NCT07517770

Effectiveness of Artificial-Intelligence (AI) Bolus Priming Added to an Existing Fully Automated Control Algorithm (AIDANET)

• Status: Not Yet Recruiting
• Phase: N/A
• Study type: Interventional
• Enrollment: 50 (estimated)
• Sponsor: Sue Brown · Academic / Other
• Sex: All
• Age: 18 Years
• Healthy volunteers: Not accepted

Summary

Bolus Priming (BP) based on Artificial Intelligence (AI) learning of meal patterns, added to our established Automated insulin delivery as Adaptive Network (AIDANET) algorithm and running on iPhone Diabetes Assistant (iDiAs) phone wirelessly connected to Tandem Mobi insulin pump and Dexcom Continuous Glucose Monitor (CGM).

Detailed description

A randomized cross-over trial assessing glycemic control on AIDANET equipped with its standard bolus vs AIDANET AI. A secondary comparison of AIDANET AI vs a current commercial Hybrid Closed Loop (HCL) system is planned as well. Following enrollment and screening, participants will be randomized 1:1 to two 8-week sequences: Group A participants will continue to use their home Hybrid closed loop (HCL) system for 2 weeks, then switch to AIDANET for two weeks, and the switch to AIDANET AI for another 4 weeks. Group B participants will begin with 4 weeks of AIDANET AI, then switch to AIDANET for 2 weeks and then revert to their home HCL systems for the last 2 weeks of the study (Figure 1). The last two weeks of the 4-week AIDANET AI session will be used for analysis, comparing standard Ambulatory Glucose Profile (AGP) metrics across AIDANET vs AIDANET AI, with primary outcome Time in Range (TIR) (70-180 mg/dL) during the day. Secondary analyses will compare AIDANET AI 2-week AGP to HCL AGP metrics. Both analyses use randomized crossover design.

Conditions

• Type 1 Diabetes Mellitis

Interventions

Type	Name	Description
DEVICE	Hybrid Closed Loop (HCL) x 2 weeks	During the HCL session, participants will be using their own HCL systems for 2-weeks.
DEVICE	AIDANET x 2 weeks	Participant will use the AIDANET algorithm on the Mobi system with the standard Bolus Priming System (BPS) automated bolus that does not require announcement of meals.
DEVICE	AIDANET AI x 4 weeks	Participant will use the AIDANET algorithm with the addition of the Bolus Priming (BP) based on AI learning of meal patterns.

Timeline

• Start date: 2026-05-01
• Primary completion: 2027-04-30
• Completion: 2027-04-30
• First posted: 2026-04-08
• Last updated: 2026-04-08

Locations

1 site across 1 country: United States

Regulatory

• FDA-regulated device study