|Title:||Multivariate functional clustering for the analysis of ECG curves morphology|
|Date:||Friday 14th January 2011|
|Author(s) :||Ieva, F.; Paganoni, A.m.; Pigoli, D.; Vitelli, V.|
|Abstract:|| Cardiovascular 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 is a pilot analysis on electrocardiographic ECG) traces (both normal 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 consists of preliminary steps like reconstructing signals, wavelets denoising and removing the biological variability in the signals
through data registration.
Then, a multivariate functional k-means clustering of reconstructed and registered ECGs is performed, and performances of classification
method are validated. So a semi-automatic diagnostic procedure, based on the sole ECG's morphology, is proposed to classify patients and predict pathologies.|
This report, or a modified version of it, has been also submitted to, or published on
Journal of the Royal Statistical Society - Series C, Vol. 62, No. 3, pp. 401-418 (doi: 10.1111/j.1467-9876.2012.01062.x)