Method Boudet et al.(2019) (WMFB)
Boudet, S., Houzé de l’Aulnoit, A., Demailly, R., Peyrodie, L., Beuscart, R., Houzé de l’Aulnoit,D. - Fetal heart rate baseline computation with a weighted median filter Computers in Biology and Medicine pp. in Press,2019 View on researchgate - 50 days' free access official share link
This method has been developped by the authors of this website. It consists in computing a weighted median filter baseline (WMFB) and then in detecting accelerations and decelerations (A/D) accordingly.The filter weightings are based on the prior probability that the sampled FHR is in the baseline state or in an A/D state. This probability is computed by estimating the signal's stability at low frequencies and by progressively trimming the signal.
The official MATLAB source code is available at https://github.com/utsb-fmm/FHR or directly with the following download link (without data nor other functions).
USAGE: [baseline,accelerations,decelerations]=aamwmfb(FHR) INPUT: FHR : Fetal Heart Rate sampled at 4Hz already pre-processed (with no signal loss) OUTPUT: baseline : the baseline signal at 4Hz accelerations : Table with begining and end of each accelerations in s in each column decelerations : Table with begining and end of each decelerations in s in each column
Train dataset (include consensual expert analysis for comparison):
Test dataset (consensual expert analysis is not shown):