u00ednica (English Edition)"},{"issue":"12","key":"pone.0339691.ref010","doi-asserted-by":"crossref","first-page":"1879","DOI":"10.1212\/WNL.38.12.1879","article-title":"Diagnostic value of different electrophysiologic tests in cervical disk prolapse","volume":"38","author":"F Leblhuber","year":"1988","journal-title":"Neurology"},{"issue":"7","key":"pone.0339691.ref011","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1002\/pmrj.12281","article-title":"Usefulness of Electromyography to Predict Future Muscle Weakness in Clinically Unaffected Muscles of Polio Survivors","volume":"12","author":"K Sawada","year":"2020","journal-title":"PM R"},{"issue":"3","key":"pone.0339691.ref012","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1002\/ana.410090317","article-title":"Usefulness of electrophysiological studies in the diagnosis of lumbosacral root disease","volume":"9","author":"RF Tonzola","year":"1981","journal-title":"Ann Neurol"},{"issue":"2","key":"pone.0339691.ref013","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1002\/mus.20554","article-title":"Interrater reliability of the needle examination in lumbosacral radiculopathy","volume":"34","author":"R Kendall","year":"2006","journal-title":"Muscle Nerve"},{"key":"pone.0339691.ref014","doi-asserted-by":"crossref","first-page":"12408","DOI":"10.1038\/ncomms12408","article-title":"Projected increase in amyotrophic lateral sclerosis from 2015 to 2040","volume":"7","author":"KC Arthur","year":"2016","journal-title":"Nat Commun"},{"issue":"5","key":"pone.0339691.ref015","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1097\/WCO.0000000000000730","article-title":"Epidemiology of amyotrophic lateral sclerosis: an update of recent literature","volume":"32","author":"E Longinetti","year":"2019","journal-title":"Curr Opin Neurol"},{"issue":"2","key":"pone.0339691.ref016","article-title":"Increasing incidence of adult idiopathic inflammatory myopathies in the City of Salford, UK: a 10-year epidemiological study","volume":"2","author":"MJS Parker","year":"2018","journal-title":"Rheumatol Adv Pract"},{"issue":"3","key":"pone.0339691.ref017","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0210574","article-title":"Trends in incidence, prevalence, and mortality of neuromuscular disease in Ontario, Canada: A population-based retrospective cohort study (2003-2014)","volume":"14","author":"L Rose","year":"2019","journal-title":"PLoS One"},{"key":"pone.0339691.ref018","volume-title":"Deep learning","author":"I Goodfellow","year":"2016"},{"key":"pone.0339691.ref019","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1038\/s41746-019-0157-2","article-title":"Putting the data before the algorithm in big data addressing personalized healthcare","volume":"2","author":"EM Cahan","year":"2019","journal-title":"NPJ Digit Med"},{"key":"pone.0339691.ref020","doi-asserted-by":"crossref","first-page":"110239","DOI":"10.1016\/j.compbiomed.2025.110239","article-title":"Review learning: Real world validation of privacy preserving continual learning across medical institutions","volume":"192","author":"J Yoo","year":"2025","journal-title":"Comput Biol Med"},{"issue":"1","key":"pone.0339691.ref021","doi-asserted-by":"crossref","first-page":"15","DOI":"10.5391\/JKIIS.2024.34.1.15","article-title":"Dual Policy as Self-Model for Planning","volume":"34","author":"J Yoo","year":"2024","journal-title":"JKIIS"},{"key":"pone.0339691.ref022","doi-asserted-by":"crossref","DOI":"10.3389\/fphy.2019.00103","article-title":"A fast machine learning model for ECG-based heartbeat classification and arrhythmia detection","volume":"7","author":"M Alfaras","year":"2019","journal-title":"Frontiers in Physics"},{"key":"pone.0339691.ref023","doi-asserted-by":"crossref","unstructured":"Lu X, Wu Y, Yan R, Cao S, Wang K, Mou S, et al. Pulse waveform analysis for pregnancy diagnosis based on machine learning. In: 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), 2018. 1075\u20139. https:\/\/doi.org\/10.1109\/iaeac.2018.8577535","DOI":"10.1109\/IAEAC.2018.8577535"},{"key":"pone.0339691.ref024","doi-asserted-by":"crossref","first-page":"117021","DOI":"10.1016\/j.neuroimage.2020.117021","article-title":"Machine-learning-based diagnostics of EEG pathology","volume":"220","author":"LAW Gemein","year":"2020","journal-title":"Neuroimage"},{"issue":"5","key":"pone.0339691.ref025","doi-asserted-by":"crossref","first-page":"051001","DOI":"10.1088\/1741-2552\/ab260c","article-title":"Deep learning-based electroencephalography analysis: a systematic review","volume":"16","author":"Y Roy","year":"2019","journal-title":"J Neural Eng"},{"issue":"11","key":"pone.0339691.ref026","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1002699","article-title":"Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet","volume":"15","author":"N Bien","year":"2018","journal-title":"PLoS Med"},{"issue":"1","key":"pone.0339691.ref027","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1038\/s41591-018-0268-3","article-title":"Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network","volume":"25","author":"AY Hannun","year":"2019","journal-title":"Nat Med"},{"issue":"11","key":"pone.0339691.ref028","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1002686","article-title":"Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists","volume":"15","author":"P Rajpurkar","year":"2018","journal-title":"PLoS Med"},{"key":"pone.0339691.ref029","doi-asserted-by":"crossref","first-page":"109322","DOI":"10.1016\/j.jbiomech.2019.109322","article-title":"Neural muscle activation detection: A deep learning approach using surface electromyography","volume":"95","author":"I Akef Khowailed","year":"2019","journal-title":"J Biomech"},{"key":"pone.0339691.ref030","doi-asserted-by":"crossref","first-page":"9","DOI":"10.3389\/fnbot.2016.00009","article-title":"Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands","volume":"10","author":"M Atzori","year":"2016","journal-title":"Front Neurorobot"},{"issue":"2","key":"pone.0339691.ref031","doi-asserted-by":"crossref","first-page":"131","DOI":"10.4258\/hir.2019.25.2.131","article-title":"Development of Artificial Intelligence to Support Needle Electromyography Diagnostic Analysis","volume":"25","author":"S Nam","year":"2019","journal-title":"Healthc Inform Res"},{"issue":"5","key":"pone.0339691.ref032","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1016\/j.clinph.2019.01.024","article-title":"Deep learning for waveform identification of resting needle electromyography signals","volume":"130","author":"H Nodera","year":"2019","journal-title":"Clin Neurophysiol"},{"issue":"10","key":"pone.0339691.ref033","doi-asserted-by":"crossref","first-page":"2964","DOI":"10.1109\/TBME.2019.2899222","article-title":"Surface-Electromyography-Based Gesture Recognition by Multi-View Deep Learning","volume":"66","author":"W Wei","year":"2019","journal-title":"IEEE Trans Biomed Eng"},{"key":"pone.0339691.ref034","doi-asserted-by":"crossref","first-page":"107079","DOI":"10.1016\/j.cmpb.2022.107079","article-title":"Residual one-dimensional convolutional neural network for neuromuscular disorder classification from needle electromyography signals with explainability","volume":"226","author":"J Yoo","year":"2022","journal-title":"Comput Methods Programs Biomed"},{"issue":"2","key":"pone.0339691.ref035","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.2020200029","article-title":"Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A Guide for Authors and Reviewers","volume":"2","author":"J Mongan","year":"2020","journal-title":"Radiol Artif Intell"},{"key":"pone.0339691.ref036","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.clinph.2023.12.134","article-title":"Artificial intelligence for automatic classification of needle EMG signals: A scoping review","volume":"159","author":"S de Jonge","year":"2024","journal-title":"Clin Neurophysiol"},{"key":"pone.0339691.ref037","first-page":"55","volume-title":"Early stopping - but when?","author":"L Prechelt","year":"1998"},{"key":"pone.0339691.ref038","first-page":"8792","article-title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","volume":"32","author":"Z Zhang","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"issue":"11","key":"pone.0339691.ref039","doi-asserted-by":"crossref","DOI":"10.23915\/distill.00007","article-title":"Feature Visualization","volume":"2","author":"C Olah","year":"2017","journal-title":"Distill"},{"issue":"1","key":"pone.0339691.ref040","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1093\/jamiaopen\/ooy012","article-title":"tableone: An open source Python package for producing summary statistics for research papers","volume":"1","author":"TJ Pollard","year":"2018","journal-title":"JAMIA Open"},{"issue":"12","key":"pone.0339691.ref041","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0261983","article-title":"Prevalence and incidence of neuromuscular conditions in the UK between 2000 and 2019: A retrospective study using primary care data","volume":"16","author":"IM Carey","year":"2021","journal-title":"PLoS One"},{"key":"pone.0339691.ref042","doi-asserted-by":"crossref","first-page":"1295396","DOI":"10.3389\/fneur.2023.1295396","article-title":"Electromyography varies by stage in inclusion body myositis","volume":"14","author":"T Mano","year":"2024","journal-title":"Front Neurol"},{"issue":"3","key":"pone.0339691.ref043","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1002\/mus.28023","article-title":"The role of artificial intelligence in electrodiagnostic and neuromuscular medicine: Current state and future directions","volume":"69","author":"MA Taha","year":"2024","journal-title":"Muscle Nerve"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0339691","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T17:38:23Z","timestamp":1779212303000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0339691"}},"subtitle":[],"editor":[{"given":"Claudia","family":"Brogna","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":43,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5,19]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0339691","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,19]]}}}