Characterization of Type 1 Diabetes Subgroup: An Artificial Intelligence Analysis of Clinical and Glucometric Features
For patients and families
In plain language
An automatic summary of structured registry data. It is an orientation aid, not a substitute for the official protocol or a physician assessment.
- What is being studied
- This is an observational study: the protocol does not assign a study treatment.
- Who it may be relevant to
- Registry conditions: Type 1 Diabetes Mellitus. Basic parameters: from 18 years · All.
- What needs checking
- Age, condition and sex are only basic indicators. Prior treatment, laboratory values and other mandatory requirements appear in the eligibility criteria below.
- Where it takes place
- Spain
- Next step
- Save the trial, show it to the treating physician, and confirm current recruitment with the study center. Costs, documents and travel →
Unsure about the terms? Read our patient guide →
Official title
Caracterización de Subgrupos de Personas Con Diabetes Tipo 1: análisis de características clínicas y glucométricas Utilizando Una aproximación de Inteligencia Artificial
Overview
The goal of this observational study is to characterize different subgroups among patients with type 1 diabetes. The main research question is: Are there distinct subtypes among people with type 1 diabetes? Participants will be invited to take part in the study by allowing access to their health data. They will not be required to undergo any additional examinations, tests, visits, or interventions.
Detailed description
Study Description
Main Objective The primary objective of this study is to characterize subgroups of individuals with type 1 diabetes (T1D) based on clinical and glucometric features using an artificial intelligence (AI) approach.
Secondary objectives Evaluate cluster stability over time (1, 2, and 3 years); assess cluster utility for predicting complications; analyze the contribution of different clinical variables to cluster characterization and its evolution over time; and model endpoints such as diabetes-related complications.
Study Design This is an ambispective observational study.
Disease Under Study Type 1 Diabetes Mellitus.
Methodology This ambispective observational study will use information extracted from participants' electronic medical records and glucometric data obtained from the corresponding monitoring platforms. The data will be analyzed using artificial intelligence techniques to identify patterns and potential subgroups within the type 1 diabetes population.
Study Population and Sample Size The study population includes individuals with type 1 diabetes (T1D) who are being followed at the Endocrinology and Nutrition Department of Hospital de la Santa Creu i Sant Pau. As this is an exploratory study, no formal sample size calculation is required. Approximately 800 patients are expected to be included.
Primary outcome measures
- Type 1 diabetes clusters [Time frame: Subgroups defined based on data from the year 2024.]
Secondary outcome measures (12)
- Cluster stability over time [Time frame: 2024 - 2027]
- Acute and chronic diabetes complications [Time frame: 2024-2027]
- Glycemic control: mean glucose [Time frame: 2024-2027]
- Glycemic control: GMI (glucose management indicator) [Time frame: 2024-2027]
- Glycemic control: CV (coefficient of variation) [Time frame: 2024-2027]
- Glycemic control: time in range [Time frame: 2024-2027]
- HbA1c [Time frame: 2024-2027]
- Lipid profile [Time frame: 2024-2027]
- Creatinine [Time frame: 2024-2027]
- Estimated glomerular filtration rate [Time frame: 2024-2027]
- Albuminuria [Time frame: 2024-2027]
- Antihypertensive treatment [Time frame: 2024-2027]
Eligibility criteria
Inclusion criteria
- Individuals with type 1 diabetes (T1D) aged 18 years or older.
- T1D individuals expected to have regular follow-up at the Endocrinology and Nutrition Department of Hospital de la Santa Creu i Sant Pau.
- Users of continuous glucose monitoring (CGM) systems for at least the last 6 months of 2024.
- Willingness and ability to provide written informed consent to participate in the study (by the patient or his/her representative).
Exclusion criteria
- Presence of severe comorbidities or medical conditions that, in the investigator's judgment, could interfere with participation in the study or the interpretation of results. This circumstance is expected to be exceptional, as the study aims to be as inclusive as possible.
Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.
Healthy volunteers: No
Study design
- Observational model
- Case-only
Study locations
Spain · 1 center
- Hospital de la Santa Creu i Sant Pau, Barcelona, Barcelona 08041 — Barcelona
Publications
- Goldstein A, Shahar Y, Weisman Raymond M, Peleg H, Ben-Chetrit E, Ben-Yehuda A, Shalom E, Goldstein C, Shiloh SS, Almoznino G. Multi-Dimensional Validation of the Integration of Syntactic and Semantic Distance Measures for Clustering Fibromyalgia Patients in the Rheumatic Monitor Big Data Study. Bioengineering (Basel). 2024 Jan 19;11(1):97. doi: 10.3390/bioengineering11010097. PMID 38275577
- Celeux G, Govaert G. Gaussian parsimonious clustering models. Pattern Recognit. 1995 May;28(5):781-93.
- Sammouda R, El-Zaart A. An Optimized Approach for Prostate Image Segmentation Using K-Means Clustering Algorithm with Elbow Method. Comput Intell Neurosci. 2021 Nov 15;2021:4553832. doi: 10.1155/2021/4553832. eCollection 2021. PMID 34819951
- Vigers T, Chan CL, Snell-Bergeon J, Bjornstad P, Zeitler PS, Forlenza G, Pyle L. cgmanalysis: An R package for descriptive analysis of continuous glucose monitor data. PLoS One. 2019 Oct 11;14(10):e0216851. doi: 10.1371/journal.pone.0216851. eCollection 2019. PMID 31603912
- Kovatchev B, Lobo B. Clinically Similar Clusters of Daily Continuous Glucose Monitoring Profiles: Tracking the Progression of Glycemic Control Over Time. Diabetes Technol Ther. 2023 Aug;25(8):519-528. doi: 10.1089/dia.2023.0117. PMID 37130300
- Tobias DK, Merino J, Ahmad A, Aiken C, Benham JL, Bodhini D, Clark AL, Colclough K, Corcoy R, Cromer SJ, Duan D, Felton JL, Francis EC, Gillard P, Gingras V, Gaillard R, Haider E, Hughes A, Ikle JM, Jacobsen LM, Kahkoska AR, Kettunen JLT, Kreienkamp RJ, Lim LL, Mannisto JME, Massey R, Mclennan NM, Miller RG, Morieri ML, Most J, Naylor RN, Ozkan B, Patel KA, Pilla SJ, Prystupa K, Raghavan S, Rooney PMID 37794253
- Somolinos-Simon FJ, Garcia-Saez G, Tapia-Galisteo J, Corcoy R, Elena Hernando M. Cluster analysis of adult individuals with type 1 diabetes: Treatment pathways and complications over a five-year follow-up period. Diabetes Res Clin Pract. 2024 Sep;215:111803. doi: 10.1016/j.diabres.2024.111803. Epub 2024 Jul 30. PMID 39089589
- Kahkoska AR, Nguyen CT, Jiang X, Adair LA, Agarwal S, Aiello AE, Burger KS, Buse JB, Dabelea D, Dolan LM, Imperatore G, Lawrence JM, Marcovina S, Pihoker C, Reboussin BA, Sauder KA, Kosorok MR, Mayer-Davis EJ. Characterizing the weight-glycemia phenotypes of type 1 diabetes in youth and young adulthood. BMJ Open Diabetes Res Care. 2020 Jan;8(1):e000886. doi: 10.1136/bmjdrc-2019-000886. PMID 32049631
Identifiers
NCT: NCT07461805 · IIBSP-GIA-2024-115