Evaluation of a Mobile AI-powered Decision Support System for Insulin Dosing and Glucose Prediction in Type 1 Diabetes: The glUCModel Clinical Trial Protocol (glUCModel-1)

The goal of this clinical trial is to evaluate the safety and efficacy of integrating predictive models into insulin therapy management via the user-centered glUCModel mobile app in People with Type 1 Diabetes Mellitus following Multiple Insulin Dosing therapy. Participants will be aged 18 to 65 years. The main questions it aims to answer are:

Does using the app improve glycaemic control, as measured by time in range? Does using the app reduce the number of episodes of hyperglycaemia and hypoglycaemia? Are the app's design and functionality adequate?

The study will comprise four phases:ses}):

• Screening phase: Informed consent, collection of sociodemographic and clinical data, and baseline Pittsburg, IFIS, and DTSQ questionnaires.
• Run-in phase: 2 weeks of standard care with CGM. Data will be used to generate personalized predictive models in the intervention group.
• Active treatment phase: Participants continue MDI therapy. The intervention group will additionally use the glUCModel mobile app. CGM data from the final 2 weeks will be analyzed.
• Evaluation and analysis phase: Participants will complete the uMARS, Pittsburgh, and DTSQ questionnaires. Statistical analysis and correlations among outcomes will be processed.

Study Overview

• Status: Recruiting
• Conditions: Diabetes (Insulin-requiring, Type 1 or Type 2)
• Intervention / Treatment: Other: glUCModel app

Detailed Description

Diabetes mellitus is a chronic, metabolic disorder characterized by impaired regulation of blood glucose, affecting more than 400 million people worldwide. Insulin, a hormone produced by the pancreas, facilitates the uptake of glucose into cells for energy production. In diabetes, either insufficient insulin is produced or the body cannot use it effectively, leading to persistent hyperglycemia. Over time, uncontrolled glucose levels can result in serious complications, including cardiovascular disease, neuropathy, retinopathy, and nephropathy. Effective management is therefore essential to prevent both acute and long-term adverse outcomes.

Two main forms of diabetes can be distinguished. Type 1 diabetes mellitus (T1DM) is an autoimmune condition in which pancreatic β-cells are destroyed, resulting in absolute insulin deficiency. It accounts for approximately 10% of all cases. Individuals with T1DM require lifelong insulin replacement therapy, typically delivered as multiple daily injections (MDI) or via an insulin pump. In contrast, type 2 diabetes mellitus (T2DM), the more prevalent form, is characterized primarily by insulin resistance. While insulin production is preserved in early stages, progressive dysfunction may ultimately necessitate pharmacological therapy, including insulin. Lifestyle interventions such as healthy diet and physical activity can delay or prevent T2DM onset and progression.

For individuals with diabetes, day-to-day self-management requires frequent glucose monitoring and insulin dose adjustments that must take into account meals, physical activity, stress, illness, and other factors. Capillary glucose meters and, more recently, continuous glucose monitoring systems (CGMs) have greatly improved access to real-time glucose data. However, interpreting these data and deciding on corrective actions remains challenging, and errors in insulin dosing can lead to hypoglycemia or persistent hyperglycemia. Both acute complications and the constant decision-making load contribute to reduced quality of life and treatment fatigue.

To support patients in these complex tasks, predictive models of glucose dynamics have been extensively investigated. Accurate prediction could enable early warnings of hypo- or hyperglycemia and assist in optimizing insulin therapy. The ultimate vision is the development of a fully automated ''artificial pancreas'' combining glucose sensing, insulin delivery, and robust prediction algorithms. Various machine learning (ML) approaches have been explored for glucose forecasting, including Genetic Programming , K-Nearest Neighbours , Grammatical Evolution, and, most prominently, Neural Networks. Among neural architectures, Long Short-Term Memory (LSTM) and other recurrent models have demonstrated strong performance for time-series data such as CGM traces, although convolutional and multilayer perceptron (MLP) networks have also been applied. Despite encouraging results, challenges remain in ensuring accuracy, robustness, and real-world usability across diverse patient populations.

Managing T1DM, particularly in patients using MDI, continues to pose a major challenge. While CGM and insulin pumps have improved outcomes, decisions about insulin dosing still depend heavily on patient intuition and experience, leaving room for error and variability. There is therefore a clear need for decision-support tools that combine predictive analytics with personalized recommendations to enhance safety, autonomy, and treatment adherence.

The glUCModel mobile application was developed to address this need. Since its early versions, it integrates proprietary, patented artificial intelligence models to provide real-time insulin recommendations, short-term glucose forecasts, and predictive alerts for hypo- and hyperglycemia. With a forecast horizon of up to two hours, the system aims to reduce glycemic variability and support timely corrective actions.

This protocol describes a randomized, open-label clinical study to evaluate the efficacy and safety of the glUCModel application in patients with T1DM using MDI therapy. The primary objective is to assess improvement in short-term glycemic control, measured by the percentage of time spent in target range (70-180 mg/dL). Secondary objectives include reductions in glycemic excursions, improved treatment satisfaction, and evaluation of usability and adherence in a real-world setting.

• Study Type: Interventional
• Enrollment (Estimated): 34
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Ignacio Hidalgo, PhD; Phone Number: +34679562712; Email: hidalgo@dacya.ucm.es

Study Locations

• Spain
  • Madrid
    • Madrid, Madrid, Spain, 280240
      • Not yet recruiting
      • Universidad Complutense de Madrid
      • Contact: Ignacio Hidalgo, PhD; Phone Number: +34679562712; Email: hidalgo@dacya.ucm.es
      • Contact: Jose-Manuel Velasco, PhD; Phone Number: +34619549105; Email: mvelascc@ucm.es
  • Toledo
    • Toledo, Toledo, Spain, 45007
      • Recruiting
      • Hospital Universitario de Toledo
      • Contact: Esther Maqueda, MD; Phone Number: +34 679562712; Email: esthemaq@ucm.es
      • Contact: J. Ignacio Hidalgo, PhD; Phone Number: +34913947537; Email: HIDALGO@UCM.ES

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• HbA1c < 9%

• Currently following an MDI Bolus-Basal therapy.

  • Wearing CGMs connected to a mobile phone.
  • Spanish language proficiency.
  • Willingness to participate in the trial.
  • At least one year since the time of diabetes diagnosis.
  • Ability to use a mobile application like glUCModel.
  • Own a mobile phone running Android or iOS operating system.
  • Ability to follow a Portion-controlled diet for diabetes.
  • Educated to do an active management of insulin dosing

Exclusion Criteria:

• HbA1c < 9%.
• Not wearing CGMs.
• Non-Spanish language proficiency.
• Less than one year since the time of diabetes diagnosis
• Unable to use a mobile application like glUCModel
• Unable to follow a Portion-controlled diet for diabetes
• Unable to do an active management of insulin dosing.
• Diagnosed with a significant psychiatric disorder.
• Subjects in treatment with corticoids
• Patients who have required hospitalization or surgery in the last six months.
• Pregnancy or planning a pregnancy

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Intervention; Participants continue MDI therapy. The intervention group will additionally use the glUCModel app. CGM data from the final 2 weeks will be analyzed	Other: glUCModel app; The intervention consists on using glUCModel, an application designed to help people with diabetes. It features a suite of artificial intelligence tools and statistical techniques for capturing and managing key information that people with diabetes need to track, as well as for predicting glucose values to aid users in informed decision-making.
No Intervention: Control; Participants continue MDI therapy. CGM data from the final 2 weeks will be analyzed

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Time in Range (TIR)	Time in Range (TIR), defined as the percentage of time that interstitial glucose is between 70-180 mg/dL during the final 2 weeks of the intervention phase	During the last 2 weeks of intervention
Usability and adherence	Patient-reported outcomes on usability and adherence through uMARS. The usability of the app will be evaluated using the Spanish Version of the User Version of the Mobile Application Rating Scale (uMARS). This scale provides a comprehensive and objective measure of app usability and consists of 20 items. Each item is rated on a 5-point scale, ranging from 1 (inadequate) to 5 (excellent).	Two weeks

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Frequency of Level 1 hypoglycemia	Frequency in minutes of Level 1 hypoglycemia (40 ≤ CGM glucose < 55).	During the last 2 weeks of intervention
Frequency of Level 2 hypoglycemias	Frequency in minutes of Level 2 hypoglycemia (55 ≤ interstitial glucose ≤ 70)	During the last 2 weeks of intervention
Frequency of Level 1 hyperglycemias	Frequency in minutes of Level 1 hyperglycemia (180 ≤ CGM glucose ≤ 240).	During the last 2 weeks of intervention
Frequency of Level 2 hyperglycemias	Frequency in minutes of Level 2 hyperglycemia (241 ≤ interstitial glucose ≤ 400).	During the last 2 weeks of the intervention
Duration of Level 1 hypoglycemias	Average Duration in minutes of Level 1 hypoglycemia (40 ≤ CGM glucose < 55)	During the last 2 weeks of intervention
Duration of Level 2 hypoglycemia	Average duration in minutes of Level 2 hypoglycemia (55 ≤ interstitial glucose ≤ 70).	During the last 2 weeks of intervention
Duration of Level 1 hyperglycemias	Average duration in minutes of Level 1 hyperglycemia (180 ≤ CGM glucose ≤ 240).	During the last 2 weeks of intervention
Duration of Level 2 hyperglycemias	Average duration in minutes of Level 2 hyperglycemia (241 ≤ interstitial glucose ≤ 400).	During the last 2 weeks of the intervention
Glycemic coefficient of variation	Coefficient of Variation (CV) is calculated using the mean and the standard deviation of the glucose values. Coefficient of Variation (CV) is calculated by dividing the Standard Deviation by the mean of the glucose values.	During the last 2 weeks of intervention
Glycemic variability	Glycemic variability is computed as the standard deviation. Standard Deviation (SD) is measured as the dispersion of glucose values from the average.	During the last 2 weeks of intervention
Accepted Recommendations	Percentage of insulin recommendations accepted and applied by the user from the total number of recommendations requested.	During the last 2 weeks of intervention
Quality of predictions	Quality of predictions measured using the Parkes Errod Grid analysis.	During the last 2 weeks of intervention
Treatment satisfaction	Treatment satisfaction using the Diabetes Treatment Satisfaction Questionnaire (DTSQ)	last 2 weeks of the intervention

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Sleep Quality before the intervention	We will evaluate Sleep Quality before and after the intervention. The Pittsburg Sleep Quality Index (PSQI) will be used. The Pittsburgh Sleep Quality Index (PSQI) is a self-rated questionnaire that assesses sleep quality and disturbances over a 1-month time interval. Nineteen individual items generate seven "component" scores: subjective sleep quality, sleep latency, sleep duration, habitual sleep efficiency, sleep disturbances, use of sleeping medication, and daytime dysfunction. The sum of scores for these seven components yields one global score. The seven component scores are then summed to obtain a global PSQI score, which ranges from 0 to 21. Higher scores indicate poorer sleep quality, with a score greater than 5 suggesting significant sleep difficulties. https://www.sleep.pitt.edu/psqi	The day of the start of the intervention
Sleep Quality after the intervention	We will evaluate Sleep Quality before and after the intervention. The Pittsburg Sleep Quality Index (PSQI) will be used. The Pittsburgh Sleep Quality Index (PSQI) is a self-rated questionnaire that assesses sleep quality and disturbances over a 1-month time interval. Nineteen individual items generate seven "component" scores: subjective sleep quality, sleep latency, sleep duration, habitual sleep efficiency, sleep disturbances, use of sleeping medication, and daytime dysfunction. The sum of scores for these seven components yields one global score. The seven component scores are then summed to obtain a global PSQI score, which ranges from 0 to 21. Higher scores indicate poorer sleep quality, with a score greater than 5 suggesting significant sleep difficulties. https://www.sleep.pitt.edu/psqi	Two weeks after the day of the end of the intervention

Collaborators and Investigators

• Sponsor: Universidad Complutense de Madrid
• Collaborators: Hospital de Toledo; Bioinspired Intelligence SL

Study record dates

Study Major Dates

• Study Start (Actual): July 11, 2025
• Primary Completion (Estimated): February 1, 2026
• Study Completion (Estimated): June 1, 2026

Study Registration Dates

• First Submitted: November 30, 2025
• First Submitted That Met QC Criteria: December 12, 2025
• First Posted (Estimated): December 26, 2025

Study Record Updates

• Last Update Posted (Actual): January 6, 2026
• Last Update Submitted That Met QC Criteria: January 2, 2026
• Last Verified: December 1, 2025

More Information

Terms related to this study

• Keywords: Diabetes; Artificial Intelligence; Bolus recomendation
• Additional Relevant MeSH Terms: Endocrine System Diseases; Metabolic Diseases; Glucose Metabolism Disorders; Nutritional and Metabolic Diseases; Diabetes Mellitus
• Other Study ID Numbers: glUCModel-HUT; PDC2022-133429-I00 (Other Grant/Funding Number: Agencia Estatal de Investigación -Ministerio de Ciencia, Innovación y Universidades-Gobierno de España); PID2021-125549OB-I00 (Other Grant/Funding Number: Agencia Estatal de Investigación -Ministerio de Ciencia, Innovación y Universidades-Gobierno de España); PID2024-158129OB-I00 (Other Grant/Funding Number: Agencia Estatal de Investigación -Ministerio de Ciencia, Innovación y Universidades-Gobierno de España)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED
• IPD Plan Description: It depends on the autorization of the University

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No