Predicting who with diabetes may develop a foot ulcer
Prediction Model for the Risk of Developing Foot Ulcers in Diabetes
This project will try an AI-based model to see if it can predict which adults with diabetes are likely to develop a foot ulcer using regional health records and registry data.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 100000 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Sahlgrenska University Hospital Academic / other |
| Locations | 1 site (Jonsered) |
| Trial ID | NCT07307183 on ClinicalTrials.gov |
What this trial studies
This is a retrospective, register-based project using electronic health records from Närhälsan in Region Västra Götaland linked to Statistics Sweden data to build predictive models. Machine learning models will be trained on diagnostic codes, procedure codes, visit data, prescriptions, ECG parameters, clinical notes, and socioeconomic variables to identify risk factors for diabetic foot ulcers. Cross-validation will be used to tune models, and model performance will be compared with traditional statistical approaches in a later phase. The cohort includes adults with diabetes diagnoses or diabetes medication prescriptions recorded from 2014 through 30 June 2025, and missing or incomplete key data will be excluded.
Who should consider this trial
Good fit: Adults (18+) with a recorded diabetes diagnosis (ICD-10 E10–E14) or at least one diabetes medication prescription in the Närhälsan/Västra Götaland records between 2014 and 30 June 2025 are ideal candidates.
Not a fit: People under 18, those without diabetes diagnoses or diabetes medication records, patients with important missing data, and individuals living outside the Västra Götaland health record coverage are unlikely to benefit from this project.
Why it matters
Potential benefit: If successful, the model could help clinicians find high-risk patients earlier so preventive care can reduce ulcers, infections, amputations, and related costs.
How similar studies have performed: Other machine-learning efforts have shown promising results predicting diabetic complications, but combining regional EHR, free-text clinical notes, and linked socioeconomic registry data is relatively novel.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Adult patients aged 18 years or older at the time of inclusion * Patients with a diagnosis of diabetes mellitus according to ICD-10 codes E10-E14, and/or * Patients who have been prescribed at least one diabetes-related medication after the age of 18 * Patients with relevant diagnoses and/or prescriptions recorded in the study data sources between 1 January 2014 and 30 June 2025 Exclusion Criteria: * Patients younger than 18 years of age at the time of diabetes diagnosis or prescription * Patients with no recorded diagnosis of diabetes (ICD-10 E10-E14) and no prescription of diabetes medication after the age of 18 * Patients with incomplete or missing key data required for model development or validation (e.g. missing outcome or essential covariates)
Where this trial is running
Jonsered
- Region Västra Götaland — Jonsered, Sweden (Recruiting)
Study contacts
- Principal investigator: Ulla Hellstrand Tang, Associate Professor — The Department of Prosthetics & Orthotics at the Department for Biomedical Engineering and Medical Physics at Sahlgrenska University Hospital, Gothenburg, Sweden
- Study coordinator: Ulla Hellstrand Tang, Associate Professor
- Email: ulla.tang@vgregion.se
- Phone: +46706397913
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.