AI helper (Tia Bete) on WhatsApp to assist with carb counting and insulin dosing for people with type 1 diabetes

Efficacy and Safety of an Artificial Intelligence Tool for Carbohydrate Counting (Tiabete) in Children and Adults With Type 1 Diabetes Mellitus

Not applicable Interventional University of Sao Paulo · NCT07150052

This trial will test whether an AI tool delivered via WhatsApp can help children and adults with type 1 diabetes count carbohydrates and adjust insulin doses more accurately.

Quick facts

PhaseNot applicable
Study typeInterventional
Enrollment50 (estimated)
Ages6 Years and up
SexAll
SponsorUniversity of Sao Paulo Academic / other
Locations1 site (São Paulo, São Paulo)
Trial IDNCT07150052 on ClinicalTrials.gov

What this trial studies

This is a prospective, longitudinal interventional study testing the AI-based tool Tia Bete, which gives real-time carbohydrate-counting and insulin-dose recommendations via WhatsApp using personalized insulin-to-carbohydrate ratios and insulin sensitivity factors. Participants include children (6–18 years) with caregiver involvement and adults over 18 who are on a basal-bolus insulin regimen and have recent HbA1c between 7.2% and 10.5%. The protocol requires regular outpatient follow-up at the University of São Paulo and a minimum frequency of interaction with the tool during the study. Key exclusions include inability to use WhatsApp, illiteracy, failure to follow instructions, or interacting with the tool fewer than three days per week.

Who should consider this trial

Good fit: Ideal candidates are people with type 1 diabetes aged 6 years and older (with caregiver support for children), on a basal-bolus regimen, with HbA1c 7.2–10.5% in the past six months, who use WhatsApp and can follow study instructions.

Not a fit: Patients who cannot use WhatsApp, are illiterate, cannot attend periodic clinic visits, or interact with the tool less than three days per week are unlikely to benefit from this intervention.

Why it matters

Potential benefit: If successful, the tool could improve carb-counting accuracy and lead to better daytime blood sugar control with fewer dosing errors.

How similar studies have performed: App- and AI-based carb-counting tools have shown promising improvements in meal dosing accuracy in some adult studies, but pediatric data and WhatsApp-delivered AI support remain limited.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* Diagnosis of type 1 diabetes mellitus
* children between 6 and 18 years old and their caregivers; and adults \> 18 years old.

Glycated Hb between 7.2-10.5% in the last 6 months. Being on a basal-bolus regimen Participating in and understanding the guidelines on how to use the program to be tested in this study Agreeing to the free and informed consent form. Performing periodic monitoring at the DM outpatient clinic at HC-FMUSP

Exclusion Criteria:

* Not understanding the instructions.
* Being illiterate
* Not attending the visits proposed by the study
* Not using the tool via WhatsApp.
* Not accepting consent.
* Interacting with the tool less than 3 days a week during the study period.

Where this trial is running

São Paulo, São Paulo

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Type 1 Diabetestype 1 diabetestechnologyartificial intelligencecarb counting
Last reviewed 2026-06-10 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.