Machine learning profiles of cardiovascular risk in patients with diabetes mellitus: the Silesia Diabetes-Heart Project
Authors' conclusion
Using a ML approach in a prospective cohort of patients with DM, we identified important factors that predicted CV risk. If a patient was treated with ACEi or BB, is older and has/had a foot ulcer, this strongly predicts that he/she is at high risk of having overt CVD.
Study context
- Population
- Patients with diabetes mellitus (DM) in the Silesia Diabetes-Heart Project; mean age ± SD 52.15 ± 17.27 years, 54% female
- Participants
- 238 patients
- Outcome
- Prediction of overt cardiovascular disease (CVD) by machine learning (ML) on the basis of the five most discriminative predictors
Methodological detailssingle-centre, unsupervised clustering
- Single-centre
- Unsupervised clustering
Main finding
As reported in the abstract
ML prediction of overt CVD (five most discriminative predictors)
AUC
0.86
95% CI 0.80–0.91
Observational data: associations, not effects.
Further findings
Unsupervised clustering of cardiovascular (CV) risk groups
- Highest CV risk in the eldest patients treated largely with angiotensin converting enzyme inhibitor (ACEi) but not beta-blocker (BB) and with current foot ulceration, and in slightly younger patients treated extensively with both drugs, with a relatively small percentage of diabetic ulceration
Original publication
Machine learning profiles of cardiovascular risk in patients with diabetes mellitus: the Silesia Diabetes-Heart Project. Cardiovasc Diabetol. Published 24 August 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →