Voice changes associated with stress and distress in people living with diabetes: Results from the Colive Voice study
6 affiliations
- 1Université Grenoble Alpes, Fonds de Dotation Clinatec, Grenoble, France
- 2Deep Digital Phenotyping Research Unit, Department of Precision Health, Luxembourg Institute of Health, Strassen, Luxembourg
- 3University of Luxembourg, Esch-sur-Alzette, Luxembourg
- 4Urban Development and Mobility, Luxembourg Institute of Socio-Economic Research, Porte des Sciences, Maison des Sciences Humaines, Esch sur Alzette/Belval, Luxembourg
- 5Université Grenoble Alpes, CEA-Leti, Grenoble, France
- 6Université Grenoble Alpes, Inserm, CHU Grenoble Alpes, Grenoble, France
Abstract
Stress and diabetes distress impact glycemic control, self-care, and health outcomes in people living with diabetes, but current diabetes technologies lack easy-to-use, non-invasive methods to detect these states. The objective was to identify vocal features associated with stress and diabetes distress in people living with diabetes. Thus, we analyzed data from 679 adults with diabetes (381 women, 298 men), recruited via the global vocal biomarker screening platform Colive Voice. Participants recorded a standardized 30-second text. Vocal features were extracted using DisVoice across phonation, prosody, articulation, and phonological domains. Associations between vocal features and stress (self-reported, scale: 0–4) and diabetes distress (Problem Areas in Diabetes (PAID) questionnaire; categories: PAID<20, 20 ≤ PAID<40, 40 ≤ PAID<60, PAID≥60) were analyzed separately for men and women. Multivariate ordinal logistic regression models were adjusted for age, language, diabetes type, and HbA1c, with False Discovery Rate correction.In women, results suggest that stress was associated with 25 voice features across all domains, while distress was linked to one articulatory feature, suggesting broader effects of stress. In men, both stress (25 features) and distress (18 features) affected multiple domains, but with distinct acoustic patterns. No voice features were shared between stress and distress. These patterns were consistent across age, diabetes type, and language.To conclude, voice changes reflect stress and diabetes distress in people with diabetes, each characterized by distinct acoustic features and additional sex-specific signatures. These findings highlight the potential of vocal biomarkers to differentiate and monitor these emotional states, supporting more timely and personalized interventions to improve diabetes outcomes. Author summary: Stress and diabetes distress are common in people living with diabetes and can worsen blood sugar control and overall health. Currently, detecting these emotional states relies on questionnaires that are completed only at specific clinical visits, making it difficult to capture how they impact diabetes management. In this study, we explored whether voice recordings collected via smartphone could reflect stress and diabetes distress in adults with diabetes. We analyzed speech recordings from 679 participants and identified acoustic features of the voice that were statistically associated with each emotional state. We found that stress affected a broader range of vocal characteristics than diabetes distress, and that the two outcomes produced distinct vocal patterns with no overlapping features. We also found that these patterns differed between men and women, suggesting that vocal signatures of stress and distress in diabetes are sex-specific.
Related
- Endoplasmic reticulum stress and glucose metabolism gene signature associated with type 2 diabetes mellitus
- Stress-induced dorsal striatal dopamine release is associated with changes in functional connectivity to the prefrontal cortex in nicotine-dependent individuals—a preliminary report
- Oxidative Stress, Post‐Translational Modifications, and Type 1 Diabetes Pathogenesis
- Growth and gonadal transcriptome changes in the largest extant amphibian after prolonged heat stress
- Sex-Dependent Microbiome-Metabolome Remodeling Associated with Bacteroides acidifaciens Modulation of Acute Respiratory Distress Syndrome
BibTeX
@article{bour2026voice,
title = {{Voice changes associated with stress and distress in people living with diabetes: Results from the Colive Voice study}},
author = {Charline Bour and Abir Elbéji and Dulce Canha and Noémie Topalian and Hanin Ayadi and Christelle Godin and Claire Guyon-Gardeux and Pierre-Yves Benhamou and Malvina Billères and Guy Fagherazzi},
journal = {PLOS Digital Health},
year = {2026},
month = aug,
doi = {10.1371/journal.pdig.0001689},
url = {https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001689},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Voice changes associated with stress and distress in people living with diabetes: Results from the Colive Voice study
AU - Charline Bour
AU - Abir Elbéji
AU - Dulce Canha
AU - Noémie Topalian
AU - Hanin Ayadi
AU - Christelle Godin
AU - Claire Guyon-Gardeux
AU - Pierre-Yves Benhamou
AU - Malvina Billères
AU - Guy Fagherazzi
PY - 2026
DA - 2026/08/31
JO - PLOS Digital Health
DO - 10.1371/journal.pdig.0001689
UR - https://journals.plos.org/digitalhealth/article?id=10.1371/journal.pdig.0001689
AB - Stress and diabetes distress impact glycemic control, self-care, and health outcomes in people living with diabetes, but current diabetes technologies lack easy-to-use, non-invasive methods to detect these states. The objective was to identify vocal features associated with stress and diabetes distress in people living with diabetes. Thus, we analyzed data from 679 adults with diabetes (381 women, 298 men), recruited via the global vocal biomarker screening platform Colive Voice. Participants recorded a standardized 30-second text. Vocal features were extracted using DisVoice across phonation, prosody, articulation, and phonological domains. Associations between vocal features and stress (self-reported, scale: 0–4) and diabetes distress (Problem Areas in Diabetes (PAID) questionnaire; categories: PAID<20, 20 ≤ PAID<40, 40 ≤ PAID<60, PAID≥60) were analyzed separately for men and women. Multivariate ordinal logistic regression models were adjusted for age, language, diabetes type, and HbA1c, with False Discovery Rate correction.In women, results suggest that stress was associated with 25 voice features across all domains, while distress was linked to one articulatory feature, suggesting broader effects of stress. In men, both stress (25 features) and distress (18 features) affected multiple domains, but with distinct acoustic patterns. No voice features were shared between stress and distress. These patterns were consistent across age, diabetes type, and language.To conclude, voice changes reflect stress and diabetes distress in people with diabetes, each characterized by distinct acoustic features and additional sex-specific signatures. These findings highlight the potential of vocal biomarkers to differentiate and monitor these emotional states, supporting more timely and personalized interventions to improve diabetes outcomes. Author summary: Stress and diabetes distress are common in people living with diabetes and can worsen blood sugar control and overall health. Currently, detecting these emotional states relies on questionnaires that are completed only at specific clinical visits, making it difficult to capture how they impact diabetes management. In this study, we explored whether voice recordings collected via smartphone could reflect stress and diabetes distress in adults with diabetes. We analyzed speech recordings from 679 participants and identified acoustic features of the voice that were statistically associated with each emotional state. We found that stress affected a broader range of vocal characteristics than diabetes distress, and that the two outcomes produced distinct vocal patterns with no overlapping features. We also found that these patterns differed between men and women, suggesting that vocal signatures of stress and distress in diabetes are sex-specific.
SN - 2767-3170
ER -