28 January 2015 Effectiveness of morphological and spectral heartbeat characterization on arrhythmia clustering for Holter recordings
Author Affiliations +
Proceedings Volume 9287, 10th International Symposium on Medical Information Processing and Analysis; 92870A (2015) https://doi.org/10.1117/12.2070686
Event: Tenth International Symposium on Medical Information Processing and Analysis, 2014, Cartagena de Indias, Colombia
Abstract
Heartbeat characterization is an important issue in cardiac assistance diagnosis systems. In particular, wide sets of features are commonly used in long term electrocardiographic signals. Then, if such a feature space does not represent properly the arrhythmias to be grouped, classification or clustering process may fail. In this work a suitable feature set for different heartbeat types is studied, involving morphology, representation and time-frequency features. To determine what kind of features generate better clusters, feature selection procedure is used and assessed by means clustering validity measures. Then the feature subset is shown to produce fine clustering that yields into high sensitivity and specificity values for a broad range of heartbeat types.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Cristian Castro-Hoyos, Diego Hernán Peluffo-Ordóñez, Jose Luis Rodríguez-Sotelo, Germán Castellanos-Domínguez, "Effectiveness of morphological and spectral heartbeat characterization on arrhythmia clustering for Holter recordings", Proc. SPIE 9287, 10th International Symposium on Medical Information Processing and Analysis, 92870A (28 January 2015); doi: 10.1117/12.2070686; https://doi.org/10.1117/12.2070686
PROCEEDINGS
7 PAGES


SHARE
Back to Top