IDM/fMEG Center of the Helmholtz Center Munich at the University of Tübingen, University of Tübingen, German Center for Diabetes Research (DZD), Otfried-Müller-Str. 47, 72076, Tübingen, Germany.
Graduate Training Centre of Neuroscience, International Max Planck Research School, University of Tübingen, Tübingen, Germany.
Sci Rep. 2022 Mar 1;12(1):3410. doi: 10.1038/s41598-022-07476-x.
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.
胎儿行为状态（fetal behavioural states，fBS）描述了胎儿觉醒和睡眠的时期，通常通过身体和眼部运动以及心率等特征来定义。通过算法进行自动状态检测依赖于源自心率变异性（heart rate variability，HRV）和活动图的不同参数和阈值，这些参数和阈值高度依赖于特定数据集，并且容易受到伪影的影响。此外，胎儿状态的发育在整个妊娠期间是动态的，评估通常仅分为早期和晚期妊娠（32 周之前和之后）。在当前的工作中，在 27 至 39 孕周的 87 个胎儿磁心电图数据段中，分类算法和视觉检查之间的 fBS 检测结果一致。为了确定如何改进自动 fBS 检测，我们首先确定了 HRV 和活动图中用于 fBS 分类的常用参数，并研究了它们在不同 fBS 中的分布。然后，我们计算了接收器操作特征（receiver operating characteristics，ROC）曲线，以确定每个参数在 fBS 分类中的性能。最后，我们通过线性回归研究了参数在妊娠期间的发展。结果表明，与源自活动图中身体运动定义的参数相比，源自 HRV 的参数具有更高的分类准确性。然而，几个参数在状态之间的重叠分布限制了基于这些参数对状态进行清晰区分。HRV 参数随妊娠的变化反映了胎儿自主神经系统的成熟。鉴于 HRV 与活动图相比具有更高的分类准确性，我们建议进一步研究 HRV。此外，我们建议开发概率性 fBS 分类方法，以提高在非典型数据集上的分类效果。
