COMPARTMENTAL MULTIVARIATE-ANALYSIS OF EXERCISE ECGS FOR ACCURATE DETECTION OF MYOCARDIAL-ISCHEMIA

An accurate computer-assisted diagnostic method for defection of myoca rdial ischaemia, called MUSTA, is developed. MUSTA is based on compart mental multivariate analysis of variables available in the exercise EC Gs; and is definitively implemented in Prolog. It is heuristically dev eloped by determining diagnostic criteria, which interrelate a modifie d ST/HR-slope, ST-segment value and shape, and maximum heart rate, so that concordance with the Tl-201 SPECT is maximised. in the learning g roup consisting of 47 patients, MUSTA provides a diagnostic accuracy o f 98%, the detection of ischaemia being in absolute concordance with T l-201 SPECT. MUSTA is evaluated in a similar but independent group of 60 patients. Then, accuracy is 90%, and sensitivity is 94%. The perfor mance characteristics are significantly better than those of the stand ard exercise ECG, whose:diagnostic accuracy in these groups is 77% and 70%, respectively. This study suggests that MUSTA is a significant im provement for computerised assessment of myocardial ischaemia