Using an outcomes-based approach to identify candidates for risk stratification after exercise treadmill testing

Abstract

Objective: To develop a hierarchical approach to cardiac risk stratification after treadmill testing.

Patients: Clinical and treadmill test data were used to identify a patient population that may be candidates for further risk stratification with stress tomographic myocardial perfusion imaging. A prospective series of 3, 620 medically treated patients (42% female, mean age 63 years) with a 2.5% mortality was identified (follow-up 2.5 +/- SD 1.5 years).

Measurements and main results: A Cox proportional hazards model was used to estimate a patient's likelihood of cardiac death. Kaplan-Meier survival curves were used to estimate time to cardiac death by nuclear test results. Annual rates of cardiac death were 0. 4% (n = 921), 1% (n = 2,498), and 1% (n = 201) for patients with low, intermediate, and high Duke treadmill scores (DTS). For patients with an intermediate DTS, multivariate estimators of cardiac death included the number of ischemic vascular territories (relative risk per defect 1.4, p =.01), the number of infarcted vascular territories (relative risk per defect 2.4, p =.00001), and the DTS (relative risk per unit 0.97, p =.00001), following adjustment for a patient's pretest risk of coronary disease. For patients with an intermediate DTS, the presence of no, one or two, and three vascular territories with defects was associated with annual rates of cardiac death of 0.5%, 1.4%, and 2.5%, respectively (p <.0001). Kaplan-Meier survival curves exhibited a statistically worsening survival for patients with defects by 1 year after treadmill exercise.

Conclusions: For symptomatic patients with an intermediate treadmill test score, the exercise myocardial perfusion scan may be used to stratify their risk of cardiac death over 3 years of follow-up. Patient management may be efficiently guided by further outcome assessment, with an exercise nuclear scan for patients whose treadmill test score is intermediate.

FIGURE 1

Annual cardiac death rates (95% confidence intervals) by the exercise treadmill test score and exercise single photon emission computed tomography myocardial perfusion imaging results.

FIGURE 2

Kaplan-Meier survival curves by the number of infarcted vascular territories. Overall 3-year survival was 98%, 93%, 85%, and 79% for patients with no, one, two, and three vascular territories with infarction, respectively (p < .0001).

FIGURE 3

Kaplan-Meier survival curves by the number of ischemic vascular territories. Overall 3-year survival was 98%, 95%, 92%, and 90% for patients with no, one, two, and three vascular territories with ischemia, respectively (p < .0001).

FIGURE 4

Hazard ratios (95% confidence intervals) for stage of exercise completed. Exercise duration was ≤3.0, 3.1–6.0, 6.1–9.0, 9.1–12.0, and ≥12.1 minutes for stages I, II, III, IV, and V, respectively. Increasing hazard ratios were noted for patients with lower exercise stages; 1.36 for stage I, 1.27 for stage II, and 1.17 for stage III.

FIGURE 5

Supplementary value of the Duke treadmill score (DTS) and single photon emission computed tomography imaging results in patients with an intermediate-risk score for estimation of cardiac death. By the improvement in model χ², both the DTS and the nuclear test information provided a statistically significant improvement in model χ². The percentage of information content was 34%, 16.2%, and 49.8% for clinical history, DTS, and for evidence of ischemia and infarction on the exercise nuclear scan, respectively. For the model C-index, there was a significant improvement in model classification ability when the DTS (0.86) and nuclear test information (0.91) were added to the model.