Vectorcardiographic loop alignment for fetal movement detection using the expectation-maximization algorithm and support vector machines

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

4 Downloads (Pure)

Abstract

Reduced fetal movement is an important parameter to assess fetal distress. Currently, no suitable methods are available that can objectively assess fetal movement during pregnancy. Fetal vectorcardiographic (VCG) loop alignment could be such a method. In general, the goal of VCG loop alignment is to correct for motion-induced changes in the VCGs of (multiple) consecutive heartbeats. However, the parameters used for loop alignment also provide information to assess fetal movement. Unfortunately, current methods for VCG loop alignment are not robust against low-quality VCG signals. In this paper, a more robust method for VCG loop alignment is developed that includes a priori information on the loop alignment, yielding a maximum a posteriori loop alignment. Classification, based on movement parameters extracted from the alignment, is subsequently performed using support vector machines, resulting in correct classification of (absence of) fetal movement in about 75% of cases. After additional validation and optimization, this method can possibly be employed for continuous fetal movement monitoring.
Original languageEnglish
Title of host publicationProceedings of the 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 3-7 July 2013, Osaka, Japan
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages2915-2918
DOIs
Publication statusPublished - 2013

Fingerprint Dive into the research topics of 'Vectorcardiographic loop alignment for fetal movement detection using the expectation-maximization algorithm and support vector machines'. Together they form a unique fingerprint.

Cite this