Training and Evaluation of a Breath-Based Glucose Estimation Algorithm in People With Type 2 Diabetes: The BOYDSense-GM Study
Authors' conclusion
This study validates the potential of breath-based VOC analysis for non-invasive SMBG in T2D, demonstrating reliability, usability, and patient acceptance. Further optimization is needed to improve accuracy, particularly at high glucose levels, but the technology shows promise for enhancing diabetes management and screening.
Study context
- Population
- Adults with T2D not requiring prandial insulin; standardized meal test with venous, capillary and breath volatile organic compounds (VOC) measurements at 7 time points
- Participants
- 130 adults
- Comparison
- Breath VOC-based glucose estimation vs blood glucose
- Trainingn = 100
- Validationn = 30
- Outcome
- Blood glucose estimates within Parkes error grid zones A or B
Methodological detailsprospective, cross-sectional, single-center, training and validation phases
- Prospective
- Cross-sectional
- Single-center
- Training and validation phases
Performance
As reported in the abstract
| Test or model | Value | T2D grid zones A or B |
|---|---|---|
| Validation | 98.7% | 99.7% |
Validation
Value98.7%
T2D grid zones A or B99.7%
Further findings
Measurements valid on first breath
- Measurements valid on the first breath
- 99%
User feedback
- Strong enthusiasm for a non-invasive device; most participants willing to use it regularly
Safety
- VOC-based device demonstrated high reliability and safety
Original publication
Training and Evaluation of a Breath-Based Glucose Estimation Algorithm in People With Type 2 Diabetes: The BOYDSense-GM Study. J Diabetes Sci Technol. Published 26 February 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →