Related Experiment Videos
A simple model to predict coronary disease in patients undergoing operation for mitral regurgitation
Eric Lim1, Ziad A Ali, Clifford W Barlow
1Department of Cardiothoracic Surgery, Papworth Hospital, Cambridge, United Kingdom. ericlim2@hotmail.com
Insights
A simple additive model accurately predicts coronary artery disease in patients with mitral valve disease, offering a bedside-applicable tool. This method improves upon traditional risk factor identification for better patient outcomes.
Area of Science:
- Cardiology
- Cardiac Surgery
- Medical Informatics
Background:
- A significant portion of patients with mitral valve disease also have coexistent coronary artery disease.
- Accurate identification of coronary artery disease is crucial for guiding treatment decisions in these patients.
Purpose of the Study:
- To evaluate a candidate selection strategy using risk factor identification and logistic regression.
- To develop a simple additive model for predicting coexistent coronary artery disease in patients undergoing mitral valve repair.
Main Methods:
- Analysis of a consecutive series of patients who underwent mitral repair between 1987 and 1999.
- Calculation of sensitivities and specificities for individual risk factors.
- Development of a predictive score using univariate and stepwise multivariate logistic regression, followed by derivation of a logistic regression-derived additive model.
- Comparison of model discrimination and precision using receiver operating characteristic curves and the Hosmer-Lemeshow statistic.
Main Results:
- The American Heart Association and American College of Cardiology risk factor identification criteria achieved 100% sensitivity but only 1% specificity.
- The developed logistic regression model demonstrated strong predictive ability (Area Under Curve [AUC] = 0.91, Hosmer-Lemeshow p = 0.9).
- The five-item additive model showed comparable discrimination (AUC = 0.91, Hosmer-Lemeshow p = 0.80), outperforming the Cleveland Clinic model (AUC = 0.79).
Conclusions:
- While simple risk factor identification is sensitive, its low specificity limits its clinical utility.
- Logistic regression modeling provides accurate risk prediction but can be complex for bedside application.
- The logistic regression-derived additive model offers a balance of simplicity and accuracy for predicting coexistent coronary artery disease in this patient population.
Background:
Coexistent coronary disease can be identified in a third of patients with mitral valve disease. This study aims to evaluate candidate selection strategy using risk factor identification and logistic regression and to develop an additive model for the prediction of coexistent coronary disease.
Methods:
The sample is a consecutive series of patients who had mitral repair from 1987 to 1999. Sensitivities and specificities were calculated for each risk factor. Variables for prediction of coronary disease were entered into a univariate analysis, and predictors were entered into a forward and backward stepwise multivariate logistic regression model to form a predictive score. An additive model was derived from transformation of the logistic model. Receiver operating characteristic curves were used to compare discrimination and precision quantified by the Hosmer-Lemeshow statistic.
Results:
The American Heart Association and American College of Cardiology risk factor identification selection criteria for the 359 patients who had screening coronary angiography yielded 100% sensitivity and 1% specificity. Risk prediction with our logistic model produced a receiver operating characteristic curve area of 0.91 and Hosmer-Lemeshow score of 3.4 (p = 0.9). Similar discriminating ability for our patients was achieved by the Cleveland Clinic logistic model (receiver operator characteristic curve area of 0.79; Hosmer-Lemeshow score of 12; p = 0.1). Our five-item additive model produced receiver operating characteristic curve area of 0.91 and Hosmer-Lemeshow score of 3.81 (p = 0.80).
Conclusions:
Simple risk factor identification has excellent sensitivity but is limited by specificity. Logistic regression modeling is an accurate risk prediction method but is difficult to apply at the bedside. Simplicity and accuracy may be achieved by the logistic regression-derived simple additive model.