CoChat

Machine learning based identification of relevant parameters for functional voice disorders derived from endoscopic high-speed recordings

Open access

The DOI matches its Crossref record; 63 of the 63 references it cites were found in a registry or an index.

Abstract

In voice research and clinical assessment, many objective parameters are in use. However, there is no commonly used set of parameters that reflect certain voice disorders, such as functional dysphonia (FD); i.e. disorders with no visible anatomical changes. Hence, 358 high-speed videoendoscopy (HSV) recordings (159 normal females (N F), 101 FD females (FD F), 66 normal males (N M), 32 FD males (FD M)) were analyzed. We investigated 91 quantitative HSV parameters towards their significance. First, 25 highly correlated parameters were discarded. Second, further 54 parameters were discarded by using a LogitBoost decision stumps approach. This yielded a subset of 12 parameters sufficient to reflect functional dysphonia. These parameters separated groups N F vs. FD F and N M vs. FD M with fair accuracy of 0.745 or 0.768, respectively. Parameters solely computed from the changing glottal area waveform (1D-function called GAW) between the vocal folds were less important than parameters describing the oscillation characteristics along the vocal folds (2D-function called Phonovibrogram). Regularity of GAW phases and peak shape, harmonic structure and Phonovibrogram-based vocal fold open and closing angles were mainly important. This study showed the high degree of redundancy of HSV-voice-parameters but also affirms the need of multidimensional based assessment of clinical data.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-020-66405-y

Cites

63 of 63 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 HSV recording using a rigid endoscope yielding 1D-GAW and 2D-PVG signals.
Figure 1 HSV recording using a rigid endoscope yielding 1D-GAW and 2D-PVG signals.CC BY · PubMed Central
Figure 2 Glottis segmentation using Glottis Analysis Tools.
Figure 2 Glottis segmentation using Glottis Analysis Tools.CC BY · PubMed Central
Figure 3 Segmentation Process. 1. Selection of the glottis region; 2. Selection of a 1000 frames section; 3. Segmentation of the glottal area; 4. Calculation of the partial GAWs (GAWL and GAWR) and 5. Extraction of all GAWs (GAWT, GAWL and GAWR) and the PVG.
Figure 3 Segmentation Process. 1. Selection of the glottis region; 2. Selection of a 1000 frames section; 3. Segmentation of the glottal area; 4. Calculation of the partial GAWs (GAWL and GAWR) and 5. Extraction of all GAWs (GAWT, GAWL and GAWR) and the PVG.CC BY · PubMed Central
Figure 4 Distribution of subject age; for (a) females and (b) males for healthy and disordered groups with #n being the number of subjects.
Figure 4 Distribution of subject age; for (a) females and (b) males for healthy and disordered groups with #n being the number of subjects.CC BY · PubMed Central
Figure 5 Parameters correlated highest with age; for (a) FDF (b) FDM.
Figure 5 Parameters correlated highest with age; for (a) FDF (b) FDM.CC BY · PubMed Central
Figure 6 Comparison of boosting algorithms for (a) females and (b) males. (a1/b1) normalized feature importance of the 10 highest ranked parameters for Logitboost using a 300 stumps model. (a2/b2) comparison of AUC and ACC of all tested algorithms.
Figure 6 Comparison of boosting algorithms for (a) females and (b) males. (a1/b1) normalized feature importance of the 10 highest ranked parameters for Logitboost using a 300 stumps model. (a2/b2) comparison of AUC and ACC of all tested algorithms.CC BY · PubMed Central
Figure 7 Choosing the optimal number of stumps for (a) females and (b) males. Number of stumps (model complexity) included in the model versus performance in measured in AUC and ACC.
Figure 7 Choosing the optimal number of stumps for (a) females and (b) males. Number of stumps (model complexity) included in the model versus performance in measured in AUC and ACC.CC BY · PubMed Central
Figure 8 Determination of best parameter subset for group comparisons (a) NF vs. FDF and (b) NM vs. FDM. (a1/b1) normalized FI of the 13/11 parameters ranked as most important. (a2/b2) AUC and ACC of models including only the best rated parameter, the best and the second best rated parameter,…. Parameters that were included in the best set for both group comparisons are marked in red.
Figure 8 Determination of best parameter subset for group comparisons (a) NF vs. FDF and (b) NM vs. FDM. (a1/b1) normalized FI of the 13/11 parameters ranked as most important. (a2/b2) AUC and ACC of models including only the best rated parameter, the best and the second best rated parameter,…. Parameters that were included in the best set for both group comparisons are marked in red.CC BY · PubMed Central
Figure 9 PVG oscillation cycle of healthy vocal folds with indicated contour angles.
Figure 9 PVG oscillation cycle of healthy vocal folds with indicated contour angles.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 63 references

Research works printed but not linked: 6

  1. Titze, I. R. Principles of voice production (2nd ed.) (National Center for Voice and Speech, 2000).
  2. Wendler, J., Seidner, W. & Eysholdt, U. Lehrbuch der Phoniatrie und Pädaudiologie (4th ed.) 139-189 (Georg Thieme, 2005). · DOI
  3. Stemple, J. C. & Fry, L. B. Laryngeal Evaluation. 110–119 (Georg Thieme, 2010).
  4. Deliyski, D. Laryngeal evaluation., 245–270 (Georg Thieme, 2010).
  5. Géron, A. Hands-on machine learning with Scikit-Learn & TensorFlow (vol. 1) 183-205 (Media, Inc., 2017).
  6. Géron, A. Hands-on machine learning with Scikit-Learn & TensorFlow (vol. 1) 81-106 (Media, Inc., 2017).

Cited by

See all 44

Metadata

Authors
Schlegel, P., Kniesburges, S., Dürr, S., Schützenberger, A., & Döllinger, M.
Affiliations
Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
Corresponding author
Schlegel, Patrick
Venue
Scientific Reports
Published
2020-06-29
Volume
10
Issue
1
Pages
10517-10517
ISSN
2045-2322 (ISSN-L)
OpenAlex
W3040522169
Cited by
43
References
63
Citations by year
2026: 4 · 2025: 5 · 2024: 11 · 2023: 9 · 2022: 6 · 2021: 6 · 2020: 2
FWCI
3.46
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • OPUS FAU (Kooperativer Bibliotheksverbund Berlin-Brandenburg (KOBV), on behalf of the Universitätsbibliothek Erlangen-Nürnberg) (submittedVersion, cc-by)
Funders
Deutsche Forschungsgemeinschaft (BO4399/2‐1, DO1247/8-1, 323308998)
Topics
  • Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
  • Social Sciences › Psychology › Experimental and Cognitive Psychology › Phonetics and Phonology Research
  • Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Respiratory and Cough-Related Research
Keywords
functional dysphonia, high-speed videoendoscopy, voice disorders, parameter selection, LogitBoost, glottal area waveform, vocal fold vibration, parameter redundancy
MeSH terms
Machine Learning, Age Factors, Endoscopy, Female, Humans, Laryngoscopy, Male, Voice Disorders, Voice Quality

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Machine learning based identification of relevant parameters for functional voice disorders derived from endoscopic high-speed recordings. https://app.cochat.ai/papers/10.1038/s41598-020-66405-y
The paper
Schlegel, P., Kniesburges, S., Dürr, S., Schützenberger, A., & Döllinger, M. (2020). Machine learning based identification of relevant parameters for functional voice disorders derived from endoscopic high-speed recordings. Scientific Reports. https://doi.org/10.1038/s41598-020-66405-y

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.