Type 2 & other diabetes

Integration of clinical and proteomic risk factors enhances prognostic modelling of incident vascular complications in type 2 diabetes

Cardiovasc DiabetolPublished Prognostic modelling study

Authors' conclusion

Integrating proteomics with clinical data enhances risk prediction of type 2 diabetes vascular complications, especially for macrovascular outcomes.

Study context

Population
European-ancestry UK Biobank participants with prevalent T2D but no prior vascular disease at baseline; 2,923 plasma proteins analysedEuropean ancestry
Participants
917 participants
Comparison
Proteomics-integrated models vs clinical-only models
Outcome
Time to first macrovascular or microvascular complication (ICD-10 codes)
Follow-up
Mean 10.41 years
Methodological detailscohort, UK Biobank, clinical-variables-prioritized LASSO Cox regression across 100 resamples, optimism-corrected C-index, time-dependent AUC and Brier score, exploratory cross-ancestry generalizability analyses
  • Cohort, UK Biobank
  • Clinical-variables-prioritized LASSO Cox regression across 100 resamples
  • Optimism-corrected C-index, time-dependent AUC and Brier score
  • Exploratory cross-ancestry generalizability analyses

Performance

As reported in the abstract

Prediction of T2D vascular complications (Harrell's C)

Harrell's C, macrovascular: proteomics-integrated vs clinical-only

0.72 vs. 0.60

Harrell's C, microvascular: proteomics-integrated vs clinical-only

0.67 vs. 0.62

Proteins selected for macrovascular outcomes (led by LRRC37A2, NT-proBNP, CHGA, APOD and STAB2)

37

Proteins selected for microvascular complications (led by IL15, FAM3C and TNFSF11), more moderate stability

9

Further findings

Stability of prognostic accuracy over time · 10 years

Stable prognostic accuracy over 10 years for macrovascular outcomes

Cross-ancestry generalizability

Predictive gains maintained in European genetic outliers (n=116) but diminished in African (n=54) and Asian (n=80) participants
  • Exploratory

Original publication

Integration of clinical and proteomic risk factors enhances prognostic modelling of incident vascular complications in type 2 diabetes. Cardiovasc Diabetol. Published 20 January 2026. doi:10.1186/s12933-026-03083-6

Composed by AI from the published abstract and checked against it. How Briefs are made →

Get them every week

New studies on this topic in My Week and in your Monday e-mail.

We e-mail you a sign-in link and a code. No password, no spam.