Miniaturized Neural Networks for Deploying Fully Closed Loop Insulin Delivery Systems: A Pilot Study Featuring Flexible Meal Announcement Options
Authors' conclusion
This pilot-feasibility study demonstrates that the AIDANET system provides safe glycemic control. The small sample size (n = 6) limits overall generalizability, and further larger, statistically powered trials to validate these results are warranted.
Study context
- Population
- Adults with T1Dcrossover
- Participants
- 6 adults
- Comparison
- AIDANET vs usual care
- AIDANETn = 6
- Usual caren = 6reference
Methodological detailspilot, free-living conditions
- Pilot
- Free-living conditions
Primary result
As reported in the abstract
Mean glucose · 7 days
Further findings
| Outcome | AIDANET | Usual care |
|---|---|---|
| TIR 70 to 180 mg/dL · 7 days | 66.4% ± 8.3% | 63.3% ± 14.9% |
AIDANET hybrid bolusing options · 1 day each
- Carbohydrate counting: Time-in-range (TIR)
- 57.1%
- Carbohydrate counting: Time-below-range (TBR)
- 0.6%
- Easy Bolus: TIR
- 70.5%
- Easy Bolus: TBR
- 1.5%
Safety
| Outcome | AIDANET | Usual care |
|---|---|---|
| TBR <70 mg/dL · 7 daysRemained within acceptable margins | 1.6 ± 1.8 | 0.9 ± 1 |
Serious adverse events
- Serious adverse events during the study
- 0
Original publication
Miniaturized Neural Networks for Deploying Fully Closed Loop Insulin Delivery Systems: A Pilot Study Featuring Flexible Meal Announcement Options. J Diabetes Sci Technol. Published 9 August 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →