RT Generic
T1 Evaluation of a mobile AI-powered decision support system for insulin dosing and glucose prediction in type 1 diabetes: The glUCModel clinical trial protocol.
A1 Hidalgo Pérez, José Ignacio
A1 Maqueda, Esther
A1 Velasco, J. Manuel
A1 Botella, Marta
A1 Garnica Alcázar, Antonio Óscar
A1 Velasco Cabo, José Manuel
AB Introduction: Artificial Intelligence (AI) opens new possibilities for supporting decision-making in diabetes care. glUCModel is a mobile application that provides insulin dose recommendations, predictions of glucose levels, and predictive glucose alerts, utilizing proprietary AI technology. Unlike conventional tools, glUCModel provides early warnings of hypoglycemia and hyperglycemia up to two hours in advance. glUCModel also offers general and customizable glucose prediction models to support the user in decision making. Methods: We will conduct a randomized, open-label, controlled clinical trial with two parallel arms involving people with type 1 diabetes and suboptimal metabolic control, treated with multiple daily insulin injections (MDI). The study will take place at two Spanish university hospitals. The total duration is 14 weeks, comprising a 2-week run-in phase and a 12-week active treatment phase. Patients in the intervention arm will use glUCModel alongside standard therapy. Primary Outcomes: Time in range (TIR) defined as 70–180 mg/dL during the last 2 weeks of the intervention. Usability of the app. Secondary Outcomes: Reduction in hypoglycemia and hyperglycemia episodes, glycemic variability, treatment satisfaction (DTSQ and ITSQ), and adherence to insulin correction recommendations. Discussion: This study aims to evaluate the safety and efficacy of integrating predictive models into insulin therapy management via a user-centered mobile app. Insights may inform future digital health strategies in type 1 diabetes care. Ethics and dissemination: Ethical approval to conduct this study has been granted by the University Hospital ”Principe de Asturias” of Alcal´a de Henares Ethical committee (EC-11/2018). Participants in the study will provide written consent.
YR 2025
FD 2025-12-23
LK https://hdl.handle.net/20.500.14352/129640
UL https://hdl.handle.net/20.500.14352/129640
LA spa
NO Agencia Estatal de Investigación
NO Ministerio de Ciencia Innovación y Universidades
DS Docta Complutense
RD 20 ene 2026