Using artificial intelligence to personalize health risk prediction from medical images

Personalized risk and image-based stratification models using AI (EXPLORA-PRISM)

Registry ID
ISRCTN11743195
Source registry
ISRCTN
Status
Recruiting
Phase
PHASE2
Study type
OBSERVATIONAL
Sponsor
Agencia Estatal de Investigación
Enrollment
30
Start date
2026-05-01
Completion date
2027-11-30
Last update
2026-08-17

Conditions

Summary

Diabetes mellitus

Detailed description

The study includes two in-person visits, at baseline and at 3 months. Visit flow (both visits): 1. Nursing (fasting) 1.1. Blood draw for clinical analysis 1.2. Collection of blood and urine samples for dietary intake biomarkers 2. Consultation with the study nutritionist 2.1. Collection of anthropometric variables (weight, height, body mass index [BMI], blood pressure) 2.2. Collection of dietary information (MEDAS, FFQ, and dietary records) 2.3. Explanation of how the LogMeal application works and clarification of any questions 3. Telephone consultation at one and a half months: The nutritionist will call the participant to check how they are doing, identify any issues (if any), and remind them that for one week they should again take photographs of all foods consumed. They will also be asked to complete a 7-day dietary record. A follow-up FFQ will be conducted. This phone call helps maintain participant engagement with the study. The nutritionist will be responsible for collecting anthropometric and dietary variables. Both visits will take place at Córcega Street 180 (IDIBAPS). Use of LogMeal: The following instructions will be provided to each participant: Recording: take a photograph of the dish/food for each intake during the periods defined in the protocol. Minimum app data: study ID (pseudonymized); optionally, a label indicating time of intake. Capture rules: avoid including faces or identifiable elements; record only the food/dish. Incidents: if an intake cannot be recorded by photo, it will be documented through a manual entry according to the study procedure. Optionally, intake can also be recorded by scanning a product barcode.

Interventions

Inclusion criteria

1. Age ≥18 years 2. Diagnosis of type 1 or type 2 diabetes mellitus 3. Regular follow-up at Hospital Clínic de Barcelona 4. Ability to use a smartphone 5. Signing of the informed consent form

Exclusion criteria

1. Cognitive impairment that prevents the use of the app 2. Inability to understand the study information 3. Severe eating disorders

Locations

Related clinical trials

View on source registry