Dysphagia screening with sEMG, accelerometry and speech: Multimodal machine and deep learning approaches

Vista sencilla de ítem
dc.contributor.affiliationRoldan-Vasco, S., Faculty of Engineering, Instituto Tecnológico Metropolitano, Medellín, Colombia, GITA Lab. Faculty of Engineering, Universidad de Antioquia, Medellín, Colombia
dc.contributor.affiliationOrozco-Duque, A., Faculty of Engineering, Universidad de Medellín, Medellín, Colombia
dc.contributor.affiliationOrozco-Arroyave, J.R., GITA Lab. Faculty of Engineering, Universidad de Antioquia, Medellín, Colombia, Pattern Recognition Lab, Friedrich-Alexander-Universität, Erlangen-Nürnberg, Germany
dc.contributor.authorRoldan-Vasco S
dc.contributor.authorOrozco-Duque A
dc.contributor.authorOrozco-Arroyave J.R.
dc.date.accessioned2024-12-27T20:52:03Z
dc.date.available2024-12-27T20:52:03Z
dc.date.issued2025
dc.descriptionDysphagia is a swallowing disorder that affects food, liquid, or saliva transit from the mouth to the stomach. Dysphagia leads to malnutrition, dehydration, and aspiration of the bolus into the respiratory system, which can lead to pneumonia with subsequent death. Clinically accepted dysphagia diagnosis and follow-up methods are invasive, uncomfortable, expensive, and experience-dependent. This paper explores a multimodal non-invasive approach to objectively assess dysphagia with three biosignals: surface electromyography, accelerometry-based cervical auscultation, and speech. The defined acquisition protocol was applied to patients with dysphagia and healthy control subjects. Features were extracted from the three biosignals in different domains with the aim of proposing interpretable biomarkers. Finally, the methodology was evaluated according to the accuracy and area under the receiver operating characteristic curve obtained with different classifiers. According to our results, all signals demonstrated their suitability for dysphagia screening, specially speech and multi-modal scenarios evaluated with machine learning models and also with Gated Multimodal Units. This paper contributes to reducing the knowledge gap about swallowing-related phenomena and incorporates non-invasive and multi-modal methods with high potential to be transferred and implemented in clinical practice. © 2024 Elsevier Ltd
dc.identifier.doi10.1016/j.bspc.2024.107030
dc.identifier.instnameinstname:Universidad de Medellínspa
dc.identifier.issn17468094
dc.identifier.reponamereponame:Repositorio Institucional Universidad de Medellínspa
dc.identifier.repourlrepourl:https://repository.udem.edu.co/
dc.identifier.urihttp://hdl.handle.net/11407/8708
dc.language.isoeng
dc.publisherElsevier Ltdspa
dc.publisher.facultyFacultad de Ingenieríasspa
dc.publisher.programIngeniería de Telecomunicacionesspa
dc.relation.citationvolume100
dc.relation.isversionofhttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85206241071&doi=10.1016%2fj.bspc.2024.107030&partnerID=40&md5=f50629e49acb40ec7196ee45da33a383
dc.relation.referencesErtekin, C., Aydogdu, I., Neurophysiology of swallowing (2003) Clin. Neurophysiol., 114 (12), pp. 2226-2244
dc.relation.referencesShaw, S.M., Martino, R., The normal swallow: muscular and neurophysiological control (2013) Otolaryngol. Clin. North Am., 46 (6), pp. 937-956
dc.relation.referencesFarneti, D., Voice and dysphagia (2017) Dysphagia, pp. 257-274. , Springer
dc.relation.referencesBolser, D.C., Gestreau, C., Morris, K.F., Davenport, P.W., Pitts, T.E., Central neural circuits for coordination of swallowing, breathing, and coughing: predictions from computational modeling and simulation (2013) Otolaryngol. Clin. North Am., 46 (6)
dc.relation.referencesPalmer, J., Drennan, J., Baba, M., Evaluation and treatment of swallowing impairments (2000) Am. Fam. Physician, 61 (8), pp. 2453-2462
dc.relation.referencesClavé, P., Shaker, R., Dysphagia: current reality and scope of the problem (2015) Nat. Rev. Gastroenterol. Hepatol., 12 (5), p. 259
dc.relation.referencesBergström, L., Svensson, P., Hartelius, L., Cervical auscultation as an adjunct to the clinical swallow examination: A comparison with fibre-optic endoscopic evaluation of swallowing (2014) Int. J. Speech Lang. Pathol., 16 (5), pp. 517-528
dc.relation.referencesHassan, H.E., Aboloyoun, A.I., The value of bedside tests in dysphagia evaluation (2014) Egypt. J. Ear Nose Throat Allied Sci., 15 (3), pp. 197-203
dc.relation.referencesCarnaby-Mann, G., Lenius, K., The bedside examination in dysphagia (2008) Phys. Med. Rehabil. Clin. North Am., 19 (4), pp. 747-768
dc.relation.referencesYagi, N., Nagami, S., Lin, M.-K., Yabe, T., Itoda, M., Imai, T., Oku, Y., A noninvasive swallowing measurement system using a combination of respiratory flow, swallowing sound, and laryngeal motion (2017) Med. Biol. Eng. Comput., 55 (6), pp. 1001-1017
dc.relation.referencesLeslie, P., Drinnan, M.J., Finn, P., Ford, G.A., Wilson, J.A., Reliability and validity of cervical auscultation: a controlled comparison using videofluoroscopy (2004) Dysphagia, 19 (4), pp. 231-240
dc.relation.referencesLangmore, S.E., Evaluation of oropharyngeal dysphagia: which diagnostic tool is superior? (2003) Curr. Opin. Otolaryngol. Head Neck Surg., 11 (6), pp. 485-489
dc.relation.referencesEarl, V.J., Badawy, M.K., Radiation exposure to staff and patient during videofluoroscopic swallowing studies and recommended protection strategies (2019) Dysphagia, 34 (3), pp. 290-297
dc.relation.referencesWilson, R.D., Howe, E.C., A cost-effectiveness analysis of screening methods for dysphagia after stroke (2012) PM&R, 4 (4), pp. 273-282
dc.relation.referencesNacci, A., Ursino, F., La Vela, R., Matteucci, F., Mallardi, V., Fattori, B., Fiberoptic endoscopic evaluation of swallowing (FEES): proposal for informed consent (2008) Acta Otorhinolaryngol. Ital., 28 (4), p. 206
dc.relation.referencesZoratto, D.C.B., Chau, T., Steele, C.M., Hyolaryngeal excursion as the physiological source of swallowing accelerometry signals (2010) Physiol. Meas., 31 (6), p. 843
dc.relation.referencesLee, J., Steele, C.M., Chau, T., Time and time–frequency characterization of dual-axis swallowing accelerometry signals (2008) Physiol. Meas., 29 (9), p. 1105
dc.relation.referencesDudik, J.M., Coyle, J.L., Sejdić, E., Dysphagia screening: Contributions of cervical auscultation signals and modern signal-processing techniques (2015) IEEE Trans. Human-Mach. Syst., 45 (4), pp. 465-477
dc.relation.referencesDudik, J.M., Jestrović, I., Luan, B., Coyle, J.L., Sejdić, E., A comparative analysis of swallowing accelerometry and sounds during saliva swallows (2015) Biomed. Eng. Online, 14 (1), p. 3
dc.relation.referencesMovahedi, F., Kurosu, A., Coyle, J.L., Perera, S., Sejdić, E., A comparison between swallowing sounds and vibrations in patients with dysphagia (2017) Comput. Methods Programs Biomed., 144, pp. 179-187
dc.relation.referencesNozue, S., Ihara, Y., Takahashi, K., Harada, Y., Takei, Y., Yuasa, K., Yokoyama, K., Accuracy of cervical auscultation in detecting the presence of material in the airway (2017) Clin. Exp. Dent. Res., 3 (6), pp. 209-214
dc.relation.referencesMovahedi, F., Kurosu, A., Coyle, J.L., Perera, S., Sejdić, E., Anatomical directional dissimilarities in tri-axial swallowing accelerometry signals (2017) IEEE Trans. Neural Syst. Rehabil. Eng., 25 (5), pp. 447-458
dc.relation.referencesLee, J., Steele, C.M., Chau, T., Classification of healthy and abnormal swallows based on accelerometry and nasal airflow signals (2011) Artif. Intell. Med., 52 (1), pp. 17-25
dc.relation.referencesDudik, J.M., Kurosu, A., Coyle, J.L., Sejdić, E., Dysphagia and its effects on swallowing sounds and vibrations in adults (2018) Biomed. Eng. Online, 17 (1), p. 69
dc.relation.referencesSejdić, E., Steele, C.M., Chau, T., Classification of penetration–aspiration versus healthy swallows using dual-axis swallowing accelerometry signals in dysphagic subjects (2013) IEEE Trans. Biomed. Eng., 60 (7), pp. 1859-1866
dc.relation.referencesSteele, C.M., Mukherjee, R., Kortelainen, J.M., Pölönen, H., Jedwab, M., Brady, S.L., Theimer, K.B., Swigert, N.B., Development of a non-invasive device for swallow screening in patients at risk of oropharyngeal dysphagia: Results from a prospective exploratory study (2019) Dysphagia, 34 (5), pp. 698-707
dc.relation.referencesDonohue, C., Khalifa, Y., Perera, S., Sejdić, E., Coyle, J.L., A preliminary investigation of whether HRCA signals can differentiate between swallows from healthy people and swallows from people with neurodegenerative diseases (2021) Dysphagia, 36 (4), pp. 635-643
dc.relation.referencesMao, S., Zhang, Z., Khalifa, Y., Donohue, C., Coyle, J.L., Sejdic, E., Neck sensor-supported hyoid bone movement tracking during swallowing (2019) Royal Soc. Open Sci., 6 (7)
dc.relation.referencesKhalifa, Y., Donohue, C., Coyle, J.L., Sejdić, E., Upper esophageal sphincter opening segmentation with convolutional recurrent neural networks in high resolution cervical auscultation (2020) IEEE J. Biomed. Health Inform., 25 (2), pp. 493-503
dc.relation.referencesDonohue, C., Khalifa, Y., Mao, S., Perera, S., Sejdić, E., Coyle, J.L., Establishing reference values for temporal kinematic swallow events across the lifespan in healthy community dwelling adults using high-resolution cervical auscultation (2022) Dysphagia, pp. 1-12
dc.relation.referencesKhalifa, Y., Coyle, J.L., Sejdić, E., Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings (2020) Sci. Rep., 10 (1), pp. 1-13
dc.relation.referencesDonohue, C., Khalifa, Y., Perera, S., Sejdić, E., Coyle, J.L., How closely do machine ratings of duration of UES opening during videofluoroscopy approximate clinician ratings using temporal kinematic analyses and the mbsimp? (2020) Dysphagia, pp. 1-12
dc.relation.referencesSo, B.P.-H., Chan, T.T.-C., Liu, L., Yip, C.C.-K., Lim, H.-J., Lam, W.-K., Wong, D.W.-C., Cheung, J.C.-W., Swallow detection with acoustics and accelerometric-based wearable technology: A scoping review (2022) Int. J. Environ. Res. Public Health, 20 (1), p. 170
dc.relation.referencesPoorjavad, M., Talebian, S., Ansari, N.N., Soleymani, Z., Surface electromyographic assessment of swallowing function (2017) Iran. J. Med. Sci., 42 (2), p. 194
dc.relation.referencesErtekin, C., Electrophysiological evaluation of oropharyngeal Dysphagia in Parkinson's disease (2014) J. Movem. Disord., 7 (2), p. 31
dc.relation.referencesPalmer, J.B., Electromyography of the muscles of oropharyngeal swallowing: basic concepts (1989) Dysphagia, 3 (4), pp. 192-198
dc.relation.referencesVaiman, M., Eviatar, E., Surface electromyography as a screening method for evaluation of dysphagia and odynophagia (2009) Head Face Med., 5 (1), p. 9
dc.relation.referencesCrary, M.A., Carnaby, G.D., Groher, M.E., Identification of swallowing events from sEMG signals obtained from healthy adults (2007) Dysphagia, 22 (2), pp. 94-99
dc.relation.referencesHsu, C.-C., Chen, W.-H., Chiu, H.-C., Using swallow sound and surface electromyography to determine the severity of dysphagia in patients with myasthenia gravis (2013) Biomed. Signal Process. Control, 8 (3), pp. 237-243
dc.relation.referencesSuzuki, M., Sasaki, M., Kamata, K., Nakayama, A., Shibamoto, I., Tamada, Y., Swallowing pattern classification method using multichannel surface EMG signals of suprahyoid and infrahyoid muscles (2020) Adv. Biomed. Eng., 9, pp. 10-20
dc.relation.referencesWaito, A., Bailey, G.L., Molfenter, S.M., Zoratto, D.C., Steele, C.M., Voice-quality abnormalities as a sign of dysphagia: validation against acoustic and videofluoroscopic data (2011) Dysphagia, 26 (2), pp. 125-134
dc.relation.referencesDaniels, S.K., Pathak, S., Stach, C.B., Mohr, T.M., Morgan, R.O., Anderson, J.A., Speech pathology reliability for stroke swallowing screening items (2015) Dysphagia, 30 (5), pp. 565-570
dc.relation.referencesSantos, K.W.D., Scheeren, B., Maciel, A.C., Cassol, M., Vocal variability post swallowing in individuals with and without oropharyngeal dysphagia (2015) Int. Arch. Otorhinolaryngol., 19 (1), pp. 61-66
dc.relation.referencesFestic, E., Soto, J.S., Pitre, L.A., Leveton, M., Ramsey, D.M., Freeman, W.D., Heckman, M.G., Lee, A.S., Novel bedside phonetic evaluation to identify dysphagia and aspiration risk (2016) Chest, 149 (3), pp. 649-659
dc.relation.referencesPark, H.-Y., Park, D., Kang, H.S., Kim, H., Lee, S., Im, S., Post-stroke respiratory complications using machine learning with voice features from mobile devices (2022) Sci. Rep., 12 (1), pp. 1-11
dc.relation.referencesZhao, H., Jiang, Y., Wang, S., He, F., Ren, F., Zhang, Z., Yang, X., Li, Y., Dysphagia diagnosis system with integrated speech analysis from throat vibration (2022) Expert Syst. Appl.
dc.relation.referencesSampaio, M., Argolo, N., Melo, A., Nóbrega, A.C., Wet voice as a sign of penetration/aspiration in Parkinson's disease: does testing material matter? (2014) Dysphagia, 29 (5), pp. 610-615
dc.relation.referencesVásquez-Correa, J.C., Orozco-Arroyave, J.R., Bocklet, T., Nöth, E., Towards an automatic evaluation of the dysarthria level of patients with Parkinson's disease (2018) J. Commun. Disord.
dc.relation.references(2014), pp. 342-347. , Juan Rafael Orozco-Arroyave, Julián David Arias-Londoño, Jesus Francisco Vargas Bonilla, María Claudia Gonzalez-Rátiva, Elmar Nöth, New Spanish speech corpus database for the analysis of people suffering from Parkinson's disease, in: LREC
dc.relation.referencesZaretsky, E., Pluschinski, P., Sader, R., Birkholz, P., Neuschaefer-Rube, C., Hey, C., Identification of the most significant electrode positions in electromyographic evaluation of swallowing-related movements in humans (2017) Eur. Arch. Otrhinolaryngol., 274 (2), pp. 989-995
dc.relation.referencesMerletti, R., Di Torino, P., Standards for reporting EMG data (1999) J. Electromyogr. Kinesiol., 9 (1), pp. 3-4
dc.relation.referencesSebastian, R.-V., Estefania, P.-G., Andres, O.-D., Scalogram-Energy based Segmentation of surface Electromyography signals from swallowing related muscles (2020) Comput. Methods Programs Biomed.
dc.relation.referencesMatsuo, K., Palmer, J.B., Anatomy and physiology of feeding and swallowing: normal and abnormal (2008) Phys. Med. Rehabil. Clin. North Am., 19 (4), pp. 691-707
dc.relation.referencesETSI, Digital Cellular Telecommunications System (Phase 2+) (GSM)
dc.relation.referencesFull Rate Speech
dc.relation.referencesTranscoding (GSM 06.10 Version 8.1.1 Release 1999): Technical Report (2000), European Telecommunications Standards Institute
dc.relation.referencesRoldan-Vasco, S., Orozco-Duque, A., Orozco-Arroyave, J.R., Swallowing disorders analysis using surface EMG biomarkers and classification models (2023) Digit. Signal Process., 133
dc.relation.referencesOrozco-Arroyave, J.R., Vásquez-Correa, J.C., Vargas-Bonilla, J.F., Arora, R., Dehak, N., Nidadavolu, P.S., Christensen, H., Chinaei, H., NeuroSpeech: An open-source software for Parkinson's speech analysis (2018) Digit. Signal Process., 77, pp. 207-221
dc.relation.referencesRoldan-Vasco, S., Orozco-Duque, A., Suarez-Escudero, J.C., Orozco-Arroyave, J.R., Machine learning based analysis of speech dimensions in functional oropharyngeal dysphagia (2021) Comput. Methods Programs Biomed., 208
dc.relation.referencesBoersma, P., Praat, a system for doing phonetics by computer (2001) Glot. Int., 5 (9), pp. 341-345
dc.relation.referencesGuyon, I., Elisseeff, A., An introduction to variable and feature selection (2003) J. Mach. Learn. Res., 3 (Mar), pp. 1157-1182
dc.relation.referencesRoldan-Vasco, S., Restrepo-Uribe, J.P., Orozco-Duque, A., Suarez-Escudero, J.C., Orozco-Arroyave, J.R., Analysis of electrophysiological and mechanical dimensions of swallowing by non-invasive biosignals (2023) Biomed. Signal Process. Control, 82
dc.relation.referencesPowers, D., Evaluation: From precision, recall and F-measure to ROC, informedness, markedness & correlation (2011) J. Mach. Learn. Technol., 2 (1), pp. 37-63
dc.relation.referencesMandrekar, J.N., Receiver operating characteristic curve in diagnostic test assessment (2010) J. Thorac. Oncol., 5 (9), pp. 1315-1316
dc.relation.referencesArevalo, J., Solorio, T., Montes-y Gomez, M., González, F.A., Gated multimodal networks (2020) Neural Comput. Appl., 32, pp. 10209-10228
dc.relation.referencesVabalas, A., Gowen, E., Poliakoff, E., Casson, A.J., Machine learning algorithm validation with a limited sample size (2019) PLoS One, 14 (11)
dc.relation.referencesBerrar, D., Cross-validation (2019)
dc.relation.referencesStepp, C.E., Surface electromyography for speech and swallowing systems: Measurement, analysis, and interpretation (2012) J. Speech Lang. Hear. Res., 55 (4), pp. 1232-1246
dc.relation.referencesGéron, A., Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow (2022), “O'Reilly Media, Inc.”
dc.relation.referencesOsisanwo, F.Y., Akinsola, J.E.T., Awodele, O., Hinmikaiye, J.O., Olakanmi, O., Akinjobi, J., Supervised machine learning algorithms: classification and comparison (2017) Int. J. Comput. Trends Technol. (IJCTT), 48 (3), pp. 128-138
dc.relation.referencesZhou, X.-H., McClish, D.K., Obuchowski, N.A., (2009) Statistical Methods in Diagnostic Medicine, , John Wiley & Sons
dc.relation.referencesGroves-Wright, K.J., Acoustics and Perception of Wet Vocal Quality in Identifying Penetration/aspiration During Swallowing (2007), (Ph.D. thesis) University of Cincinnati
dc.relation.referencesMiyagi, S., Sugiyama, S., Kozawa, K., Moritani, S., Sakamoto, S.-I., Sakai, O., Classifying dysphagic swallowing sounds with support vector machines (2020) Healthcare, 8, p. 103. , MDPI
dc.relation.referencesHe, F., Hu, X., Zhu, C., Li, Y., Liu, Y., Multi-scale spatial and temporal speech associations to swallowing for dysphagia screening (2022) IEEE/ACM Trans. Audio Speech Lang. Process., 30, pp. 2888-2899
dc.rights.accessrightsinfo:eu-repo/semantics/restrictedAccess
dc.sourceBiomedical Signal Processing and Control
dc.sourceBiomed. Signal Process. Control
dc.sourceScopus
dc.subjectAccelerometryeng
dc.subjectDysphagiaeng
dc.subjectGated multimodal unitseng
dc.subjectMachine learningeng
dc.subjectMultimodal modelseng
dc.subjectsEMGeng
dc.subjectSignal processingeng
dc.subjectSpeecheng
dc.subjectDiseaseseng
dc.subjectLung cancereng
dc.subjectAccelerometryeng
dc.subjectBiosignalseng
dc.subjectDysphagiaeng
dc.subjectGated multimodal uniteng
dc.subjectLearning approacheng
dc.subjectMachine-learningeng
dc.subjectMulti-modaleng
dc.subjectMultimodal modelseng
dc.subjectSEMGeng
dc.subjectSignal-processingeng
dc.subjectElectromyographyeng
dc.titleDysphagia screening with sEMG, accelerometry and speech: Multimodal machine and deep learning approacheseng
dc.typeArticle
dc.type.localArtículo de revistaspa
dc.type.versioninfo:eu-repo/semantics/publishedVersion

Archivos

Colecciones

Indexados Scopus