Predicting the risk of coronary artery calcium progression in the general population: insights from the MESA and CARDIA studies

Aim: Coronary artery calcium (CAC) progression is a strong predictor of cardiovascular disease. This study aims to develop and validate a practical tool for predicting individual CAC progression in the general population.

Materials and methods: Data were utilized from the Multi-Ethnic Study of Atherosclerosis (MESA) cohort, comprising 5486 participants (47.3% male, mean ± SD age: 61.9 ± 10.2 years), who were randomly assigned to either a training set or an internal validation set at a 7:3 ratio. Additionally, a separate cohort of 2447 participants (44.6% male, mean ± SD age: 40.4 ± 3.5 years) from the Coronary Artery Risk Development in Young Adults (CARDIA) study served as the external validation set. A nomogram was developed based on a Cox regression model incorporating 10 variables selected by the least absolute shrinkage and selection operator (LASSO) method to predict CAC progression.

Results: From the 61 features considered, 10 key variables were identified: age, male sex, smoking status, waist circumference, systolic blood pressure, fasting glucose, lipid abnormalities, and the use of antihypertensive, glucose-lowering, and lipid-lowering medications. The nomogram demonstrated good discrimination with a C-statistic of 0.682 (95% confidence interval [CI], 0.665-0.699) in the training set and 0.750 (95% CI, 0.729-0.771) in the external validation set. Decision curve analysis further confirmed the nomogram's clinical utility in predicting the risk of CAC progression.

Conclusion: Our nomogram offers a practical tool for individualized prediction of CAC progression potentially aiding in the primary prevention of cardiovascular disease in clinical practice. REGISTRATION URL: https://www.

Clinicaltrials: gov; Unique identifier: NCT00005130 (CARDIA), NCT00005487 (MESA).