Segmentation of Dual-Axis Swallowing Accelerometry Signals in Healthy Subjects With Analysis of Anthropometric Effects on Duration of Swallowing Activities
The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
Dysphagia (swallowing difficulty) is a serious and debilitating condition that often accompanies stroke, acquired brain injury, and neurodegenerative illnesses. Individuals with dysphagia are prone to aspiration (the entry of foreign material into the airway), which directly increases the risk of serious respiratory consequences such as pneumonia. Swallowing accelerometry is a promising noninvasive tool for the detection of aspiration and the evaluation of swallowing. In this paper, dual-axis accelerometry was implemented since the motion of the hyolaryngeal complex occurs in both anterior-posterior and superior-inferior directions during swallowing. Dual-axis cervical accelerometry signals were acquired from 408 healthy subjects during dry, wet, and wet chin tuck swallowing tasks. The proposed segmentation algorithm is based on the idea of sequential fuzzy partitioning of the signal and is well suited for long signals with nonstationary variance. The algorithm was validated with simulated signals with known swallowing locations and a subset of 295 real swallows manually segmented by an experienced speech language pathologist. In both cases, the algorithm extracted individual swallows with over 90% accuracy. The time duration analysis was carried out with respect to gender, body mass index (BMI), and age. Demographic and anthropometric variables influenced the duration of these segmented signals. Male participants exhibited longer swallows than female participants (p=0.05). Older participants and participants with higher BMIs exhibited swallows with significantly longer (p=0.05) duration than younger participants and those with lower BMIs, respectively.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“They used also a good dataset with multiple swallowing maneuvers and materials; however, the algorithm is computationally expensive especially when the number of swallowing segments in the signal is unknown.”
From Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings (2020) · cites this paper as [3]
In the citing paper
“In this work, Sejdić et al.3 performed a maximum likelihood estimation to calculate the onset and offset times of swallows in acceleration signals.”
From Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings (2020) · cites this paper as [3]
In the citing paper
“Evidently, the proposed algorithm achieved results better than most of the swallowing signal segmentation algorithms in the literature, especially the work in3 which achieved the best swallowing segmentation accuracy in swallowing accelerometry.”
From Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings (2020) · cites this paper as [3]
Citations
Cites
Pattern Recognition with Fuzzy Objective Function Algorithms
Bezdek, J. C. (1981) · doi:10.1007/978-1-4757-0450-1 · Cited by 9,881 · cited 3×
“For complete proof of the previous statements, refer to [25].”
BackgroundInfluentialDuck, F. A. (1990) · Cited by 2,727
Physical properties of tissue : a comprehensive reference book
Duck, F. A. (1990) · Cited by 1,675
Preliminary observations on the effects of age on oropharyngeal deglutition
Tracy, J. F., Logemann, J. A., Kahrilas, P. J., Jacob, P., Kobara, M., & Krugler, C. (1989) · Dysphagia · doi:10.1007/bf02407151 · Cited by 334 · cited 2×
“We further note that the segmented vibration signals likely included events associated with both the oral and pharyngeal phases of swallowing, each of which persists for approximately 1 s [26].”
BackgroundA new statistical approach for the automatic segmentation of continuous speech signals
Andre-Obrecht, R. (1988) · IEEE Transactions on Acoustics, Speech, and Signal Processing · doi:10.1109/29.1486 · Cited by 243 · cited 1×
“Different solutions to this segmentation problem have been proposed in the literature over the years [21]– [23].”
BackgroundHyoid Motion During Swallowing: Factors Affecting Forward and Upward Displacement
Ishida, R., Palmer, J. B., & Hiiemae, K. M. (2002) · Dysphagia · doi:10.1007/s00455-002-0064-5 · Cited by 240 · cited 1×
“In addition, there appears to be a physiological basis for considering dual-axis accelerometry, given the 2-D movement of the hyoid and larynx during swallowing [16], [17].”
BackgroundA heart sound segmentation algorithm using wavelet decomposition and reconstruction
Huiying, L., Sakari, L., & Iiro, H. (2002) · Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136) · doi:10.1109/iembs.1997.757028 · Cited by 189 · cited 1×
“, heart sounds analysis [9], speech analysis [10], electroencephalogram signals analysis [11], knee joint vibroarthrographic signals analysis [12], and in the analysis of uterine magnetomyogram contractions during pregnancy [13], to name a few.”
Durational aspects of the oral-pharyngeal phase of swallow in normal adults
Sonies, B. C., Parent, L. J., Morrish, K., & Baum, B. J. (1988) · Dysphagia · doi:10.1007/bf02406274 · Cited by 185 · cited 2×
“also found that wet swallows were shorter than dry ones [19].”
BackgroundMaximum Hyoid Displacement in Normal Swallowing
Kim, Y., & McCullough, G. H. (2008) · Dysphagia · doi:10.1007/s00455-007-9135-y · Cited by 179 · cited 1×
“In addition, there appears to be a physiological basis for considering dual-axis accelerometry, given the 2-D movement of the hyoid and larynx during swallowing [16], [17].”
BackgroundOptimal segmentation of random processes
Lavielle, M. (1998) · IEEE Transactions on Signal Processing · doi:10.1109/78.668798 · Cited by 134
Acoustic Signature of the Normal Swallow: Characterization by Age, Gender, and Bolus Volume
Cichero, J. A. Y., & Murdoch, B. E. (2002) · Annals of Otology Rhinology & Laryngology · doi:10.1177/000348940211100710 · Cited by 113 · cited 1×
“This difference in duration can be attributed to gender-based anatomical differences in the oropharyngeal mechanism [28].”
BackgroundA Three-Channel Microcomputer System for Segmentation and Characterization of the Phonocardiogram
Lehner, R. J., & Rangayyan, R. M. (1987) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.1987.326060 · Cited by 110 · cited 1×
“In particular, several successful methods rely on multiple channels of information to enhance segmentation [14], [15].”
MethodThe Physiologic Cause of Swallowing Sounds: Answers from Heart Sounds and Vocal Tract Acoustics
Cichero, J. A. Y., & Murdoch, B. E. (1998) · Dysphagia · doi:10.1007/pl00009548 · Cited by 77 · cited 1×
“In order to eventually recognize differences between normal and dysphagic swallowing, the healthy, nondysphagic swallow must first be rigorously studied [18].”
BackgroundA radial basis classifier for the automatic detection of aspiration in children with dysphagia
Lee, J., Blain, S., Casas, M., Kenny, D., Berall, G., & Chau, T. (2006) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/1743-0003-3-14 · Cited by 74
Self-citationHybrid fuzzy logic committee neural networks for recognition of swallow acceleration signals
Das, A., Reddy, N. P., & Narayanan, J. (2001) · Computer Methods and Programs in Biomedicine · doi:10.1016/s0169-2607(00)00099-7 · Cited by 70 · cited 1×
“[5] proposed a hybrid fuzzy logic committee of neural networks trained to accurately distinguish between swallows from a dozen healthy subjects and 16 with dysphagia.”
BackgroundKrishnan, S., Rangayyan, R. M., Bell, G. D., Frank, C. B., & Ladly, K. O. (1997) · Medical & Biological Engineering & Computing · doi:10.1007/bf02510977 · Cited by 70 · cited 1×
“, heart sounds analysis [9], speech analysis [10], electroencephalogram signals analysis [11], knee joint vibroarthrographic signals analysis [12], and in the analysis of uterine magnetomyogram contractions during pregnancy [13], to name a few.”
Investigating the stationarity of paediatric aspiration signals
Chau, T. T., Chau, D., Casas, M. J., Berall, G., & Kenny, D. J. (2005) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2004.841384 · Cited by 64 · cited 2×
“Swallowing accelerometry signals often possess nonstationary variance [8], and hence, the present algorithm may “overestimate” the number of segments.”
BackgroundSelf-citationBiomechanical measurements to characterize the oral phase of dysphagia
Reddy, N. P., Costarella, B. R., Grotz, R. C., & Canilang, E. P. (1990) · IEEE Transactions on Biomedical Engineering · doi:10.1109/10.52346 · Cited by 60 · cited 1×
“= arg max c∈[1,2] Ic(Nχ) − 2c − 1 2 ln(Nχ) (7)”
Measurements of acceleration during videofluorographic evaluation of dysphagic patients
Reddy, N. P., Katakam, A., Gupta, V., Unnikrishnan, R., Narayanan, J., & Canilang, E. P. (2000) · Medical Engineering & Physics · doi:10.1016/s1350-4533(00)00047-3 · Cited by 59 · cited 1×
“[4] attributed the accelerometric signal to the extent of laryngeal elevation during swallowing, thus arguing that accelerometry would be of diagnostic value.”
BackgroundNoninvasive acceleration measurements to characterize the pharyngeal phase of swallowing
Reddy, N. P., Canilang, E. P., Casterline, J., Rane, M. B., Joshi, A. M., Thomas, R., & Candadai, R. S. (1991) · Journal of Biomedical Engineering · doi:10.1016/0141-5425(91)90018-3 · Cited by 56
A fuzzy logic diagnosis system for classification of pharyngeal dysphagia
Suryanarayanan, S., Reddy, N. P., & Canilang, E. P. (1995) · International Journal of Bio-Medical Computing · doi:10.1016/s0020-7101(05)80002-9 · Cited by 47 · cited 1×
“[7] developed a hand-crafted fuzzy rule base to classify 16 patients with dysphagia according to aspiration risk.”
BackgroundRosa, P. S. L., Nehorai, A., Eswaran, H., Lowery, C. L., & Preissl, H. T. (2008) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2007.912663 · Cited by 38 · cited 1×
“, heart sounds analysis [9], speech analysis [10], electroencephalogram signals analysis [11], knee joint vibroarthrographic signals analysis [12], and in the analysis of uterine magnetomyogram contractions during pregnancy [13], to name a few.”
On Using Multiple Models for Automatic Speech Segmentation
Park, S. S., & Kim, N. S. (2007) · IEEE Transactions on Audio Speech and Language Processing · doi:10.1109/tasl.2007.903933 · Cited by 36 · cited 1×
“, heart sounds analysis [9], speech analysis [10], electroencephalogram signals analysis [11], knee joint vibroarthrographic signals analysis [12], and in the analysis of uterine magnetomyogram contractions during pregnancy [13], to name a few.”
Two algorithms to segment white gaussian data with piecewise constant variances
Wang, Z., & Willett, P. (2003) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2002.806979 · Cited by 18 · cited 8×
“In order to determine which hypothesis best describes the segment χ, the MDL principle is employed as follows [24]:”
BackgroundMethodInfluentialBiomechanical quantification for assessment and diagnosis of dysphagia
Reddy, N. P., Canilang, E. P., Grotz, R. C., Rane, M. B., Casterline, J., & Costarella, B. R. (1988) · IEEE Engineering in Medicine and Biology Magazine · doi:10.1109/51.7929 · Cited by 17 · cited 3×
“= arg max c∈[1,2] Ic(Nχ) − 2c − 1 2 ln(Nχ) (7)”
BackgroundAn algorithm to partition DFT data into sections of constant variance
Kenefic, R. J. (1998) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/7.705886 · Cited by 12 · cited 1×
“Different solutions to this segmentation problem have been proposed in the literature over the years [21]– [23].”
BackgroundLan, T., Deniz Erdogmus, B., Pavel, M., & Mathan, S. A. (2006) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2006.247116 · Cited by 5 · cited 1×
“, heart sounds analysis [9], speech analysis [10], electroencephalogram signals analysis [11], knee joint vibroarthrographic signals analysis [12], and in the analysis of uterine magnetomyogram contractions during pregnancy [13], to name a few.”
Segmentation of heart rate variability in different physical activities
Chan, H., Lin, C. H., & Ko, Y. (2003) · Computers in cardiology · doi:10.1109/cic.2003.1291099 · Cited by 5 · cited 1×
“In particular, several successful methods rely on multiple channels of information to enhance segmentation [14], [15].”
Method
Research works printed but not linked: 2
- lee, 0, J Neuroeng Rehabil
- bennett, 2007, an examination of normal sip size behaviour in a natural drinking condition versus instructed experimental conditions, Dysphagia, 22, 387
Cited by
Dudik, J. M., Coyle, J. L., & Sejdić, E. (2015) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2015.2408615 · Cited by 97
“maintain a “pure” signal [21], [49], [51], [65], [66], [83], [86], [90], others place it as high as 30 Hz or more in order to eliminate motion artifacts and other low-frequency noise [39], [42], [44],”
InfluentialDudik, J. M., Kurosu, A., Coyle, J. L., & Sejdić, E. (2015) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2015.01.007 · Cited by 76
“A third technique which strikes a balance between computation requirements and accuracy and has been used to automatically segment swallowing vibrations successfully is the k-means clustering technique [36,37,18,19].”
BackgroundMethodResultInfluentialKhalifa, Y., Mandic, D. P., & Sejdić, E. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.11.008 · Cited by 88
“In swallowing, acceleration signals have been used for the detection of pharyngeal swallowing activity via maximum likelihood methods with minimum description length in [16] and using short time Fourier transform and neural networks in [14].”
MethodKhalifa, Y., Coyle, J. L., & Sejdić, E. (2020) · Scientific Reports · doi:10.1038/s41598-020-65492-1 · Cited by 82
“This algo-rithm achieved precision and recall values that are comparable to the results in 3 and outperformed k-means and density-based spatial clustering of applications with noise (DBSCAN) algorithms 32 .”
BackgroundMethodResultInfluentialA comparative analysis of swallowing accelerometry and sounds during saliva swallows
Dudik, J. M., Jestrović, I., Luan, B., Coyle, J. L., & Sejdić, E. (2015) · BioMedical Engineering OnLine · doi:10.1186/1475-925x-14-3 · Cited by 72
Metadata
- Authors
- Sejdic, E., Steele, C. M., & Chau, T.
- Affiliations
- University of Toronto (CA)
- Venue
- IEEE Transactions on Biomedical Engineering
- Published
- 2009-04
- Volume
- 56
- Issue
- 4
- Pages
- 1090-1097
- ISSN
- 0018-9294 (ISSN-L)
- 1558-2531
- OpenAlex
- W2159232358
- Cited by
- 73
- References
- 28
- Citations by year
- 2026: 4 · 2025: 4 · 2024: 3 · 2023: 5 · 2022: 4 · 2021: 1 · 2020: 6 · 2019: 4 · 2018: 4 · 2017: 3 · 2016: 5 · 2015: 5 · 2014: 4 · 2013: 5 · 2012: 4
- FWCI
- 14.56
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Biomedical Engineering (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Health Professions › Speech and Hearing › Dysphagia Assessment and Management
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Keywords
- dysphagia, aspiration detection, fuzzy partitioning, swallowing duration, body mass index, gender differences, age effects, chin tuck
- MeSH terms
- Adolescent, Adult, Aged, Algorithms, Anthropometry, Deglutition, Electromyography, Humans, Middle Aged, Models, Biological, Movement, Pattern Recognition, Automated, Reference Values, Time Factors, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.