Citi, Luca and Olariu, Claudia and Barbieri, Riccardo (2015) A LightWAVE client for semi-automated annotation of Heart Beats from ECG Time Series. In: 2015 Computing in Cardiology Conference (CinC), 2015-09-06 - 2015-09-09.
Citi, Luca and Olariu, Claudia and Barbieri, Riccardo (2015) A LightWAVE client for semi-automated annotation of Heart Beats from ECG Time Series. In: 2015 Computing in Cardiology Conference (CinC), 2015-09-06 - 2015-09-09.
Citi, Luca and Olariu, Claudia and Barbieri, Riccardo (2015) A LightWAVE client for semi-automated annotation of Heart Beats from ECG Time Series. In: 2015 Computing in Cardiology Conference (CinC), 2015-09-06 - 2015-09-09.
Abstract
LightWAVE is an open-source web-based software for viewing ECGs and other physiologic waveforms and associated annotations (such as heart-beat markers). At present, most users run the raw ECG through an automated QRS detector and later use LightWAVE to review and correct the detected heart beats. Although this 2-stage procedure may work well with clean signals, it is inefficient and time consuming when the recordings are contaminated by noise, artefacts or recurring ectopic events. To overcome this limitation, we customized the LightWAVE client to allow automated and semi-automated annotation of heart beats from ECG time series. In semi-automatic mode, the algorithm automatically identifies most QRS complexes and stops - asking for manual intervention - whenever the confidence of a detection falls below a given threshold. Additionally, the software now shows the series of inter-beat intervals, which is an invaluable tool to easily spot R-wave misdetections and genuine arrhythmias. The new client introduces further additional features compared to the standard version, for example the possibility of importing raw signals from local CSV files and of exporting the current plot in SVG format. Overall, our customized client extends the functionality of LightWAVE and brings it closer to one of its design goals, i.e. to provide a comfortable and efficient method of annotating physiologic data.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Additional Information: | Published proceedings: Computing in Cardiology |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science R Medicine > R Medicine (General) |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Computer Science and Electronic Engineering, School of |
SWORD Depositor: | Unnamed user with email elements@essex.ac.uk |
Depositing User: | Unnamed user with email elements@essex.ac.uk |
Date Deposited: | 12 Dec 2016 16:42 |
Last Modified: | 30 Oct 2024 19:57 |
URI: | http://repository.essex.ac.uk/id/eprint/17439 |