Voice analysis in asthmatic and healthy individuals: comparative assessment of asthma control levels using machine learning models
5 affiliations
- 1Department of Chest Diseases, Sağlık Bilimleri Üniversitesi, Istanbul, Türkiye
- 2Department of Chest Diseases, Nişantaşı University, Istanbul, Türkiye
- 3Department of Computer Engineering, Istanbul Medeniyet University, Istanbul, Türkiye
- 4Department of Computer Sciences, Ascleb, Istanbul, Türkiye
- 5Department of Computer Sciences, Monitor CRO, Istanbul, Türkiye
Abstract
Introduction: Machine learning (ML) has significant potential for diagnosing and monitoring asthma. Previous studies have primarily focused on wheezing, coughing, breathing sounds, and phonetic features, while the potential of specific spoken words remains less explored. This study aimed to use ML models to distinguish individuals with asthma from healthy controls and classify asthma control according to the Global Initiative for Asthma (GINA) criteria using recorded vowels and specific words.
Methods: This single-center, cross-sectional study included 344 participants: 284 patients with asthma and 60 healthy volunteers. Participants were asked to repeat six different Turkish words 10 times each and sustain the vowel “a” for 10 s. Voice recordings were analyzed using various ML models, including ensemble methods, Support Vector Machines (SVM), and multilayer perceptrons (MLP). The model performance was evaluated based on metrics, including accuracy, sensitivity, and F1 score.
Results: When distinguishing asthmatic patients from healthy individuals, the highest-performing model (Voting Ensemble using the word ‘gelecek) achieved an AUC of 0.769, accuracy of 82.0%, and sensitivity of 93.3%. For the classification of asthma control status, the models showed limited discriminatory power, with the highest AUC of 0.592, reflecting significant class imbalance between controlled and uncontrolled patients.
Conclusions: Speech-based machine learning models have shown potential as a noninvasive approach for distinguishing individuals with asthma from healthy controls. Therefore, voice-based assessment may serve as a complementary tool to standard clinical and functional evaluations. Larger, more diverse populations and external validation are required before clinical implementation.
Related
- Establishment of age- and sex-stratified normative data for the Brief Assessment of Cognition (BAC) app in healthy Japanese individuals.
- After the Trip: A Qualitative Study of Healthy Individuals’ Motor Experiences Following Different Doses of Psilocybin
- Skin carotenoid levels are associated with blood amyloid-beta 42/40 ratios in healthy individuals under 60 years of age
- Prediction of acute myeloid leukaemia risk in healthy individuals
- CYBA Gene Polymorphisms, Lipid Parameters and Atherogenic Indices: A Cohort Study of Healthy Individuals Without Prior Lipid-Lowering Therapy
BibTeX
@article{alagoz2026voice,
title = {{Voice analysis in asthmatic and healthy individuals: comparative assessment of asthma control levels using machine learning models}},
author = {Neval Alagöz and Mehmet Atilla Uysal and Murat Gezer and Can Ortak and Elif Yelda Ozgun Niksarlioglu},
journal = {BMC Pulmonary Medicine},
year = {2026},
month = sep,
doi = {10.1186/s12890-026-04654-9},
url = {https://doi.org/10.1186/s12890-026-04654-9},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Voice analysis in asthmatic and healthy individuals: comparative assessment of asthma control levels using machine learning models
AU - Neval Alagöz
AU - Mehmet Atilla Uysal
AU - Murat Gezer
AU - Can Ortak
AU - Elif Yelda Ozgun Niksarlioglu
PY - 2026
DA - 2026/09/01
JO - BMC Pulmonary Medicine
DO - 10.1186/s12890-026-04654-9
UR - https://doi.org/10.1186/s12890-026-04654-9
AB - Introduction: Machine learning (ML) has significant potential for diagnosing and monitoring asthma. Previous studies have primarily focused on wheezing, coughing, breathing sounds, and phonetic features, while the potential of specific spoken words remains less explored. This study aimed to use ML models to distinguish individuals with asthma from healthy controls and classify asthma control according to the Global Initiative for Asthma (GINA) criteria using recorded vowels and specific words. Methods: This single-center, cross-sectional study included 344 participants: 284 patients with asthma and 60 healthy volunteers. Participants were asked to repeat six different Turkish words 10 times each and sustain the vowel “a” for 10 s. Voice recordings were analyzed using various ML models, including ensemble methods, Support Vector Machines (SVM), and multilayer perceptrons (MLP). The model performance was evaluated based on metrics, including accuracy, sensitivity, and F1 score. Results: When distinguishing asthmatic patients from healthy individuals, the highest-performing model (Voting Ensemble using the word ‘gelecek) achieved an AUC of 0.769, accuracy of 82.0%, and sensitivity of 93.3%. For the classification of asthma control status, the models showed limited discriminatory power, with the highest AUC of 0.592, reflecting significant class imbalance between controlled and uncontrolled patients. Conclusions: Speech-based machine learning models have shown potential as a noninvasive approach for distinguishing individuals with asthma from healthy controls. Therefore, voice-based assessment may serve as a complementary tool to standard clinical and functional evaluations. Larger, more diverse populations and external validation are required before clinical implementation.
SN - 1471-2466
ER -