Does fuzzy cluster analysis of positive stress tests provide comparable sensitivity to stress echocardiography and nuclear imaging for detecting high-grade coronary disease?
Fuzzy cluster analysis of standard treadmill stress tests can identify high-grade coronary disease with sensitivity comparable to more expensive imaging modalities.
Fuzzy cluster analysis (FCA) was used to classify 166 outpatient positive treadmill stress tests as mildly, moderately, or severely abnormal. The method combines ST-segment change with five other stress test variables, and then computes a similarity measure to determine how closely each patient's stress test resembles a prototypical mildly, moderately, or severely abnormal stress test. All patients had coronary angiography within 1 month of their stress tests. For the 45 patients with triple vessel disease (TVD), FCA classified 34 of these stress tests as severely abnormal (sensitivity = 75%). For the 22 patients with left main disease (LM), FCA classified 19 stress tests as severely abnormal (sensitivity = 86%). For the combined group with high-grade disease (TVD + LM), the sensitivity was 79%. A literature review shows that for stress echocardiography, multiple exercise-induced wall motion abnormalities have a sensitivity in the 70-80% range for patients with high-grade disease. For nuclear stress testing, the high-risk pattern of multiple reversible defects, with or without increased lung uptake, has a sensitivity in the range of 70-80% for patients with high-grade disease. Thus classification of a positive stress test as severely abnormal by FCA has a sensitivity comparable to high-risk patterns on stress echocardiography and nuclear stress testing in patients with TVD or LM.
Robert Peters (Fri,) studied this question.