T. Baas, K. Gräfe, A. Khawaja, and O. Dössel. Investigation of parameters highlighting drug induced small changes of the T-wave's morphology for drug safety studies. In Conf Proc IEEE Eng Med Biol Soc, pp. 3796-3799, 2011
In guideline E14, the American Food and Drug Administration (FDA) requests for clinical studies to investigate the prolongation of the heart rate corrected QT-interval (QTc) of the ECG. As drug induced QT-prolongation can be caused by changes in the repolarisation of the ventricles, it is so far a thorough ECG biomarker of risk for ventricular tachyarrhythmias and Torsade de Pointes (TdP). Ventricular repolarisation changes not only change QT but also influence the morphology of the T-wave. In a (400 mg single dose) Moxifloxacin positive control study both, QTc and several descriptors describing the T-wave morphology have been measured. Moxifloxacin is changing two shape dependent descriptors significantly (P<0.05) about 3 to 4 hours after a 400 mg oral single dose of Moxifloxacin.
G. Lenis, T. Baas, and O. Dössel. Automatic detection and classification of ectopic beats in the ECG using a Support Vector Machine. In 45. Jahrestagung der DGBMT im VDE. Proceedings BMT 2011, 2011
Ectopic beats are a common cause of cardiac arrhythmia. In order to automatically detect and classify ectopic beats in the ECG a new method based on a Support Vector Machine (SVM) was developed. The numerical patterns needed for this classification task were obtained from rhythmical and morphological characteristics of the QRS complexes. The SVM was trained and tested using the MIT-BIH Arrythmia Database and the MIT-BIH Supraventricular Arrythmia Database. A sensitivity of 92.46% was achieved.
T. Oesterlein, T. Baas, H. Malberg, and O. Dössel. Multivariate AR model parameter estimation on time series extracted from the ECG of myocarditis patients. In Biomedizinische Technik / Biomedical Engineering (Proceedings BMT2011), vol. 56(1) , 2011
Biosignal analysis is aiming at analyzing physiological parameters for improved diagnosis and treatment. In this paper, the use of multivariate autoregressive models is proposed as a new method to analyze ECG data and to gain further information about the functionality of the heart. This application is demonstrated on myocarditis patients, where cure and diagnosis was observed. Timeseries of RR and QT intervals are analyzed by an autoregressive (AR) model, whose parameters are found dependent on the condition of the inflammation. The heart muscle inflammation is known as potentially lethal and an invasive biopsy still is the gold standard. Due to the variety of its symptoms, detailled non-invasive diagnosis is rather difficult and thus a highly challenging topic.