Evaluation of parameters for fetal behavioural state classification

Abstract

Fetal behavioural states (fBS) describe periods of fetal wakefulness and sleep and are commonly defined by features such as body and eye movements and heart rate. Automatic state detection through algorithms relies on different parameters and thresholds derived from both the heart rate variability (HRV) and the actogram, which are highly dependent on the specific datasets and are prone to artefacts. Furthermore, the development of the fetal states is dynamic over the gestational period and the evaluation usually only separated into early and late gestation (before and after 32 weeks). In the current work, fBS detection was consistent between the classification algorithm and visual inspection in 87 fetal magnetocardiographic data segments between 27 and 39 weeks of gestational age. To identify how automated fBS detection could be improved, we first identified commonly used parameters for fBS classification in both the HRV and the actogram, and investigated their distribution across the different fBS. Then, we calculated a receiver operating characteristics (ROC) curve to determine the performance of each parameter in the fBS classification. Finally, we investigated the development of parameters over gestation through linear regression. As a result, the parameters derived from the HRV have a higher classification accuracy compared to those derived from the body movement as defined by the actogram. However, the overlapping distributions of several parameters across states limit a clear separation of states based on these parameters. The changes over gestation of the HRV parameters reflect the maturation of the fetal autonomic nervous system. Given the higher classification accuracy of the HRV in comparison to the actogram, we suggest to focus further research on the HRV. Furthermore, we propose to develop probabilistic fBS classification approaches to improve classification in less prototypical datasets.

Sex differences in prenatal development of neural complexity in the human brain

“…We utilized data that were collected from a previous study at the fMEG Center at the University of Tübingen. Recorded signals included both cortical activity (MEG) and cardiac activity (magnetocardiography or MCG), the latter of which was retained to measure HRV (one of the main parameters used to classify fetal behavioral and sleep states (40)) and, by proxy, arousal. The dataset consisted of 81 usable recordings of cortical and cardiac signals from 43 fetuses (gestational age range: 25 -40 weeks) which passed strict MEG quality control.…”

“…We hypothesized that cortical entropy would increase with maturation in fetuses as consciousness develops approaching birth, and also in newborns, as consciousness further develops in early infancy. Additionally, because fetal behavioral states are categorized in large part using heart rate variability (HRV) (40), we also hypothesized that cortical entropy would increase with HRV, as more active fetuses might plausibly be in a more conscious state compared with inactive or sleeping fetuses.…”

Fetal States Identification in Cardiotocographic Tracings Through Discrete Emissions Multivariate Hidden Markov Models

“…It has been observed that prolonged phases of inactivity are important indicators of pathological conditions, and alterations in the physiological alternation of fetal states have been associated with several conditions in pregnancy [6][7][8][9][10]. Moreover, CTG parameters have been shown to vary substantially according to the behavioral state, which suggests that they should be more correctly interpreted knowing the fetal state in which they were computed [11][12][13][14].…”

Classification of Fetal Behavioral States by using 1D-CNN based on Fetal Electrocardiography

“…Four FBSes have been identified starting from 32 weeks of gestation, namely quiet sleep (1F), active sleep (2F), quiet awake (3F) and active awake (4F). For these states to be defined, the body/eye movement patterns and heart rate patterns must remain stable for a mini-mum of 3 min [7].…”

“…It is known that Heart Rate Variability (HRV), analyzed using both time domain and spectral domain techniques, is a mirror of the Autonomic Nervous System (ANS) in adults, neonates, and fetuses [7]. In terms of fetal surveillance, it may be beneficial to consider this feature of Fetal Heart Rate Variability (FHRV).…”