Abstract
In this paper, we propose an application of non-parametric Bayesian (NPB) models for classification of fetal heart rate (FHR) recordings. More specifically, we propose models that are used to differentiate between FHR recordings that are from fetuses with or without adverse outcomes. In our work, we rely on models based on hierarchical Dirichlet processes (HDP) and the Chinese restaurant process with finite capacity (CRFC). Two mixture models were inferred from real recordings, one that represents healthy and another, non-healthy fetuses. The models were then used to classify new recordings and provide the probability of the fetus being healthy. First, we compared the classification performance of the HDP models with that of support vector machines on real data and concluded that the HDP models achieved better performance. Then we demonstrated the use of mixture models based on CRFC for dynamic classification of the performance of (FHR) recordings in a real-time setting.
Highlights
Fetal heart rate (FHR), along with other physiological signals, is routinely monitored before and during labor to assess fetal health
We first provide the classification performance of HDP Gaussian mixture models (HDPGMs) and the comparison with that of support vector machine (SVM), which achieved the best performance in studies [9, 12]
We show the real-time classification of FHR tracings by models based on Chinese restaurant process with finite capacity (CRFC)
Summary
Fetal heart rate (FHR), along with other physiological signals, is routinely monitored before and during labor to assess fetal health. The HDP mixture model is a non-parametric Bayesian approach to data processing It aims at modeling grouped data jointly, where each group (segment features of an FHR recording) is associated with a mixture model, and all the mixing components are shared across the groups (different FHR recordings share features). The prior probability of tj,i taking an occupied table is proportional to nÀ j;i j;t;Á according to Eq (3), where, as before, the notation −j,i means the corresponding variable is removed from a set or a count. The classifier operated in a feature space with reduced dimension and obtained via principle component analysis (PCA), as explained They include the mean and the standard deviation of the segment sji. We use the short-term variability (STV) and long-term variability (LTV), which are defined in [8] as vSTV 1⁄4 K jsðk þ 1Þ À sðkÞj; ð14Þ
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
