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

Обзор

IntroductionType 1 Diabetes Mellitus (T1DM) requires lifelong exogenous insulin therapy, along with self-management strategies, such as carbohydrate counting, to appropriately adjust insulin doses in response to meals. However, many patients face challenges in adhering consistently to carbohydrate counting, compromising glycemic control and increasing the risk of diabetes-related complications. Emerging technologies, such as artificial intelligence (AI), hold significant potential for optimizing disease management by enhancing the accuracy and efficiency of self-care practices. ObjectiveThe primary aim of this study is to evaluate the efficacy and safety of the AI-based tool Tia Bete, designed to assist patients with T1DM in carbohydrate counting and insulin dose adjustment. The tool provides real-time recommendations based on personalized insulin-to-carbohydrate ratios, insulin sensitivity factors, and individualized glycemic goals. MethodsThis is a prospective, longitudinal study involving 40 patients with T1DM, stratified into two cohorts: 20 children and adolescents (6-18 years) and 20 adults (\>18 years), recruited at the Hospital das Clínicas, University of São Paulo (HCFMUSP). Participants will be assessed before and after six months of using the Tia Bete tool. Glycemic control will be evaluated using parameters such as glycated hemoglobin (HbA1c), time in range, and the incidence of hypoglycemia and hyperglycemia. Quality of life and satisfaction with the tool will also be assessed. Overview of the AI Tool Launched in June 2024, Tia Bete is an AI-based digital solution designed to facilitate glycemic control and improve quality of life for patients with T1DM. By offering real-time assistance with carbohydrate counting and insulin dose recommendations, the tool aims to enhance patient autonomy while enabling flexible treatment adherence in collaboration with their multidisciplinary healthcare team. Results and ConclusionsPreliminary data indicate high engagement, with over 35,000 active users interacting with the platform at least four times per week. Initial findings suggest significant improvements in glycemic control, as well as increased confidence in carbohydrate counting and insulin dose adjustments. The dissemination of this project is crucial for advancing T1DM care, offering a scalable, accessible, and effective technological solution. Final results are expected by October 2025.

Вмешательства

• Другое Artifical intelligence in whatsapp
  AI-based tool Tia Bete, designed to assist patients with T1DM in carbohydrate counting and insulin dose adjustment. The tool provides real-time recommendations based on personalized insulin-to-carbohydrate ratios, insulin sensitivity factors, and individualized glycemic goals.

Первичные конечные точки

• Glycated hemoglobin (HbA1c) [Срок оценки: 6 months]
• - time in range ( percentage) - hypoglycemia (mean daily percentage of hypo- glycemia less than 70 mg/dl) - hyperglycemia(mean daily percentage of hyper- glycemia above than 180mg/dl) [Срок оценки: 6 months]

Вторичные конечные точки (2)

• Quality of life [Срок оценки: 6 months]
• Satisfaction with the tool [Срок оценки: 6 months]

Критерии участия

Критерии включения

• 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

Критерии исключения

• 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.

Критерии приведены из реестра в оригинале (на английском). Окончательную оценку соответствия проводит исследовательский центр.

Здоровые добровольцы: Нет

Дизайн исследования

Распределение

Не применимо

Модель

Одна группа

Маскирование

Открытое

Основная цель

Поддерживающая терапия

Центры проведения

Бразилия · 1 центр

• University of Sao Paulo — São Paulo

Публикации

• Cengiz E, Danne T, Ahmad T, Ayyavoo A, Beran D, Ehtisham S, Fairchild J, Jarosz-Chobot P, Ng SM, Paterson M, Codner E. ISPAD Clinical Practice Consensus Guidelines 2022: Insulin treatment in children and adolescents with diabetes. Pediatr Diabetes. 2022 Dec;23(8):1277-1296. doi: 10.1111/pedi.13442. No abstract available. PMID 36537533
• Annan SF, Higgins LA, Jelleryd E, Hannon T, Rose S, Salis S, Baptista J, Chinchilla P, Marcovecchio ML. ISPAD Clinical Practice Consensus Guidelines 2022: Nutritional management in children and adolescents with diabetes. Pediatr Diabetes. 2022 Dec;23(8):1297-1321. doi: 10.1111/pedi.13429. Epub 2022 Dec 5. No abstract available. PMID 36468223

Идентификаторы

NCT: NCT07150052 · USaoPauloTiabete

Первоисточники (государственные реестры)

• ClinicalTrials.gov (NIH, США)

Открыть это исследование на ClinicalTrials.gov ↗