DETECTION OF RESTENOSIS AFTER SUCCESSFUL CORONARY ANGIOPLASTY - IMPROVED CLINICAL DECISION-MAKING WITH USE OF A LOGISTIC MODEL COMBINING PROCEDURAL AND FOLLOW-UP VARIABLES

A prospective study of 111 patients who underwent repeat coronary angiography and exercise thallium-201 scintigraphy 6 ± 2 months after complete revascularization by percutaneous transluminal coronary angioplasty was performed to assess whether clinical, procedure-related and postangioplasty exercise variables yield independent information for the prediction of angiographic restenosis after angioplasty. Complete revascularization was defined as successful angioplasty of one or more vessels that resulted in no residual coronary lesion with >50% diameter stenosis. Restenosis was defined as a residual stenosis at the time of repeat angiography of >50% of luminal diameter. Restenosis occurred in 40% of the patients. The 111 patients were randomly subdivided into a learning group (n = 84) and a testing group (n = 27). A logistic discriminant analysis was performed in the learning group and the logistic model was used to estimate a logistic probability of restenosis. This probability of restenosis was validated in the testing group. In the learning group of 84 patients univariate analysis of 39 factors revealed 8 factors related to restenosis: recurrence of angina (p < 0.0001), postangioplasty abnormal finding on exercise thallium-201 scintigram (p < 0.0001), exercise thallium-201 scintigram score (p < 0.0001), difference between exercise and rest ST segment depression (p < 0.001), postangioplasty exercise ST segment depression (p < 0.001), absolute postangioplasty stenosis diameter (p < 0.003), postangioplasty exercise work load (p < 0.03) and postangioplasty exercise heart rate (p < 0.05). Multivariate analysis revealed four factors independently related to increased risk of restenosis in the following order of importance: recurrence of angina (p < 0.0001), abnormal finding on exercise thallium-201 scintigram (p < 0.001), absolute postangioplasty stenosis diameter (p < 0.002) and exercise ST segment depression (p < 0.01). With use of a logistic model these predictors of restenosis were weighed into a restenosis probability score (high, intermediate and low risk) that was validated in the testing group. The predictive value for restenosis in the high risk group (probability >80%) was 100% and the predictive value for no restenosis in the low risk group (probability <20%) was 94%. It is concluded that a diagnostic strategy with probability analysis that includes simple procedure-related and exercise testing variables during follow-up provides a useful clinical tool for detecting patients at high risk for restenosis who may require repeat coronary angiography and angioplasty. This risk stratification proved superior to the usual clinical practice of performing repeat catheterization only in patients with recurrent angina or ST changes during exercise testing, or both. © 1990.