Voice as a biomarker: exploratory analysis for benign and malignant vocal fold lesions
Open accessThe DOI matches its Crossref record; 23 of the 24 references it cites were found in a registry or an index.
Abstract
Benign and malignant vocal fold lesions can alter voice quality and lead to significant morbidity or, in the case of malignancy, mortality. Early, noninvasive identification of these lesions using voice as a biomarker may improve diagnostic access and outcomes. In this study, we analyzed data from the initial release of the Bridge2AI-Voice dataset to evaluate which acoustic features best distinguish laryngeal cancer and benign vocal fold lesions from other vocal pathologies and healthy voice function. Seven diagnostic cohorts were grouped into two analyses: the first included participants with laryngeal cancer, benign lesions, or no voice disorder; the second included those with laryngeal cancer or benign lesions without other voice disorders, as well as individuals with spasmodic dysphonia or vocal fold paralysis. Acoustic features including fundamental frequency, jitter, shimmer, and harmonic-to-noise ratio (HNR) were extracted from standardized speech recordings and compared using nonparametric statistical methods. Among the overall sample, significant differences were identified in HNR and fundamental frequency between benign lesions and both healthy controls and laryngeal cancer. In cisgender men, these distinctions were also observed, particularly in HNR and its variability. No statistically significant differences were observed among cisgender women, likely due to the limited sample size. These findings suggest that HNR, particularly its variability, may hold promise as a voice-based marker for early detection and monitoring of vocal fold lesions. Further research with larger, more diverse populations is needed to refine these features and validate their clinical utility.
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.
Integrity signals
Registry
Cites
Statistics
Figures
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.
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
“continuous/connected speech analysis enables the capturing of dynamic and intermittent vocal phenomena that are unlikely to appear during standardized vocal tasks and may provide more ecologically valid assessment [19,40,49].”
From Diagnostic Accuracy of Artificial Intelligence in Laryngeal Disorders: An Integrative Review (2026) · cites this paper as [49]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“only 70% of clinically confirmed diplophonic segments are detectable during sustained phonation tasks [19,49].”
From Diagnostic Accuracy of Artificial Intelligence in Laryngeal Disorders: An Integrative Review (2026) · cites this paper as [49]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“continuous speech may introduce an increased variability related to linguistic content, prosodic patterns, and articulatory demands, complicating extraction of directly comparable acoustic signatures between individuals [38,49].”
From Diagnostic Accuracy of Artificial Intelligence in Laryngeal Disorders: An Integrative Review (2026) · cites this paper as [49]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“clinical studies have shown that certain phenomena (e.g., diplophonia) are not systematically elicited by standardized vowels or short reading tasks.”
From Diagnostic Accuracy of Artificial Intelligence in Laryngeal Disorders: An Integrative Review (2026) · cites this paper as [49]
Experimental — accuracy not yet measured
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
SciPy 1.0: fundamental algorithms for scientific computing in Python
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., et al. (2020) · Nature Methods · doi:10.1038/s41592-019-0686-2 · Cited by 38,430
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473 · cited 1×
“They were obtained using openSMILE (17) and stored in PyTorch (18) fi les.”
SciPy 1.0: fundamental algorithms for scientific computing in Python
Virtanen, P., Gommers, R., Oliphant, T. E., Haberland, M., Reddy, T., Cournapeau, D., Burovski, E., Peterson, P., Weckesser, W., Bright, J., et al. (2019) · Apollo - University of Cambridge Repository · doi:10.17863/cam.64134 · Cited by 10,460
scikit-posthocs: Pairwise multiple comparison tests in Python
Terpilowski, M. (2019) · Journal of Open Source Software · doi:10.21105/joss.01169 · Cited by 357
openSMILE - The Munich Versatile and Fast Open-Source Audio Feature Extractor
Eyben, F. ;. (2013) · mediaTUM – the media and publications repository of the Technical University Munich (Technical University Munich) · Cited by 321
Updates on larynx cancer epidemiology
Nocini, R., Section of Ear Nose and Throat (ENT), D. O. S. S., Molteni, G., Mattiuzzi, C., Lippi, G., Service of Clinical Governance, P. A. F. S. A. S. S., & Section of Clinical Biochemistry, D. O. N. (2020) · Chinese Journal of Cancer Research · doi:10.21147/j.issn.1000-9604.2020.01.03 · Cited by 283
Diagnosis and Treatment of Voice Disorders
Sataloff, R. T. (2014) · The Medicine Forum · Cited by 263
Functional dysphonia: strategies to improve patient outcomes
Behlau, M., Madazio, G., & Oliveira, G. (2015) · Patient Related Outcome Measures · doi:10.2147/prom.s68631 · Cited by 129
Cho, W. K., Lee, Y. J., Joo, H. A., Jeong, I. S., Choi, Y., Nam, S. Y., Kim, S. Y., & Choi, S. (2021) · The Laryngoscope · doi:10.1002/lary.29595 · Cited by 68
Karlsen, T., Sandvik, L., Heimdal, J., & Aarstad, H. J. (2018) · Journal of Voice · doi:10.1016/j.jvoice.2018.07.002 · Cited by 49
Bonilha, H. S., Deliyski, D. D., Whiteside, J. P., & Gerlach, T. T. (2012) · American Journal of Speech-Language Pathology · doi:10.1044/1058-0360(2011/09-0086 · Cited by 44
Voice as an AI Biomarker of Health—Introducing Audiomics
Bensoussan, Y., Elemento, O., & Rameau, A. (2024) · JAMA Otolaryngology–Head & Neck Surgery · doi:10.1001/jamaoto.2023.4807 · Cited by 44
Mohamed, N., AlMutairi, R. I., Abdelrahim, S., Alharbi, R., Alhomayani, F. M., Elnaim, B. M. E., Elhag, A. A., & Dhakal, R. (2023) · Cancers · doi:10.3390/cancers16010181 · Cited by 40
The Clinicopathological Study of Benign Lesions of Vocal Cords
Malik, P., Yadav, S., Sen, R., Gupta, P., Jai, S., Singla, A., & Vashisht, S. (2017) · Indian Journal of Otolaryngology and Head & Neck Surgery · doi:10.1007/s12070-017-1240-0 · Cited by 35 · cited 2×
“Common benign lesions of the vocal folds include vocal fold nodules, polyps, cysts, polypoid degeneration, vocal process granulomas, and recurrent respiratory papillomatosis (10).”
Jung, S. Y., Han, K., Chun, M. S., Chung, S. M., & Kim, H. S. (2018) · Journal of Voice · doi:10.1016/j.jvoice.2018.08.005 · Cited by 33
Analysis of Vocal Fold Function From Acoustic Data Simultaneously Recorded With High-Speed Endoscopy
Döllinger, M., Kunduk, M., Kaltenbacher, M., Vondenhoff, S., Ziethe, A., Eysholdt, U., & Bohr, C. (2012) · Journal of Voice · doi:10.1016/j.jvoice.2012.02.001 · Cited by 32
A support vector machine–based voice disorders detection using human voice signal
Leung, P. H., Chui, K. T., Lo, K., & de Pablos, P. O. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-822060-3.00014-0 · Cited by 27
Bridge2AI-Voice: An ethically-sourced, diverse voice dataset linked to health information
Bensoussan, Y. E., Sigaras, A., Rameau, A., Elemento, O., Powell, M., Dorr, D., Payne, P., Ravitsky, V., Bélisle‐Pipon, J., Bahr, R., et al. (2025) · PhysioNet · doi:10.13026/37yb-1t42 · Cited by 14
Self-citationMalinowski, J., Pietruszewska, W., Kowalczyk, M., & Niebudek-Bogusz, E. (2024) · Journal of Cancer Research and Clinical Oncology · doi:10.1007/s00432-023-05543-y · Cited by 12
Kang, Y. A., Chang, J. W., Won, H.-R., & Koo, B. S. (2020) · Journal of Voice · doi:10.1016/j.jvoice.2020.03.005 · Cited by 8 · cited 1×
“Likewise, in a study of 112 men with vocal fold leukoplakia, a type of lesion most commonly caused by smoking – Dr. Young Ae Kang and colleagues found higher F0 among those with carcinoma relative to those without using an analysis of covariance ( P < 0.000) (16).”
InfluentialRisk factors and diagnostic methods in vocal cord mucousal lesions
Paltura, C. (2019) · SiSli Etfal Hastanesi Tip Bulteni / The Medical Bulletin of Sisli Hospital · doi:10.14744/semb.2019.29291 · Cited by 3
Acoustic Character Governing Variation in Normal, Benign, and Malignant Voices
Liu, B., Lei, J., Wischhoff, O. P., Smereka, K. A., & Jiang, J. J. (2024) · Folia Phoniatrica et Logopaedica · doi:10.1159/000540255 · Cited by 2 · cited 2×
“Interestingly, Liu et al. ’ s PCA analysis highlighted an underlying acoustic difference between multiple conditions, such as Reinke ’ s edema, polyps, cysts, and leukoplakia (21).”
Barbero (2014) · doi:10.1016/j · Cited by 1
Bridge2AI-Voice: An ethically-sourced, diverse voice dataset linked to health information
Johnson, A., Bélisle-Pipon, J.-C., Dorr, D., Ghosh, S., Payne, P., Powell, M., Rameau, A., Ravitsky, V., Sigaras, A., Elemento, O., et al. (2025) · PhysioNet · doi:10.13026/249v-w155
Research works printed but not linked: 2
- 1. Bridge2AI. Bridge2AI: A new Biomedical Data Generation Program. Bethesda, MD: National Institutes of Health (n.d.). Available online at: https://bridge2ai.org/ (Accessed August 27, 2024).
- 5. Koroulakis A, Agarwal M. Laryngeal cancer. In: StatPearls. Treasure Island, FL: StatPearls Publishing (2024). p. 1. Available online at: https://www.ncbi.nlm.nih.gov/ books/NBK526076/ (Accessed April 09, 2025).
Cited by
AI-Driven Detection and Classification of Voice Disorders Using Acoustic Recordings
Berteloot, L., Sismono, F., Maertens, L., Maryn, Y., Verguts, M., Vandaele, M., de Pol, C. V., Jaeger, P. D., & Delsupehe, K. (2026) · Journal of Voice · doi:10.1016/j.jvoice.2026.04.024 · Cited by 3
Diagnostic Accuracy of Artificial Intelligence in Laryngeal Disorders: An Integrative Review
Mairesse, S., Maniaci, A., Briganti, G., & Lechien, J. R. (2026) · Journal of Personalized Medicine · doi:10.3390/jpm16060301 · Cited by 1
“…illustrated this practically, as despite confirmed clinical diagnoses only approximately 70% of diplophonic participants produced detectable diplophonic segments during standardized recording tasks, suggesting that certain pathological symptoms are intermittent and context-dependent [19,49].”
InfluentialGórecki, S., Tatka, A., & Osmola, M. (2026) · Cancers · doi:10.3390/cancers18121905 · Cited by 1
“Systemic fatigue, vocal cord toxicity, respiratory distress, and mood alterations [12,44,45].”
InfluentialErdem, R. Ö., & Arbağ, H. (2026) · Journal of Voice · doi:10.1016/j.jvoice.2026.07.056 · Cited by 1
RRP-Voice: A Longitudinal Dataset and Benchmark for Recurrent Respiratory Papillomatosis DetectionPreprint
Ren, W., Lu, K.-H., Chang, K.-W., Feng, T., Fang, C., Liao, Z.-C., Yen, D. T. H., Wang, S., Tsao, Y., Wang, C.-T., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.01639
“Voice encodes rich physiological information about the vocal apparatus and has emerged as a non-invasive, low-cost, and remotely accessible biomarker of laryngeal health [1], [2].”
Metadata
- Authors
- Jenkins, P., Harrison, R., Bedrick, S., Karstens, L., Bridge2AI-Voice Consortium, & Hersh, W.
- Affiliations
- Oregon Health & Science University (US)
- Portland State University (US)
- Corresponding author
- Jenkins, Phillip
- Venue
- Frontiers in Digital Health
- Publisher
- Frontiers Media SA
- Published
- 2025-08-12
- Volume
- 7
- Pages
- 1609811-1609811
- ISSN
- 2673-253X (ISSN-L)
- PMC
- PMC12378753
- OpenAlex
- W4413103754
- Cited by
- 10
- References
- 22
- Citations by year
- 2026: 10
- FWCI
- 6.43
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Digital Health (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PDXScholar (Portland State University) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Institutes of Health (Bridge2AI, OT2OD032720)
- Common Fund (OT2 OD032720)
- Topics
- Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
- Health Sciences › Medicine › Pulmonary and Respiratory Medicine › Phonocardiography and Auscultation Techniques
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- vocal fold lesions, laryngeal cancer, benign vocal fold lesions, acoustic voice analysis, harmonic-to-noise ratio, fundamental frequency, jitter, shimmer, spasmodic dysphonia, vocal cord paralysis, early cancer detection, sex differences
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.
