AI takes the wheel: smart insulin pump tested in toddlers
NCT ID NCT06017089
First seen Jun 24, 2026 · Last updated Jun 26, 2026 · Updated 1 time
Summary
This pilot study tested an artificial intelligence system that helps manage insulin delivery in young children (ages 2 to 6) with type 1 diabetes. The system combines a continuous glucose monitor, an insulin pump, and an AI advisor that adjusts pump settings automatically. Thirty-three children used the system at home for eight weeks to see if it was safe and improved blood sugar control.
What this could mean
Our plain-language read of the trial. This is informational only, not medical advice or a prediction.
- Active substance
- AI-based Advisor system (Tandem t:slim X2 with Control-IQ, Dexcom CGM, and cloud dashboard)
- What this could lead to
- If successful, this AI system could help young children with type 1 diabetes maintain safer blood sugar levels with less effort from parents.
- What could go wrong
- This is a small pilot study with only 33 children, so results may not apply to everyone. The AI system may not work as well in real-world conditions or for all age groups.
This is an AI summary of the original study and may miss details. Read our disclaimer.
Study facts
What this study's own registry entry says, in plain language.
- Phase
-
Not a phased trial
Phase numbers describe drug development. The registry uses this when they do not apply, as it does for trials of devices, procedures or behaviour changes, and for observational studies.
- Participants
-
33 people
The number who actually took part.
- Started
-
Nov 2023
- Finished
-
Jun 2024
- Lead sponsor
-
Other sponsor
The registry's catch-all category, for sponsors it does not file as a company, a government agency, or a research network.
Who can take part
This study's own entry requirements. Only the study team can say for certain whether you qualify.
- Ages
-
2 to 5 years
- Sex
-
Anyone
- Healthy volunteers
-
Not accepted
This study is not open to healthy volunteers. The entry requirements below say who it is open to.
Show the full entry requirements Hide the full entry requirements
Copied word for word from the study's registry entry, so the wording is the study team's rather than ours.
Inclusion Criteria: 1. Clinical diagnosis, based on investigator assessment, of type 1 diabetes for at least 1 month 2. Familiarity and use of a carbohydrate ratio for meal boluses 3. Age ≥2 and \<6 years old 4. Using a Dexcom CGM at the time of enrollment, with use on at least 21 out of the prior 28 days 5. Living with one or more parent/legal guardian knowledgeable about emergency procedures for severe hypoglycemia and able to contact emergency services and study staff 6. Parent/guardian has a phone that can run the Tandem t:connect Mobile App (typically Android 10 or above or iPhone Operating System (iOS) 15 or above) 7. Willingness to use the t:connect Mobile App as needed during the study and ensure connectivity for a data upload at least once per day 8. Investigator has confidence that the parent can successfully operate all study devices and is capable of adhering to the protocol 9. Willingness to switch to lispro (Humalog) or aspart (Novolog) if not using already, and to use no other insulin besides lispro (Humalog) or aspart (Novolog) during the study for participants using a study162 provided Tandem pump during the study 10. Total daily insulin dose (TDD) at least 5 Units/day 11. Body weight at least 20 pounds (lbs) 12. Willingness not to start any new non-insulin glucose-lowering agent during the course of the trial 13. Participant and parent(s)/guardian(s) willingness to participate in all training sessions as directed by study staff 14. Parent/guardian proficient in reading and writing English 15. Live in the United States, with no plans to move outside the United States during the study period Exclusion Criteria: 1. Concurrent use of any non-insulin glucose-lowering agent (including GLP-1 agonists, Symlin, DPP-4 inhibitors, SGLT-2 inhibitors, sulfonylureas) 2. Hemophilia or any other bleeding disorder 3. History of \>1 severe hypoglycemic event with seizure or loss of consciousness in the last 3 months 4. History of \>1 diabetic ketoacidosis (DKA) event in the last 6 months not related to illness, infusion set failure, or initial diagnosis 5. History of chronic renal disease or currently on hemodialysis 6. History of adrenal insufficiency 7. Hypothyroidism that is not adequately treated in the opinion of the investigator 8. Use of oral or injectable steroids within the last 8 weeks 9. Known, ongoing adhesive intolerance 10. Plans to receive blood transfusions or erythropoietin injections during the course of the study 11. A condition, which in the opinion of the investigator or designee, would put the participant or study at risk 12. Participation in another pharmaceutical or device trial at the time of enrollment or during the study 13. Having immediate family members employed by Tandem Diabetes Care, Inc. or Dexcom, Inc., or having a direct supervisor at place of employment who is also directly involved in conducting the clinical trial (as a study investigator, coordinator, etc.); or having a first-degree relative who is directly involved in conducting the clinical trial
Get updates
Get notified about this study
Sign up to get updates when this study changes or when new studies for Type 1 diabetes are added.
Genom att skicka in godkänner du våra Användarvillkor
Conditions
The condition(s) this trial relates to.
As listed by the trial registrant
The condition terms exactly as the trial's registrant entered them.
Contacts and locations
Locations
-
Barbara Davis Center, University of Colorado
Aurora, Colorado, 80045, United States
-
Stanford University
Stanford, California, 94305, United States
-
University of Virginia
Charlottesville, Virginia, 22903, United States
More trials for these conditions
Other studies related to the condition(s) this trial covers.
- Tiny horses, big lessons: can ponies help kids tame diabetes?
- Can a math model tune insulin pumps better than standard care?
- Can a group program stop eating disorders in type 1 diabetes?
- Can a Two-Punch immune therapy save insulin cells in newly diagnosed diabetes?
- Can a smart insulin pump tailored for pregnancy protect mothers and babies?
- Can an automated pancreas system make type 1 diabetes safer in the real world?