Background: Non-traditional image markers can improve the traditional cardiovascular
risk estimation, is untested in Kerala based participants.
Objective: To identify the relationship between the ‘Modified CV risk’ categories with traditional
and non-traditional image-based risk markers. The correlation and improvement in reclassification,
achieved by pooling atherosclerotic non-traditional markers with Intermediate (≥7.5% and <20%)
and High (≥20%) 10-year participants is evaluated.
Methods: The cross-sectional study with 594 participants has the ultrasound measurements recorded
from the medical archives of clinical locations at Ernakulum district, Kerala. With carotid
Intima-Media Thickness (cIMT) measurement, the Plaque (cP) complexity was computed using
selected plaque characteristics to compute the carotid Total Plaque Risk Score (cTPRS) for superior
risk tagging. Statistical analysis was done using RStudio, the classification accuracy was verified
using the decision tree algorithm.
Results: The mean age of the participants was (58.14±10.05) years. The mean cIMT was
(0.956±0.302) mm, with 65.6% plaque incidence. With 94.90% variability around its mean, the
Multinomial Logistic Regression model identifies cIMT and cTPRS, age, diabetics, Familial Hypercholesterolemia
(FH), Hypertension treatment, the presence of Rheumatoid Arthritis (RA),
Chronic Kidney Disease (CKD) as significant (p<0.05). cIMT and cP were found significant for
‘Intermediate High’, ‘High’ and ‘Very High’ ‘Modified CV risk’ categories. However, age, diabetes,
gender and use of hypertension treatment are significant for the ‘Intermediate’ ‘Modified CV
risk’ category. The overall performance of the MLR model was 80.5%. The classification accuracy
verified using the decision tree algorithm has 78.7% accuracy.
Conclusion: The use of atherosclerotic markers shows a significant correlation suitable for a nextlevel
reclassification of the traditional CV risk.