Abstract
Dysphagia presents a serious risk of aspiration that requires continuous monitoring. This study introduces standardized 2 s voice segments for aspiration detection, derived from physiological constraints observed during clinical video-fluoroscopic swallowing study (VFSS) examinations. This prospective cohort study collected voice data from 198 participants aged ≥ 40 years. Of the 128 normal participants (healthy controls and VFSS-normal, penetration-aspiration scale (PAS) 1) and 70 with aspiration-risk (PAS ≥ 5) participants, the duration analysis revealed that the VFSS participants (overall mean: 2.22–2.48 s) produced significantly shorter phonations than healthy controls (6.19 ± 1.70 s) (p < 0.001), which justified the 2 s standardization. The aspiration-risk threshold was set at PAS ≥ 5 as material on the vocal cords significantly alters voice quality. Post-swallowing recordings were preprocessed into mel-spectrograms via short-time Fourier transform to extract time-frequency features. We developed three models based on MobileNetV3 (male, female, integrated) using the EfficientAT framework with 10-fold cross-validation. The integrated model demonstrated optimal performance with an area under the curve (AUC) of 0.8090 and 82.77% sensitivity. The male-specific model achieved an AUC of 0.7586 and 91.88% sensitivity, whereas the female model reached an AUC of 0.7376 and 61.11% sensitivity. This physiologically grounded approach shows promise for telemedicine-based aspiration screening.
Trial registration: This study was approved by the institutional review board of Seoul National University Bundang Hospital (approval number B-2109-707-303) and registered in the ClinicalTrials.gov database (NCT05149976).
Abbreviations
- PAS:
-
Penetration-Aspiration scale
- VFSS:
-
Video-fluoroscopic swallowing study
- MPT:
-
Maximum phonation time
- NHR:
-
Noise-to-harmonics ratio
- RAP:
-
Relative average perturbation
- GRBAS:
-
Grade, roughness, breathiness, asthenia, strain scale
- SNR:
-
Signal-to-noise ratio
- XGBoost:
-
eXtreme gradient boosting
- CPP:
-
Cepstral peak prominence
- MFCCs:
-
Mel-frequency cepstral coefficients
- ASHA:
-
American speech-language-hearing association
- STFT:
-
Short-time fourier transform
- AUC:
-
Area under the ROC curve
- ROC:
-
Receiver operating characteristic
- STROBE:
-
Strengthening the reporting of observational studies in epidemiology
- HDF5:
-
Hierarchical data format version 5
- EfficientAT:
-
Efficient pre-trained CNNs for audio pattern recognition (audio tagging)
- MLP:
-
Multilayer perceptron
- PPV:
-
Positive predictive value
- NPV:
-
Negative predictive value
- CI:
-
Confidence interval
- SD:
-
Standard deviation
Acknowledgements
This work is based in part on the author’s doctoral dissertation submitted to Seoul National University (August 2024)78. The current manuscript significantly expands the interpretation and theoretical framing while reanalyzing the previously collected dataset.· The authors thank MiriCanvas (https://www.miricanvas.com) for providing the tools used to create the figures in the Methods section.
Funding
This research was funded by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (NRF-2022R1A2C1007780). This research was also funded by grant no. 14-2021-0018 from the SNUBH Research Fund. The funding did not participate in any aspect of the research process, including study design, data collection and analysis, interpretation of results, manuscript preparation, or publication decisions.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
Dr Ryu, Jung-Min Kim and Min-Seop Kim are named inventors on patent No. 10-2023-0095566, jointly held by RS Rehab and Bundang Seoul National University Hospital. The remaining authors declare no competing interests.
Ethics approval and consent to participate
All methods were carried out in accordance with the relevant guidelines and regulations, including the Declaration of Helsinki. This study was conducted after obtaining approval from the Seoul National University Bundang Hospital Institutional Review Board (IRB No.: B-2109-707-303). Written informed consent was obtained from all participants prior to enrollment; for participants unable to provide consent owing to age or health conditions, written informed consent was obtained from their guardians. All participants scheduled for VFSS were provided with detailed information about the study and gave their informed consent before participation. Healthy volunteers were recruited through a public notice (online and hospital bulletin) and participated only after providing consent.
Consent for publication
All voice recordings were anonymized using de-identification numbers to protect participant privacy. Written informed consent was obtained from all participants for the publication of this study after receiving a verbal explanation from the researcher.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary Information
Below is the link to the electronic supplementary material.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Kim, JM., Kim, MS., Choi, SY. et al. Post-swallowing voice-based aspiration screening in dysphagia using a deep learning approach: insights from audio segmentation. Sci Rep (2026). https://doi.org/10.1038/s41598-026-53618-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-026-53618-w
