Feasibility study of a new method for low-complexity fetal movement detection from abdominal ECG recordings

M.J. Rooijakkers, C. Rabotti, H. De Lau, S. G. Oei, J.W.M. Bergmans, M. Mischi

Research output: Contribution to journalArticleAcademicpeer-review

3 Citations (Scopus)

Abstract

Fetal movement counting can provide valuable information on the fetal health, as a strong decrease in the number of movements can be seen as a precursor to fetal death. Typically, assessment of fetal health by fetal movement counting relies on the maternal perception of fetal activity. The percentage of detected movements is strongly subject dependent and with undivided attention of the mother varies between 37% and 88%. Various methods to assist in fetal movement detection exist based on a wide spectrum of measurement techniques. However, these are unsuitable for ambulatory or long-term observation. In this paper, a novel low-complexity method for fetal movement detection is presented based on amplitude and shape changes in the abdominally recorded fetal ECG. This method was compared to a state-of-the-art method from the literature. Using ultrasound-based movement annotations as ground truth, the presented method outperforms the state-of-the-art abdominal-ECG based method, with a sensitivity, specificity, and accuracy of 56%, 68%, and 63%, respectively. Additionally, a significant reduction in algorithm complexity is achieved, possibly enabling continuous ambulatory fetal movement detection and early detection of reduced fetal motility.

Original languageEnglish
Article number7147781
Pages (from-to)1361-1368
Number of pages8
JournalIEEE Journal of Biomedical and Health Informatics
Volume20
Issue number5
DOIs
Publication statusPublished - 1 Sep 2016

Keywords

  • Biomedical signal processing
  • continuous ambulatory monitoring
  • electrocardiography
  • fetal movement
  • ultrasound

Fingerprint Dive into the research topics of 'Feasibility study of a new method for low-complexity fetal movement detection from abdominal ECG recordings'. Together they form a unique fingerprint.

Cite this