Document Detail


Fetal beat detection in abdominal ECG recordings: global and time adaptive approaches.
MedLine Citation:
PMID:  25070020     Owner:  NLM     Status:  In-Data-Review    
Abstract/OtherAbstract:
We present a method for location of fetal QRS in maternal abdominal ECG recordings. This method's initial, global approach was proposed in the context of the 2013 PhysioNet/Computing in Cardiology Challenge where it was tested on the 447 four channel one-minute recordings.The first step is filtering to eliminate baseline wander and high frequency noise. Upon detection, maternal QRS is removed on each channel using a filter applied to the other three channels. Next we locate fetal QRS on each channel and select the channel with the best set of detections. The method was awarded the third-best score in the Challenge event 1 with 278.755 (beats/minute) and the fourth-best score on event 2 with 28.201 ms.The 5 min long recordings of the Abdominal and Direct Fetal ECG Database were used to further test the method. This database contains five recordings obtained from women in labor. Results in these longer recordings were not satisfactory. This appears to be particularly the case in recordings with a more clearly non-stationary nature. In a new approach to our method, some changes are introduced. Two features are updated over time: the filter used to eliminate maternal QRS and the channel used to detect fetal beats. These changes significantly improved the QRS detection performance on longer recordings, but the scores on the 1 minute Challenge recordings were degraded.
Authors:
Rui Rodrigues
Publication Detail:
Type:  Journal Article     Date:  2014-07-29
Journal Detail:
Title:  Physiological measurement     Volume:  35     ISSN:  1361-6579     ISO Abbreviation:  Physiol Meas     Publication Date:  2014 Aug 
Date Detail:
Created Date:  2014-07-29     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9306921     Medline TA:  Physiol Meas     Country:  England    
Other Details:
Languages:  eng     Pagination:  1699-711     Citation Subset:  IM    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Modified Hemostatic Technique Using Microfibrillar Collagen Hemostat in Endoscopic Endonasal Transsp...
Next Document:  Automatic modeling of pectus excavatum corrective prosthesis using artificial neural networks.