Improved recognition of sustained ventricular tachycardia from SAECG by support vector machine.
ANADOLU KARDIYOLOJI DERGISI : AKD = THE ANATOLIAN JOURNAL OF CARDIOLOGY 2007;
7 Suppl 1:112-5. [PMID:
17584700]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 05/15/2023]
Abstract
OBJECTIVE
We present the improved method of recognition of sustained ventricular tachycardia (SVT) based on new filtering technique (FIR), extended signal-averaged electrocardiography (SAECG) description by 9 parameters and the application of support vector machine (SVM) classifier.
METHODS
The dataset consisted of 376 patients (100 patients with sustained ventricular tachycardia after myocardial infarction (MI) labelled as class SVT+, 176 patients without sustained ventricular tachycardia after MI and 77 healthy persons, 50% of data were left for validation. The analysis of SAECG was performed by 2 types of filtration: low pass four-pole IIR Butterworth filter and FIR filter with Kaiser window. We calculated 3 commonly used SAECG parameters: hfQRS (ms), RMS40 (microV), LAS<40 microV(ms) and 6 new parameters: LAS<25 microV(ms) - duration of the low amplitude <25 microV signals at the end of QRS complex; RMS QRS(microV) - root mean square voltage of the filtered QRS complex; pRMS(microV) - root mean square voltage of the first 40 ms of filtered QRS complex; pLAS(ms) - duration of the low amplitude <40 microV signals in front of QRS complex; RMS t1(microV) - root mean square voltage of the last 10 ms the filtered QRS complex; RMS t2(microV) - root mean square voltage of the last 20 ms the filtered QRS complex. For the recognition of SVT+ class patients we used the SVM with the Gaussian kernel.
RESULTS
The results confirmed good generalization of obtained models. The recognition score (calculated as correct classification/total number of patients) of SVT+patients on data set containing 3 standard parameters (Butterworth filter) is 92.55%. The same score was obtained for data set containing 9 parameters (Butterworth filter). The best score (95.21%) was obtained for data set based on 9 parameters and FIR filter.
CONCLUSION
Our approach improved risk stratification up to 95% based on SAECG due to the application of FIR filter, 6 new parameters and efficient statistical classifier, the support vector machine.
Collapse