Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings
Open accessThe DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index; 1 of the 16 sources its claims cite were checked for support.
Abstract
High resolution cervical auscultation is a very promising noninvasive method for dysphagia screening and aspiration detection, as it does not involve the use of harmful ionizing radiation approaches. Automatic extraction of swallowing events in cervical auscultation is a key step for swallowing analysis to be clinically effective. Using time-varying spectral estimation of swallowing signals and deep feed forward neural networks, we propose an automatic segmentation algorithm for swallowing accelerometry and sounds that works directly on the raw swallowing signals in an online fashion. The algorithm was validated qualitatively and quantitatively using the swallowing data collected from 248 patients, yielding over 3000 swallows manually labeled by experienced speech language pathologists. With a detection accuracy that exceeded 95%, the algorithm has shown superior performance in comparison to the existing algorithms and demonstrated its generalizability when tested over 76 completely unseen swallows from a different population. The proposed method is not only of great importance to any subsequent swallowing signal analysis steps, but also provides an evidence that such signals can capture the physiological signature of the swallowing process.
Overview
CoChat Summary
TL;DR
The paper proposes an automatic swallowing-event segmentation algorithm for high-resolution cervical auscultation using spectrogram features and a deep feedforward neural network. It reports >95% window-level detection accuracy on 3,144 manually labeled swallows and promising generalization to 76 unseen swallows from a different population.
Key findings
- The best-performing signal was the anterior-posterior (A-P) accelerometer axis, with best window sizes of 800–900 samples (200–225 msec); the algorithm achieved over 95% accuracy at the window level, with sensitivity and specificity also reported as similar.
- On 3,144 swallows from 248 patients (average duration 862.6 ± 277 msec), detection exceeded 90% across single, multiple, and sequential swallows under several overlap criteria; for single swallows at 800 samples, detected swallows were 100% for 2 SD below average and 98.3% for 90% and 95% overlap.
- On 76 completely unseen swallows from a different population (average duration 1011 ± 216 msec), detection was 97.4% using a 2 SD below-average overlap, 84.2% using 1 SD below-average overlap, and 65.8% using 90% or greater overlap.
- Manual validation of more than 6,500 detected segments found the algorithm captured more than 94% of swallows and detected 353 swallows not captured/labeled in videos; false positives included hyoid bone movement (434), head and neck movement (266), coughing (134), reduced oral containment/premature spillage (38), and unexplained events (403).
Methods
- Design: an online-style sliding-window segmentation framework that computes short-time Fourier transform spectrograms for each window and feeds the magnitude spectrogram into a deep feedforward neural network to classify swallow vs. non-swallow.
- Data: 248 patients (148 males, 100 females, age 63.8 ± 13.7) referred for videofluoroscopic swallowing assessment; 3,144 swallows (603 stroke, 2,541 other) manually labeled by speech-language pathologists; signals included microphone and tri-axial accelerometer (A-P, S-I, M-L), sampled at 20 kHz and downsampled to 4 kHz.
- Analysis: four signal streams were tested independently; window sizes 500–1500 samples with and without 50% overlap were evaluated; the best configuration was retrained with 10-fold cross-validation and tested on 76 unseen swallows from 20 healthy adults (9 males, 11 females, age 65.8 ± 11.4).
Limitations
- Stated: performance dropped on the unseen dataset, possibly because average swallow duration differed between datasets and because multiple swallows were included; false positives such as coughing and head movement remained, and future work was proposed to fuse signal lines and use recurrent neural networks.
- Stated: the dataset “might be available upon reasonable request” from the corresponding author and with permission from clinical collaborators, so it is not openly available.
- Evident from the text: manual validation of false positives and visually uncovered events was performed for a specific configuration (window size 900 and 90% overlap), and the paper notes that unlabeled swallows during video pause periods were treated as false positives, which may lower reported sensitivity/specificity.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures










Verification
Claims the paper makes
1 Valid · 1 Not valid · 10 Not checked · 72 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We stated that the whole set of collected swallows is on average of 862.6 ± 277 msec.”
- Also stated in: § Methods · plain
“A total of 3144 swallows (603 from stroke diagnosed patients and 2541 from other patients) were recorded with an average duration of 862.6 ± 277 msec.”
§ Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings > Discussion
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Methods · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Among the examined assessment criteria, we found that a 2 SD below average swallow duration criterion as the minimum overlap (431.89 msec ≈47% of average swallow duration) between the detected and manually segmented swallows, is very low considering the duration of the examined swallows, however it gives excellent detection results.”
§ Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings > Discussion
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We can clearly see from Fig. 5 that training a DNN with the spectral estimate for the raw swallowing vibrations of a single channel can produce accuracies as low as 26.1% and up to 97.6% on window level over the whole dataset.”
§ Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings > Discussion
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The effect is almost the same with other components of acceleration and microphone signals.”
§ Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings > Discussion
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The algorithm also achieved 85.3 ± 12.5% sensitivity and 83.8 ± 9.5% specificity per each of the dataset records.”
§ Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings > Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
35 more claims
Create a free account to see all 84 claims and every source verdict.
- Probably not a substantial claim. 26
- It may state two separate claims as one. 27
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In research, the most addressed pathologies in adults were predominantly related to the neurological area, with stroke being highlighted in several studies(16,21,22,24,27,36,40,46,48-51).”
From Artificial intelligence in the diagnosis and management of dysphagia: a scoping review (2025) · cites this paper as [36]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“with stroke being the most cited in 12 studies(16,18,21,22,27,32,36,40,46,48-51)”
From Artificial intelligence in the diagnosis and management of dysphagia: a scoping review (2025) · cites this paper as [36]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“We used sizes of 500 to 1500 (25 to 375 msec)”
§ Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings > Results
Reported 25 · recomputed 125
Citations
Cites
A penetration-aspiration scale
Rosenbek, J. C., Robbins, J. A., Roecker, E. B., Coyle, J. L., & Wood, J. L. (1996) · Dysphagia · doi:10.1007/bf00417897 · Cited by 2,803 · cited 1×
“…event start (onset) and end (offset) times taken as gold standard for the experiment were obtained through manual segmentation of videofluoroscopy sequences by experienced SLPs in our Swallowing Research Lab along with the penetration aspiration (PA) scores 39 of the swallows as described in 40 .”
MethodSelf-citationIEEE Transactions on Signal Processing
(2023) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.78 · Cited by 1,455
IEEE Transactions on Biomedical Engineering
(2025) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.10 · Cited by 1,400
The evaluation and treatment of swallowing disorders
Logemann, J. A. (1998) · Current Opinion in Otolaryngology & Head and Neck Surgery · doi:10.1097/00020840-199812000-00008 · Cited by 1,222
A survey on ambient-assisted living tools for older adults
Rashidi, P., & Mihailidis, A. (2013) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2012.2234129 · Cited by 1,128 · cited 1×
“=−∞ ∞ − X n x m w n m ( , ) [ ] [ ]exp (1) m j n”
Evaluation and Treatment of Swallowing Disorders
Logemann, J. (1984) · NSSLHA Journal · doi:10.1044/nsshla_12_38 · Cited by 994
Andreu-Perez, J., Poon, C. C. Y., Merrifield, R. D., Wong, S. T. C., & Yang, G.-Z. (2015) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2015.2450362 · Cited by 670
IEEE Transactions on Neural Systems and Rehabilitation Engineering
(2025) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.7333 · Cited by 569
IEEE Journal of Biomedical and Health Informatics
(2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2021.3126038 · Cited by 525
Engineering in Medicine and Biology Society, 2006.
Nambakhsh, Ahmadian, A., Ghavami, M., Dilmaghani, R., & Karimifard, S. (2006) · Cited by 458
Cited by
Kang, Y. J., Arafa, H., Yoo, J., Kantarcigil, Ç., Kim, J., Jeong, H., Yoo, S., Oh, S., Kim, J., Wu, C., et al. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00691-w · Cited by 102
Borbone, N., Piccialli, G., Roviello, G. N., & Oliviero, G. (2021) · Molecules · doi:10.3390/molecules26040986 · Cited by 78
Khalifa, 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].”
MethodSelf-citationChest-Worn Inertial Sensors: A Survey of Applications and Methods
Rahmani, M. H., Berkvens, R., & Weyn, M. (2021) · Sensors · doi:10.3390/s21082875 · Cited by 62
“AdaBoost [61] ANN, MLP [33,62] [53] CNN [21] [77] Decision Tree [33,62] [72] DNN [71] GMM [78] k-NN [26] [32,33,61,64] [43] [44] LDA, PCA [28] [74] Naïve Bayes [33,62,67] [43] [72] [44] Regression Models [23,25,56] [11,67] [37,38] [68,69] [72] Random Forest [35,67] [51,53,76,77] SVM [33,61,62] [43] [47,72] [44,51,53]…”
BackgroundKhalifa, Y., Donohue, C., Coyle, J. L., & Sejdic, E. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3000057 · Cited by 49
“lus propulsion during swallowing from the moment the bolus passes the mandible till the UES closes [33]–[36].”
BackgroundSelf-citation
Metadata
- Authors
- Khalifa, Y., Coyle, J. L., & Sejdić, E.
- Affiliations
- University of Pittsburgh (US)
- Corresponding author
- Sejdić, Ervin
- Venue
- Scientific Reports
- Published
- 2020-05-26
- Volume
- 10
- Issue
- 1
- Pages
- 8704-8704
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC7251089
- OpenAlex
- W3030237993
- Cited by
- 82
- References
- 53
- Citations by year
- 2026: 10 · 2025: 11 · 2024: 13 · 2023: 13 · 2022: 14 · 2021: 14 · 2020: 7
- FWCI
- 17.05
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Scientific Reports (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- U.S. Department of Health & Human Services | NIH | Eunice Kennedy Shriver National Institute of Child Health and Human Development (R01HD074819, R01HD092239)
- Topics
- Health Sciences › Health Professions › Speech and Hearing › Dysphagia Assessment and Management
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Phonocardiography and Auscultation Techniques
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Keywords
- swallowing detection, cervical auscultation, dysphagia screening, aspiration detection, swallowing sounds, deep feedforward neural network, online detection
- MeSH terms
- Deep Learning, Aged, Auscultation, Deglutition, Deglutition Disorders, Female, Humans, Male, Middle Aged, Signal Processing, Computer-Assisted
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-09-30, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-09-30 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings. https://app.cochat.ai/papers/10.1038/s41598-020-65492-1
- The paper
- Khalifa, Y., Coyle, J. L., & Sejdić, E. (2020). Non-invasive identification of swallows via deep learning in high resolution cervical auscultation recordings. Scientific Reports. https://doi.org/10.1038/s41598-020-65492-1
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.