Skip to content

Using artificial intelligence to personalize health risk prediction from medical images

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

Status
Recruiting
Phases
Phase 2
Study type
Observational
Source
ISRCTN
Registry ID
ISRCTN11743195
Enrollment
30
Registered
2026-04-23
Start date
2026-05-01
Completion date
Unknown
Last updated
2026-05-25

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Diabetes mellitus Nutritional, Metabolic, Endocrine

Interventions

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
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 b

Sponsors

Agencia Estatal de Investigación
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 65 Years

Inclusion criteria

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

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

Design outcomes

Secondary

MeasureTime frame
1. Anthropometric and clinical variables measured at baseline and 3 months as follows: 1.1. Weight (kg) measured using a calibrated digital scale 1.2. Height (cm) measured using a stadiometer 1.3. Body mass index (BMI, kg/m²) calculated from weight and height 1.4. Systolic and diastolic blood pressure (mmHg) measured using a validated automated sphygmomanometer 2. Serum biochemical parameters, including glucose, glycated hemoglobin (HbA1c), triglycerides, total cholesterol and HDL cholesterol (HDL-c), are measured using routine commercially available enzymatic assays (Roche Diagnostics, Basel, Switzerland), at baseline and at 3 months 3. Biomarkers of food intake (exploratory outcomes) are measured at baseline and 3 months as follows: 3.1. Hydroxytyrosol and tyrosol are measured in urine samples using liquid chromatography coupled with high-resolution mass spectrometry (LC-HRMS) 3.2. a-linolenic acid and carotenoids are measured in plasma samples using liquid chromatography coupled with high-resolution mass spectrometry (LC-HRMS) 4. Dietary variables are measured using the Mediterranean Diet Adherence Screener (MEDAS), a Food Frequency Questionnaire (FFQ), structured dietary records, and image-based dietary records collected via the LogMeal app, at baseline and 3 months 5. Usability of the LogMeal app measured using the LogMeal App Usability Questionnaire at baseline and 3 months 6. Sociodemographic variables: age (years) self-reported at baseline and 3 months

Countries

Spain

Contacts

Public ContactRosa Casas Rodríguez
RCASAS1@recerca.clinic.cat+34 (0)932275400

Outcome results

None listed

Source: ISRCTN (via WHO ICTRP) · Data processed: May 30, 2026