A clinical prediction rule for the diagnosis of coronary artery disease: validation, updating, and extension

Aims The aim was to validate, update, and extend the Diamond-Forrester model for estimating the probability of obstructive coronary artery disease (CAD) in a contemporary cohort. Methods and results Prospectively collected data from 14 hospitals on patients with chest pain without a history of CAD and referred for conventional coronary angiography (CCA) were used. Primary outcome was obstructive CAD, defined as ≥50% stenosis in one or more vessels on CCA. The validity of the Diamond-Forrester model was assessed using calibration plots, calibration-in-the-large, and recalibration in logistic regression. The model was subsequently updated and extended by revising the predictive value of age, sex, and type of chest pain. Diagnostic performance was assessed by calculating the area under the receiver operating characteristic curve (c-statistic) and reclassification was determined. We included 2260 patients, of whom 1319 had obstructive CAD on CCA. Validation demonstrated an overestimation of the CAD probability, especially in women. The updated and extended models demonstrated a c-statistic of 0.79 (95% CI 0.77-0.81) and 0.82 (95% CI 0.80-0.84), respectively. Sixteen per cent of men and 64% of women were correctly reclassified. The predicted probability of obstructive CAD ranged from 10% for 50-year-old females with non-specific chest pain to 91% for 80-year-old males with typical chest pain. Predictions varied across hospitals due to differences in disease prevalence. Conclusion Our results suggest that the Diamond-Forrester model overestimates the probability of CAD especially in women. We updated the predictive effects of age, sex, type of chest pain, and hospital setting which improved model performance and we extended it to include patients of 70 years and older