Henrik Haraldsson, Mattias Ohlsson and Lars Edenbrandt
Value of Exercise Data for the Interpretation of Myocardial Perfusion SPECT
Journal of Nuclear Cardiology 9 (2002) 169-173.

The purpose of this study was to investigate whether the automated interpretation of myocardial perfusion images using Bayesian neural networks was improved if exercise test data was used as input in addition to the perfusion images. A population of 229 patients who had undergone both a rest-stress myocardial perfusion scintigraphy in conjunction with an exercise test and coronary angiography, with no more than three months elapsing between the two examinations, were studied.

The networks were trained to detect coronary artery disease or myocardial ischemia using two different gold standards. The first was based on coronary angiography and the second was bases on a clinical evaluation of all data available, i.e. perfusion scintigrams coronary angiography, exercise test, resting ECG, patient history etc.

The performance of the neural networks was quantified as areas under the receiver operating characteristic curves.

The results showed that the performance of the networks did not improve when data from the exercise test was used as input in addition to the perfusion images.

Keywords: Diagnosis, Bayesian neural networks, Heart disease

LU TP 00-39