UNVEILING EARLY CARDIOVASCULAR DISEASE PREDICTION IN TYPE 2 DIABETES

POTENTIAL ROLE OF CARDIOMETABOLIC BIOMARKERS

Abstract

INTRODUCTION/BACKGROUND
Type 2 diabetes individuals are at higher risk of developing cardiovascular disease compared to the general population. Cardiovascular disease remains the leading cause of death in type 2 diabetes despite vigilant monitoring. Early detection of type 2 diabetes patients predisposed to cardiovascular complications is important to reduce the disease burden.

METHODOLOGY
This study aimed to investigate the potential role of cardiometabolic biomarkers in cardiovascular risk prediction among type 2 diabetes patients. A case-control study consisting of type 2 diabetes with cardiovascular disease outcome, type 2 diabetes without cardiovascular complications and healthy control group was conducted in 221 participants. We employed a machine learning algorithm to develop a cardiovascular risk prediction model.

RESULT
A combination of sociodemographic, anthropometry and routine biochemical data was assessed using ensemble classifier as the base model for predicting cardiovascular risk (84.8% accuracy, 76.5% positive predictive value in high-risk). The predictive ability was improved when serum ferritin, vitamin D and NT-proBNP (89.4% accuracy, 83.3% positive predictive value in high-risk) were added to the model.

CONCLUSION
As cardiometabolic biomarkers may potentially improve cardiovascular prediction, further analysis can be performed to validate their clinical utility in diverse type 2 diabetes individuals.