CodiceQDD 103
TitoloMultivariate Functional Clustering for the Morphological Analysis of ECG Curves
Autore/iIeva, F.;Paganoni,A.M.;Pigoli,D.;Vitelli,V.
LinkDownload full text
AbstractCardiovascular ischemic diseases are one of the main causes of death all over the world. In this kind of pathologies, it is fundamental to be well-timed in order to obtain good prognosis in reperfusive treatment. In particular, an automatic classification procedure based on statistical analyses of tele-transmitted ECG traces would be very helpful for an early diagnosis. This work presents an analysis on electrocardiographic (ECG) traces (both physiological and pathological ones) of patients whose 12-leads pre-hospital ECG has been sent by life supports to 118 Dispatch Center of Milan. The statistical analysis starts with a preprocessing step, in which functional data are reconstructed from noisy observations and biological variability is removed by a non linear registration procedure. Then, a multivariate functional k-means clustering is carried out on reconstructed and registered ECG curves and their first derivatives. Hence, a new semi-automatic diagnostic procedure, based on the sole ECG’s morphology, is proposed to classify ECG traces and the performance of this classification method is evaluated.