Deep Learning-based Artificial Intelligence in Audio based Analysis of Swallowing using Cervical Auscultation
Swallowing problems (dysphagia) is associated with significant morbidity and mortality therefore diagnosis and treatment of dysphagia is important. Diagnostic tests include screening procedures, clinical swallowing examinations, and instrumental examination procedures. A non-invasive diagnostic opti...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2024-09-01
|
| Series: | Current Directions in Biomedical Engineering |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/cdbme-2024-1055 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832570458921238528 |
|---|---|
| author | Salloum Hazem Graf Simone Schilling Berit Richter Lena Jeleff-Wölfler Olivia Feussner Hubertus Ostler Daniel Wilhelm Dirk Fuchtmann Jonas |
| author_facet | Salloum Hazem Graf Simone Schilling Berit Richter Lena Jeleff-Wölfler Olivia Feussner Hubertus Ostler Daniel Wilhelm Dirk Fuchtmann Jonas |
| author_sort | Salloum Hazem |
| collection | DOAJ |
| description | Swallowing problems (dysphagia) is associated with significant morbidity and mortality therefore diagnosis and treatment of dysphagia is important. Diagnostic tests include screening procedures, clinical swallowing examinations, and instrumental examination procedures. A non-invasive diagnostic option is auscultation of the swallowing act. However, there are different statements about the reliability and validity of the manual execution of this test. We developed a mobile hardware system to record cervical sounds using two microphones on the neck to acquire audio a data set. To generate ground truth data, fiberendoscopic swallow examinations were performed simultaneously to identify dysphagia. In order to diagnostically assess the swallowing sounds a spectrogram based classification pipeline was developed. In a first step this enabled us to identify different swallowing patterns in healthy individuals. With an accuracy of ~95%, we were able to reliably detect swallows within audio recordings, while the classification of types of swallow (dry, water, solid food) indicate the need for further improvements within the project ahead. In the future, we anticipate AI based analysis of auscultated swallowing sounds to detect swallowing disorders and aspirations. |
| format | Article |
| id | doaj-art-c5bb03648ffd474183083c9247576c42 |
| institution | Kabale University |
| issn | 2364-5504 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Current Directions in Biomedical Engineering |
| spelling | doaj-art-c5bb03648ffd474183083c9247576c422025-02-02T15:45:00ZengDe GruyterCurrent Directions in Biomedical Engineering2364-55042024-09-01102161910.1515/cdbme-2024-1055Deep Learning-based Artificial Intelligence in Audio based Analysis of Swallowing using Cervical AuscultationSalloum Hazem0Graf Simone1Schilling Berit2Richter Lena3Jeleff-Wölfler Olivia4Feussner Hubertus5Ostler Daniel6Wilhelm Dirk7Fuchtmann Jonas8Hazem Salloum: Department of Otorhinolaryngology, University of Regensburg,Regensburg, GermanyDepartment of Hearing, Speech and Voice Disorders, Medical University of Innsbruck,Innsbruck, AustriaTechnical University of Munich, School of Medicine, Munich, University Hospital rechts der Isar, Department of Otorhinolaryngology,, Munich, GermanyTechnical University of Munich, School of Medicine, Munich, University Hospital rechts der Isar, Department of Otorhinolaryngology,, Munich, GermanyTechnical University of Munich, School of Medicine, Munich, University Hospital rechts der Isar, Department of Otorhinolaryngology,, Munich, GermanyTechnical University of Munich, School of Medicine, Munich, University, Hospital rechts der Isar, Department of Surgery,Munich, GermanyTechnical University of Munich, School of Medicine, Chair of Research Group Minimally invasive interdisciplinary Therapeutical Interventions (MITI),Munich, GermanyTechnical University of Munich, School of Medicine, Chair of Research Group Minimally invasive interdisciplinary Therapeutical Interventions (MITI),Munich, GermanyTechnical University of Munich, School of Medicine, Chair of Research Group Minimally invasive interdisciplinary Therapeutical Interventions (MITI),Munich, GermanySwallowing problems (dysphagia) is associated with significant morbidity and mortality therefore diagnosis and treatment of dysphagia is important. Diagnostic tests include screening procedures, clinical swallowing examinations, and instrumental examination procedures. A non-invasive diagnostic option is auscultation of the swallowing act. However, there are different statements about the reliability and validity of the manual execution of this test. We developed a mobile hardware system to record cervical sounds using two microphones on the neck to acquire audio a data set. To generate ground truth data, fiberendoscopic swallow examinations were performed simultaneously to identify dysphagia. In order to diagnostically assess the swallowing sounds a spectrogram based classification pipeline was developed. In a first step this enabled us to identify different swallowing patterns in healthy individuals. With an accuracy of ~95%, we were able to reliably detect swallows within audio recordings, while the classification of types of swallow (dry, water, solid food) indicate the need for further improvements within the project ahead. In the future, we anticipate AI based analysis of auscultated swallowing sounds to detect swallowing disorders and aspirations.https://doi.org/10.1515/cdbme-2024-1055dysphagiacervical auscultationdeep learningbased artificial intelligencefiberendoscopic evaluation of swallowingfees |
| spellingShingle | Salloum Hazem Graf Simone Schilling Berit Richter Lena Jeleff-Wölfler Olivia Feussner Hubertus Ostler Daniel Wilhelm Dirk Fuchtmann Jonas Deep Learning-based Artificial Intelligence in Audio based Analysis of Swallowing using Cervical Auscultation Current Directions in Biomedical Engineering dysphagia cervical auscultation deep learningbased artificial intelligence fiberendoscopic evaluation of swallowing fees |
| title | Deep Learning-based Artificial Intelligence in Audio based Analysis of Swallowing using Cervical Auscultation |
| title_full | Deep Learning-based Artificial Intelligence in Audio based Analysis of Swallowing using Cervical Auscultation |
| title_fullStr | Deep Learning-based Artificial Intelligence in Audio based Analysis of Swallowing using Cervical Auscultation |
| title_full_unstemmed | Deep Learning-based Artificial Intelligence in Audio based Analysis of Swallowing using Cervical Auscultation |
| title_short | Deep Learning-based Artificial Intelligence in Audio based Analysis of Swallowing using Cervical Auscultation |
| title_sort | deep learning based artificial intelligence in audio based analysis of swallowing using cervical auscultation |
| topic | dysphagia cervical auscultation deep learningbased artificial intelligence fiberendoscopic evaluation of swallowing fees |
| url | https://doi.org/10.1515/cdbme-2024-1055 |
| work_keys_str_mv | AT salloumhazem deeplearningbasedartificialintelligenceinaudiobasedanalysisofswallowingusingcervicalauscultation AT grafsimone deeplearningbasedartificialintelligenceinaudiobasedanalysisofswallowingusingcervicalauscultation AT schillingberit deeplearningbasedartificialintelligenceinaudiobasedanalysisofswallowingusingcervicalauscultation AT richterlena deeplearningbasedartificialintelligenceinaudiobasedanalysisofswallowingusingcervicalauscultation AT jeleffwolflerolivia deeplearningbasedartificialintelligenceinaudiobasedanalysisofswallowingusingcervicalauscultation AT feussnerhubertus deeplearningbasedartificialintelligenceinaudiobasedanalysisofswallowingusingcervicalauscultation AT ostlerdaniel deeplearningbasedartificialintelligenceinaudiobasedanalysisofswallowingusingcervicalauscultation AT wilhelmdirk deeplearningbasedartificialintelligenceinaudiobasedanalysisofswallowingusingcervicalauscultation AT fuchtmannjonas deeplearningbasedartificialintelligenceinaudiobasedanalysisofswallowingusingcervicalauscultation |