Modified Multi-Auscultation Device for Swallowing Sound Analysis: A Feasibility Study toward Non-Invasive Dysphagia Assessment
DOI:
https://doi.org/10.3991/ijoe.v22i05.59009Keywords:
Biomedical Equipment, Engineering in Medicine, Machine Learning, Microphones, Sound RecognitionAbstract
This work explores a portable multi-auscultation tool to non-invasively analyse swallowing acoustics, aiming to facilitate early dysphagia screening. To repurpose the existing BODYTUNE vascular-monitoring unit, MEMS microphones were integrated, along with ESP32-based processing, into its architecture. Eight healthy volunteers recorded swallowing sounds while ingesting either saliva or water; the device captured intervals across the cervical domain. Signal segments were clinically defined into initial discrete sound, Bolus transit sound and final discrete sound (FDS), which were extracted and interrogated via time- and frequency-based metrics. Support vector machine (SVM), linear discriminant analysis (LDA), random forest, simple neural network and XGBoost, were employed to differentiate substance types of bolus. Audio fidelity across trials remained high, and the participants adhered to the protocol effortlessly. Within the FDS phase, the peak frequency (PF) and the mean power frequency (MPF) of water and saliva trials diverged substantially (p = 0.007 and p = 0.049, respectively), corroborating the biological relevance of the extracted features. LDA emerged as the most effective classifier, achieving an overall accuracy of 67% and a balanced F1 measure of 0.73. This study highlights the potential of low-cost, wearable acoustic systems for remote swallowing monitoring and paves the way for future integration with electromyography and machine learning (ML) algorithms for clinical dysphagia diagnosis.
References
[1] L. J. Lazareck and Z. M. Moussavi, “Classification of normal and dysphagic swallows by acoustical means,” IEEE Trans. Biomed. Eng., vol. 51, no. 12, pp. 2103–2112, Dec. 2004, doi: 10.1109/TBME.2004.836504.
[2] C. S. Easterling and E. Robbins, “Dementia and dysphagia,” Geriatr. Nurs., vol. 29, no. 4, pp. 275–285, Jul.–Aug. 2008, doi: 10.1016/j.gerinurse.2007.10.015.
[3] Y. Suido and S. Teramoto, “Assessment of swallowing function and dysphagia: Is the assessment of swallowing function necessary for the diagnosis of aspiration pneumonia?,” in Aspiration Pneumonia (Respiratory Disease Series: Diagnostic Tools and Disease Managements), S. Teramoto and K. Komiya, Eds. Singapore: Springer, 2020, pp. 49–62, doi: 10.1007/978-981-15-4506-1_5.
[4] B. C. Villegas, “Clinical swallow evaluation in head and neck cancer,” in Head and Neck Cancer: A Manual and Atlas. Singapore: Springer, 2018, doi: 10.1007/978-981-10-8282-5_4.
[5] H. Wakabayashi, “Assessment of swallowing function and muscle using ultrasonography in general and family medicine,” J. Gen. Fam. Med., vol. 21, no. 2, pp. 1–2, Feb. 2020, doi: 10.1002/jgf2.298.
[6] J. D. Hoffmeister, “Clinical evaluation of swallow,” in Multidisciplinary Management of Pediatric Voice and Swallowing Disorders. Cham: Springer, 2020, doi: 10.1007/978-3-030-26191-7_16.
[7] D. J. Ramsey, D. G. Smithard, and L. Kalra, “Early assessments of dysphagia and aspiration risk in acute stroke patients,” Stroke, vol. 34, no. 5, pp. 1252–1257, May 2003, doi: 10.1161/01.STR.0000066309.06490.B8.
[8] J. C. O’Horo, N. Rogus-Pulia, L. Garcia-Arguello, J. Robbins, and N. Safdar, “Bedside diagnosis of dysphagia: A systematic review,” J. Hosp. Med., vol. 10, no. 4, pp. 256–265, Apr. 2015, doi: 10.1002/jhm.2313.
[9] A. Kaindlstorfer and R. Pointner, “An appraisal of current dysphagia diagnosis and treatment strategies,” Expert Rev. Gastroenterol. Hepatol., vol. 10, no. 8, pp. 929–942, Aug. 2016, doi: 10.1586/17474124.2016.1158098.
[10] M. El Halabi, R. Arwani, and H. P. Parkman, “Dysphagia in neurological disorders,” Semin. Neurol., vol. 43, no. 4, pp. 530–539, Aug. 2023, doi: 10.1055/s-0043-1771458.
[11] E. Nunes, L. Menzen, and M. Cardoso, “Swallowing acoustic characteristics of time, intensity, and frequency in healthy adults,” Open J. Otolaryngol., vol. 2, no. 2, pp. 10–16, 2019, doi: 10.22259/2639-3603.0202002.
[12] S. Morinière, M. Boiron, D. Alison, P. Makris, and P. Beutter, “Origin of the sound components during pharyngeal swallowing in normal subjects,” Dysphagia, vol. 23, no. 3, pp. 267–273, Sep. 2008, doi: 10.1007/s00455-007-9134-z.
[13] J. L. Ferrucci, L. D. Mangilli, F. C. Sassi, S. C. Limongi, and C. R. Andrade, “Swallowing sounds in speech therapy practice: A critical analysis of the literature,” Einstein (Sao Paulo), vol. 11, no. 4, pp. 535–539, Dec. 2013, doi: 10.1590/s1679-45082013000400024.
[14] S. R. Youmans and J. A. Stierwalt, “An acoustic profile of normal swallowing,” Dysphagia, vol. 20, no. 3, pp. 195–209, Summer 2005, doi: 10.1007/s00455-005-0013-1.
[15] S. L. Hamlet, R. J. Nelson, and R. L. Patterson, “Interpreting the sounds of swallowing: Fluid flow through the cricopharyngeus,” Ann. Otol. Rhinol. Laryngol., vol. 99, pp. 749–752, 1990, doi: 10.1177/000348949009900916.
[16] F. S. Soria, R. G. Silva, and A. M. Furkim, “Acoustic analysis of oropharyngeal swallowing using sonar Doppler,” Braz. J. Otorhinolaryngol., vol. 82, no. 1, pp. 39–46, Jan.–Feb. 2016, doi: 10.1016/j.bjorl.2015.12.001.
[17] O. Brasil, R. Yamasaki, and S. Leão, “Proposta de medição da posição vertical da laringe em repouso,” Rev. Bras. Otorrinolaringol., vol. 71, pp. 313–317, 2005, doi: 10.1590/S0034-72992005000300008.
[18] K. Oliveira, B. Faria, J. Silva, C. Reis, A. Ghio, and A. C. Gama, “Análise das medidas aerodinâmicas no português brasileiro por meio do método multiparamétrico de avaliação vocal objetiva assistida (EVA),” Rev. CEFAC, vol. 15, pp. 119–127, 2013, doi: 10.1590/S1516-18462012005000053.
[19] J. Baqué, O. Huret, P. Rayneau, M. Schleich, and S. Morinière, “Acoustic analysis of swallowing of an experimental meal of three food textures: A comparative aging study,” Dysphagia, vol. 39, no. 3, pp. 452–458, Jun. 2024, doi: 10.1007/s00455-023-10629-3.
[20] B. P. So et al., “Swallow detection with acoustics and accelerometric-based wearable technology: A scoping review,” Int. J. Environ. Res. Public Health, vol. 20, no. 1, p. 170, Dec. 2022, doi: 10.3390/ijerph20010170.
[21] H. Firmin, S. Reilly, and A. Fourcin, “Non-invasive monitoring of reflexive swallowing,” Speech Hear. Lang., vol. 10, 1997. [Online]. Available: http://laryngograph.com/pdfdocs/paper5.pdf
[22] K. V. M. Taveira et al., “Diagnostic validity of methods for assessment of swallowing sounds: A systematic review [dataset],” figshare, 2018, doi: 10.6084/m9.figshare.7243523.v1.
[23] T. Olubanjo and M. Ghovanloo, “Real-time swallowing detection based on tracheal acoustics,” in Proc. IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP), Florence, Italy, 2014, pp. 4384–4388, doi: 10.1109/ICASSP.2014.6854430.
[24] Y. Song, I. Yun, S. Giovanoli et al., “Multimodal deep ensemble classification system with wearable vibration sensor for detecting throat-related events,” npj Digit. Med., vol. 8, p. 14, 2025, doi: 10.1038/s41746-024-01417-w.
[25] T. A. Rafeedi et al., “Wearable, epidermal devices for assessment of swallowing function,” npj Flex. Electron., vol. 7, p. 52, 2023, doi: 10.1038/s41528-023-00286-9.
[26] L. Gravellier, M. Le Coz, J. Farinas, and J. Pinquier, “Detection of pharyngolaryngeal activities in real-world settings using wearable sensors,” in Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC), Orlando, FL, USA, 2024, pp. 1–5, doi: 10.1109/EMBC53108.2024.10782007.
[27] D. Li et al., “A review on intelligent aid diagnosis for dysphagia using swallowing sounds,” Interdiscip. Nurs. Res., vol. 2, no. 4, pp. 250–256, 2023, doi: 10.1097/NR9.0000000000000040.
[28] J. M. Dudik, J. L. Coyle, and E. Sejdić, “Dysphagia screening: Contributions of cervical auscultation signals and modern signal-processing techniques,” IEEE Trans. Hum.-Mach. Syst., vol. 45, no. 4, pp. 465–477, Aug. 2015, doi: 10.1109/THMS.2015.2408615.
[29] E. Sejdić, G. A. Malandraki, and J. L. Coyle, “Computational deglutition: Using signal- and image-processing methods to understand swallowing and associated disorders,” IEEE Signal Process. Mag., vol. 36, no. 1, pp. 138–146, Jan. 2019, doi: 10.1109/MSP.2018.2875863.
[30] M.-L. Huckabee, P. Macrae, and K. Lamvik, “Expanding instrumental options for dysphagia diagnosis and research: Ultrasound and manometry,” Folia Phoniatr. Logop., vol. 67, no. 6, pp. 269–284, 2015, doi: 10.1159/000444636.
[31] L. F. Santoso et al., “Applying machine learning algorithms for automatic detection of swallowing from sound,” in Proc. 41st Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC), Berlin, Germany, 2019, pp. 2584–2588, doi: 10.1109/EMBC.2019.8857937.
[32] S. Miyagi, S. Sugiyama, K. Kozawa, S. Moritani, S.-i. Sakamoto, and O. Sakai, “Classifying dysphagic swallowing sounds with support vector machines,” Healthcare (Basel), vol. 8, no. 2, p. 103, 2020, doi: 10.3390/healthcare8020103.
[33] D. Li et al., “Development of the swallowing activity classification model for old adults based on acoustic analysis,” Innov. Aging, vol. 8, suppl. 1, p. 927, 2024, doi: 10.1093/geroni/igae098.2991.
[34] Y. Srinivasan, A. Liu, and A. Rameau, “Machine learning in the evaluation of voice and swallowing in the head and neck cancer patient,” Curr. Opin. Otolaryngol. Head Neck Surg., vol. 32, no. 2, pp. 105–112, 2024, doi: 10.1097/MOO.0000000000000948.
[35] T. Sühn et al., “Auscultation system for acquisition of vascular sounds—towards sound-based monitoring of the carotid artery,” Med. Devices (Auckl.), vol. 13, pp. 349–364, 2020, doi: 10.2147/MDER.S268057.
[36] R. Salvi et al., “BODYTUNE: Multi auscultation device—personal health parameter monitoring at home,” Curr. Dir. Biomed. Eng., vol. 7, pp. 5–8, 2021, doi: 10.1515/cdbme-2021-2002.
[37] I. Müller, J. Henze, A. Burmann, R. Salvi, and R. Baum, “User-centred design of a patient app for carotid artery monitoring at home,” in Human Systems Engineering and Design (IHSED 2023): Future Trends and Applications, W. Karwowski, T. Ahram, M. Milicevic, D. Etinger, and K. Zubrinic, Eds. USA: AHFE International, 2023, vol. 112, doi: 10.54941/ahfe1004111.
[38] P. Fuentealba et al., “Carotid sound signal artifact detection based on discrete wavelet transform decomposition,” Curr. Dir. Biomed. Eng., vol. 7, no. 2, pp. 299–302, 2021, doi: 10.1515/cdbme-2021-2076.
[39] M. Jaghbeer, A. L. Sutt, and L. Bergström, “Dysphagia management and cervical auscultation: Reliability and validity against FEES,” Dysphagia, vol. 38, no. 1, pp. 305–314, 2023, doi: 10.1007/s00455-022-10468-8.
[40] K. Takahashi, M. E. Groher, and K. Michi, “Methodology for detecting swallowing sounds,” Dysphagia, vol. 9, pp. 54–62, 1994, doi: 10.1007/BF00262760.
[41] International Dysphagia Diet Standardisation Initiative (IDDSI), “The IDDSI framework and descriptors,” ver. 2.0, Jul. 2019. [Online]. Available: https://creativecommons.org/licenses/by-sa/4.0/. [Accessed: Sep. 28, 2025].
[42] M. Aboofazeli and Z. Moussavi, “Automated classification of swallowing and breath sounds,” in Proc. IEEE Eng. Med. Biol. Soc. (EMBC), San Francisco, CA, USA, 2004, pp. 3816–3819, doi: 10.1109/IEMBS.2004.1404069.
[43] A. Santamato, F. Panza, V. Solfrizzi, A. Russo, V. Frisardi, M. Megna, M. Ranieri, and P. Fiore, “Acoustic analysis of swallowing sounds: A new technique for assessing dysphagia,” J. Rehabil. Med., vol. 41, no. 8, pp. 639–645, 2009, doi: 10.2340/16501977-0384.
[44] S. R. Youmans and J. A. G. Stierwalt, “Normal swallowing acoustics across age, gender, bolus viscosity, and bolus volume,” Dysphagia, vol. 26, no. 4, pp. 374–384, 2011, doi: 10.1007/s00455-010-9323-z.
[45] A. Kurosu, J. L. Coyle, J. M. Dudik, and E. Sejdić, “Detection of swallow kinematic events from acoustic high-resolution cervical auscultation signals in patients with stroke,” Arch. Phys. Med. Rehabil., vol. 100, no. 3, pp. 501–508, Mar. 2019, doi: 10.1016/j.apmr.2018.05.038.
[46] Y. Khalifa, J. L. Coyle, and E. Sejdić, “Non-invasive identification of swallows via deep learning in high-resolution cervical auscultation recordings,” Sci. Rep., vol. 10, p. 8704, 2020, doi: 10.1038/s41598-020-65492-1.
[47] A. Y. Cichero and B. E. Murdoch, “What happens after the swallow? Introducing the glottal release sound,” J. Med. Speech Lang. Pathol., vol. 11, no. 1, pp. 31–41, 2003.
[48] A. Yadollahi and Z. Moussavi, “Feature selection for swallowing sounds classification,” in Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC), 2007, pp. 3172–3175, doi: 10.1109/IEMBS.2007.4353003.
[49] S. T. Almeida, E. L. Ferlin, M. A. M. P. Parente, and H. A. S. Goldani, “Assessment of swallowing sounds by digital cervical auscultation in children,” Ann. Otol. Rhinol. Laryngol., vol. 117, no. 4, pp. 253–258, 2008, doi: 10.1177/000348940811700403.
[50] T. Honda et al., “Characterization of swallowing sound: Preliminary investigation of normal subjects,” PLoS One, vol. 11, no. 12, p. e0168187, 2016, doi: 10.1371/journal.pone.0168187.
[51] Z. Moussavi, “Assessment of swallowing sounds' stages with hidden Markov model,” in Proc. IEEE Eng. Med. Biol. Soc. (EMBC), 2005, pp. 6989–6992, doi: 10.1109/IEMBS.2005.1616114.
[52] M. Taniwaki and K. Kohyama, “Fast Fourier transform analysis of sounds made while swallowing various foods,” J. Acoust. Soc. Am., vol. 132, no. 4, pp. 2478–2482, 2012, doi: 10.1121/1.4750491.
[53] H. Inokuchi, M. González-Fernández, K. Matsuo et al., “Electromyography of swallowing with fine wire intramuscular electrodes in healthy humans: Activation sequence of selected hyoid muscles,” Dysphagia, vol. 29, no. 6, pp. 713–721, 2014, doi: 10.1007/s00455-014-9566-1.
[54] A. L. Perlman, P. M. Palmer, T. M. McCulloch, and D. J. Vandaele, “Electromyographic activity from human laryngeal, pharyngeal, and submental muscles during swallowing,” J. Appl. Physiol., vol. 86, no. 5, pp. 1663–1669, May 1999, doi: 10.1152/jappl.1999.86.5.1663.
[55] D. Kennedy, J. Kieser, C. Bolter et al., “Tongue pressure patterns during water swallowing,” Dysphagia, vol. 25, no. 1, pp. 11–19, 2010, doi: 10.1007/s00455-009-9223-2.
[56] I. J. Cook, W. J. Dodds, R. O. Dantas et al., “Timing of videofluoroscopic, manometric events, and bolus transit during the oral and pharyngeal phases of swallowing,” Dysphagia, vol. 4, no. 1, pp. 8–15, 1989, doi: 10.1007/BF02407397.
[57] T. Gay, J. K. Rendell, and J. Spiro, “Oral and laryngeal muscle coordination during swallowing,” Laryngoscope, vol. 104, no. 3, pp. 341–349, 1994, doi: 10.1288/00005537-199403000-00017.
[58] E. Sejdić, C. M. Steele, and T. Chau, “Segmentation of dual-axis swallowing accelerometry signals in healthy subjects with analysis of anthropometric effects on duration of swallowing activities,” IEEE Trans. Biomed. Eng., vol. 56, no. 4, pp. 1090–1097, Apr. 2009, doi: 10.1109/TBME.2008.2010504.
[59] M. L. Ng and A. Ki, “Acoustic characteristics associated with liquid swallowing sounds of different bolus consistencies in young healthy adults,” Int. J. Lang. Commun. Disord., vol. 57, pp. 552–564, 2022, doi: 10.1111/1460-6984.12706.
[60] C. Feng, K. Volkman, C. Wagoner, and K.-C. Siu, “The effects of different viscous liquids and solid foods on swallowing speeds and sounds among healthy adults,” Int. J. Lang. Commun. Disord., vol. 57, pp. 78–89, 2022, doi: 10.1111/1460-6984.12675.
[61] N. W. Hennessey, G. Fisher, and N. Ciccone, “Developmental changes in pharyngeal swallowing acoustics: A comparison of adults and children,” Logoped. Phoniatr. Vocol., vol. 43, no. 2, pp. 63–72, 2017, doi: 10.1080/14015439.2017.1326526.
[62] U. Witte, M.-L. Huckabee, S. H. Doeltgen, F. Gumbley, and M. Robb, “The effect of effortful swallow on pharyngeal manometric measurements during saliva and water swallowing in healthy participants,” Arch. Phys. Med. Rehabil., vol. 89, no. 5, pp. 822–828, May 2008, doi: 10.1016/j.apmr.2007.08.167.
[63] B. Shin et al., “Automatic clinical assessment of swallowing behavior and diagnosis of silent aspiration using wireless multimodal wearable electronics,” Adv. Sci., vol. 11, p. 2404211, 2024, doi: 10.1002/advs.202404211.
[64] S. Subramani, M. V. A. Rao, A. Roy, and P. S. Hegde, “SegNet-based deep representation learning for dysphagia classification,” in Proc. IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP), Singapore, 2022, pp. 1141–1145, doi: 10.1109/ICASSP43922.2022.9747732.
[65] J. P. Restrepo-Uribe, S. Roldan-Vasco, E. Perez-Giraldo, J. R. Orozco-Arroyave, and A. Orozco-Duque, “Electrophysiological and mechanical approaches to the swallowing analysis,” in Applied Computer Sciences in Engineering (Communications in Computer and Information Science, vol. 1274), J. C. Figueroa-García, F. S. Garay-Rairán, G. J. Hernández-Pérez, and Y. Díaz-Gutierrez, Eds. Cham: Springer, 2020, pp. 281–290, doi: 10.1007/978-3-030-61834-6_24.
[66] A. Anwar, Y. Khalifa, E. Lucatorto, J. L. Coyle, and E. Sejdić, “Swallowing assessment using high-resolution cervical auscultations and transformer-based neural networks,” in Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC), Orlando, FL, USA, 2024, pp. 1–5, doi: 10.1109/EMBC53108.2024.1078228
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Pedro Galdames, Bojan Petrović, David Valencia, Lazar Milić, Sanja Kojić, Guillaume Serandour, Goran M. Stojanović
This work is licensed under a Creative Commons Attribution 4.0 International License.
