Detecting Type 2 Diabetes From Voice

NCT07421921 | Completed

• 1 other identifier: 25-DIABETES-011
• Study Type: observational
• Target: 7,319
• Locations: 1 country
• Sites: 1

Brief Summary

The goal of this observational study is to learn if computer analysis of voice recordings can detect Type 2 diabetes in adults. The main questions it aims to answer are:

• Can advanced voice analysis accurately identify participants with Type 2 diabetes or pre-diabetes based on vocal biomarkers?
• How do voice-based predictions compare to HbA1c blood test results for diabetes screening?
• Can machine learning approaches effectively address the challenge of undiagnosed diabetes in population screening? Participants will:
• Record themselves reading a short passage and answering brief questions out loud in a single online session.
• Complete health questionnaires about diabetes risk factors, medications, and general health status.
• A subset of participants (n=1,000) will provide a blood sample through an at-home HbA1c testing kit to validate voice-based predictions against laboratory results.
• Use their own devices (computer, tablet, or smartphone) to complete all study activities online from home.

Conditions

Type 2 Diabetes; Diabetes (DM); T2DM; T2DM (Type 2 Diabetes Mellitus)

Keywords

Diabetes Mellitus Type 2; Type 2 Diabetes; Diabetes; Pre-diabetes; voice biomarkers; digital health; speech analysis; artificial intelligence; machine learning; acoustic analysis; remote monitoring; diabetes screening; glycated hemoglobin A; HbA1c; vocal biomarkers; digital biomarkers

Outcome Measures

Primary Outcomes (1)

• Accuracy of AI Model for Type 2 Diabetes Classification as Assessed by Voice Biomarker Analysis

  Binary classification performance (presence vs. absence of Type 2 diabetes) of the artificial intelligence-based system using voice biomarker analysis, with HbA1c laboratory results (≥48 mmol/mol threshold) serving as ground truth. Performance will be measured using sensitivity (target ≥65%), specificity (target ≥65%), and area under the receiver operating characteristic curve (AUC target \~0.70) through cross-validation methods.

  Single assessment session at enrolment with HbA1c validation results obtained within 2 months of submission of voice measurement.

Secondary Outcomes (1)

• Detection of Pre-diabetes Using Voice Biomarker Analysis

  Single assessment session at enrolment with HbA1c validation within 2 months of submitting voice measurement.

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population consists of a convenience sample of UK-based adults recruited through Prolific, an established online research platform widely used in the UK by researchers. This remote recruitment enables access to a geographically dispersed population across the UK, including individuals with known diabetes and those unaware of their metabolic health status. The online methodology reaches populations who may not engage with traditional healthcare screening, where NHS Health Check attendance is only 40.4%. The study recruits 10,000 participants for initial voice analysis, capturing diverse demographic representation to ensure model applicability across different population groups. A strategically selected subset of 1,000 participants will receive HbA1c validation testing. Existing participants from thymia's research database who consented to recontact are also eligible, having completed similar voice protocols, enriching the dataset whilst reducing participant burden.

You may qualify if:

• + years of age
• English as a first language
• No language difficulties
• Geographically based in the UK
• Normal or corrected to normal eye-sight, i.e., wearing glasses/contact lenses

You may not qualify if:

• No hearing impairments

Sponsors & Collaborators

• Thymia Limited: lead

Study Sites (1)

Online

Nationwide, United Kingdom

Location

Related Publications (3)

• Kaufman JM, Thommandram A, Fossat Y. Acoustic Analysis and Prediction of Type 2 Diabetes Mellitus Using Smartphone-Recorded Voice Segments. Mayo Clin Proc Digit Health. 2023 Oct 17;1(4):534-544. doi: 10.1016/j.mcpdig.2023.08.005. eCollection 2023 Dec.

  PMID: 40206319 BACKGROUND

• Fara, S., Hickey, O., Georgescu, A., Goria, S., Molimpakis, E., Cummins, N. (2023) Bayesian Networks for the robust and unbiased prediction of depression and its symptoms utilizing speech and multimodal data. Proc. INTERSPEECH 2023, 1728-1732, doi:10.21437/Interspeech.2023-1709

  BACKGROUND

• Elbeji A, Pizzimenti M, Aguayo G, Fischer A, Ayadi H, Mauvais-Jarvis F, Riveline JP, Despotovic V, Fagherazzi G. A voice-based algorithm can predict type 2 diabetes status in USA adults: Findings from the Colive Voice study. PLOS Digit Health. 2024 Dec 19;3(12):e0000679. doi: 10.1371/journal.pdig.0000679. eCollection 2024 Dec.

  PMID: 39700066 BACKGROUND

Related Links

• Public Health England. NHS Health Check. Retrieved \[09/07/2025\]

MeSH Terms

Conditions

Diabetes Mellitus, Type 2; Diabetes Mellitus; Glucose Intolerance

Condition Hierarchy (Ancestors)

Glucose Metabolism Disorders; Metabolic Diseases; Nutritional and Metabolic Diseases; Endocrine System Diseases; Hyperglycemia

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: CROSS SECTIONAL
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: January 27, 2026
• First Posted: February 19, 2026
• Study Start: September 1, 2025
• Primary Completion: March 6, 2026
• Study Completion: March 16, 2026
• Last Updated: March 19, 2026

Record last verified: 2026-03

Locations

GB (1)