NCT06728059

Safety and Feasibility of a Machine-Learning Bolus Priming Added to Existing Control Algorithm

• Status: Recruiting
• Phase: N/A
• Study type: Interventional
• Enrollment: 16 (estimated)
• Sponsor: Sue Brown · Academic / Other
• Sex: All
• Age: 18 Years
• Healthy volunteers: Not accepted

Summary

A randomized crossover trial assessing glycemic control using Reinforcement Learning trained Bolus Priming System (BPS\_RL) added to the the Automated Insulin Delivery as Adaptive NETwork (AIDANET algorithm) compared to the original AIDANET algorithm.

Detailed description

After receiving training on the study equipment, participants will use the AIDANET system at home for 7 days/6 nights to establish a baseline and initialize the control algorithm. Participants will then be studied at a hotel session for 3 days/2 nights. Participants will transition to home use of AIDANET+ BPS\_RL for 7 days/6 nights.

Conditions

• Type 1 Diabetes

Interventions

Type	Name	Description
DEVICE	Automated Insulin Delivery Adaptive NETwork (AIDANET)	Group A participants will use the AIDANET system at home for 7 days/6 nights. They will continue use of AIDANET system for 18 hours during the hotel session and then use AIDANET+BPS\_RL for 18 hours during the hotel session.
DEVICE	AIDANET+ BPS_RL→AIDANET	Group B participant will use the AIDANET+BPS\_RL system for 18 hours during the hotel session and will then use AIDANET system for 18 hours during the hotel session. They will continue to use AIDANET+BPS\_RL system at home for 7 days/6 night and then use the AIDANET system at home for 7 days/6 nights.

Timeline

• Start date: 2025-02-05
• Primary completion: 2025-07-31
• Completion: 2025-07-31
• First posted: 2024-12-11
• Last updated: 2025-05-15

Locations

1 site across 1 country: United States

Regulatory

• FDA-regulated device study