MODEL-BASED ESTIMATION OF CARDIOVASCULAR REPOLARIZATION FEATURES - ISCHEMIA DETECTION AND PTCA MONITORING

The ST-T segment of the surface ECG reflects cardiac repolarization, a nd is quite sensitive to a number of pathological conditions, particul arly ischaemia. ST-T changes generally affect the entire waveshape, an d are inadequately characterized by single features such as depression of the ST segment at one particular point. Metrics which represent ov erall waveshape should provide more sensitive indicators of ST-T wave abnormalities, particularly when they are subtle, intermittent of peri odic. This study discusses a Karhunen - Loeve transform (KLT) techniqu e for the analysis of the ST-T waveform. The KL technique was used to analyse the ST-T complexes in the ESC ST-T database. KL coefficients w ere plotted as a function of time, and were effective in detection of transient ischaemic episodes. Twenty per cat of the records showed bur sts of periodic ischaemia suggesting local vascular instability. A com parison between kl and ST depression series has shown the KL technique as more appropriate to the study of ST-T complex variations. Using th e kl series, an ischaemia detector has been developed based on a resam pled, filtered and differentiated KL series. This technique demonstrat es a sensitivity of 65% and a specificity of 54%. These low values can be due to shifts of the electrical axis which are detected as ischaem ic changes, real ischaemic episodes that were not annotated with the p rotocol used at the European ST-T database, or erroneous detections. A n increase in sensitivity can be obtained at the expense of a decrease in the positive predictive value and thus becomes a useful technique for previous scanning of the ECG record and subsequent review by the e xpert. The technique has also been used to monitor patients during a P TCA process, demonstrating that this technique allows us to monitor PT CA-induced ischaemia. A detailed analysis has shown that in some cases a repetitive oscillatory behaviour appears, lasting for a period of a round 20 s, and highly related to the oscillatory behaviour of the HR. In other cases, transient changes in KL series with salves behaviour associated with the injection of contrast are shown on the ST-T wavefo rm. We conclude that the KL-based analysts of the ST-T segment is a ro bust and sensitive technique, with considerable advantages over single feature measures in characterizing the subtle waveform changes which may be of importance in clinical risk detection.