Key result
A 12-variable model identifies high-risk multivessel CAD with an AUC of ~0.73.
Why the study?
Coronary artery disease severity and prognosis are tied to treatment strategy choice, prompting the development of a predictive model for early identification of high-risk patients based on lesion severity.
Can a predictive model using routine clinical and laboratory variables accurately predict multivessel coronary artery disease in patients presenting with chest pain?
Observational (n=510)
No
Can a predictive model using routine clinical and laboratory variables accurately predict multivessel coronary artery disease in patients presenting with chest pain?
Answers are grounded in this paper and cite their sources.
A predictive model using 12 routine clinical and laboratory variables demonstrated acceptable discrimination for identifying multivessel coronary artery disease in patients presenting with chest pain.
Objective: The severity and prognosis of coronary artery disease are closely associated with treatment strategy choice. To achieve timely, accurate, early selection of a suitable treatment plan and assess patients’ prognosis, we developed an effective predictive model for early identification of high-risk patients according to lesion severity. Methods: Among the 510 patients with chest pain admitted to the Qinghai Red Cross Hospital between August 2018 and October 2019, 386 had coronary artery disease detected by coronary angiography. A total of 24 demographic characteristics and serum markers were analyzed in study participants. Least absolute shrinkage and selection operator regression was used to select variables, and multivariate logistic regression was used to build predictive models by using nominal plots. The discriminatory power of the models was evaluated with the area under the receiver operating characteristic curve (AUC). Predictive models were calibrated with calibration plots and the Hosmer–Lemeshow test. Their clinical validity was evaluated via decision curve analysis. Results: Data were randomly divided (7:3) into training (358 cases) and test (152 cases) sets. The predictive model included sex, age, smoking status, heart rate, systolic blood pressure, diastolic blood pressure, albumin, urea nitrogen, creatinine, uric acid, total cholesterol, and high-density lipoprotein cholesterol as predictors. The AUCs for the training and test sets were 0.793 and 0.732, respectively. The predictive model showed a good fit, and decision curve analysis indicated the clinical validity of the predictive model. Conclusions: We developed an effective risk predictive model with good clinical value for predicting multivessel disease. Smoking cessation, lowering creatinine, and increasing HDL cholesterol concentrations might decrease the risk of developing multivessel disease, thereby avoiding severe disease.
No takes yet. Share an insight, caveat, or question.
Li et al. (2024) conducted an observational in Multivessel Coronary Artery Lesions (n=510). Predictive model was evaluated on Early identification of high-risk patients for multivessel disease. A 12-variable predictive model effectively identified patients at high risk for multivessel coronary artery disease, achieving an AUC of 0.793 in the training set and 0.732 in the test set.
Synapse has enriched 10 related papers. Consider them for comparative context: