The optimal reference population for cardiac normality in myocardial SPET in the detection of coronary artery stenoses: patients with normal coronaryangiography or subjects with low likelihood of coronary artery disease?

Both subjects with a low likelihood for coronary artery disease (CAD) and p atients with normal findings on coronary angiography have been used as refe rence populations in non-invasive stress testing, including myocardial perf usion scintigraphy. Both of these criteria of normality - low likelihood of CAD and normal coronary angiography - have been criticised, and consensus on this issue is lacking. The aim of this study was to compare two differen t reference populations by testing the performance of artificial neural net works designed to interpret myocardial scintigrams. The networks were train ed on myocardial perfusion scintigrams from 87 patients with angiographical ly documented CAD and on studies from one of two different reference groups : 48 patients with no signs of CAD based on angiography or 128 healthy volu nteers with a likelihood for CAD <5%. The performance of the two different networks was then tested using scintigrams from a separate test group of 68 patients. Coronary angiography was used as the gold standard in this group . The network trained on patients with no signs of CAD based on angiography showed an area under the receiver operating characteristic (ROC) curve of 93%. The ROC area for the network trained on healthy volunteers was 72%, an d this difference was statistically significant (P=0.03). The results of th is study using artificial neural networks suggest that normal angiography s hould be preferred as the reference standard in myocardial scintigraphy whe n a patient is examined for CAD prior to possible angiography. Whether the same is true for other indications, e.g. in prognostic evaluation, is unkno wn.