A 7-variable nomogram model predicted coronary heart disease risk in patients with hyperlipidemia with an AUC of 0.881 (95% CI 0.858-0.905) in the modeling cohort and 0.75 in the validation cohort.
Cohort (n=859)
Yes
Can a nomogram based on carotid ultrasound and clinical factors accurately predict the risk of coronary heart disease in patients with hyperlipidemia?
A novel nomogram incorporating clinical factors and carotid ultrasound plaque score showed good predictive accuracy for coronary heart disease risk in patients with hyperlipidemia.
Effect estimate: AUC 0.881 (95% CI 0.858-0.905)
BACKGROUND: Hyperlipidemia is one of the independent risk factors for the onset of coronary heart disease (CHD), and our aim is to construct a coronary risk prediction model for patients with hyperlipidemia based on carotid ultrasound in combination with other risk factors. METHODS: The nomogram risk prediction model is based on a retrospective study on 820 patients with hyperlipidemia. The predictive accuracy and discriminative ability of the nomogram were determined by receiver operating characteristic (ROC) curves and calibration curves. The results were validated using bootstrap resampling and a prospective study on 39 patients with hyperlipidemia accepted at consenting institutions from 2021 to 2022. RESULT: In the modeling cohort, 820 patients were included. A total of 33 variables were included in univariate logistic regression. On multivariate analysis of the modeling cohort, independent factors for survival were sex, age, hypertension, plaque score, LVEF, PLT, and HbAlc, which were all selected into the nomogram. The calibration curve for probability of survival showed good agreement between prediction by nomogram and actual observation. The area under the curve (AUC) of the nomogram model was 0.881 (95% CI 0.858∼0.905), with a sensitivity of 79% and a specificity of 81.7%. In the validation cohort, the AUC was 0.75, 95% CI (0.602∼0.906). The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy of this model were 54.16%, 80%, 81.25%, 52.17% and 64.1%. This model showed a good fitting and calibration and positive net benefits in decision curve analysis. CONCLUSION: A nomogram model for CHD risk in patients with hyperlipidemia was developed and validated using 7 predictors, which may have potential application value in clinical risk assessment, decision-making, and individualized treatment associated with CHD.
Zeng et al. (Sun,) conducted a cohort in Hyperlipidemia (n=859). Nomogram risk prediction model was evaluated on Coronary heart disease risk prediction (AUC) (AUC 0.881, 95% CI 0.858-0.905). A 7-variable nomogram model predicted coronary heart disease risk in patients with hyperlipidemia with an AUC of 0.881 (95% CI 0.858-0.905) in the modeling cohort and 0.75 in the validation cohort.