During the process of childbirth, fetal distress caused by hypoxia can lead to various abnormalities. Cardiotocography (CTG), which consists of continuous recording of the fetal heart rate (FHR) and uterine contractions (UC), is routinely used for classifying the fetuses as hypoxic or non-hypoxic. In practice, we face highly imbalanced data, where the hypoxic fetuses are significantly underrepresented. We propose to address this problem by boost ensemble learning, where for learning, we use the distribution of classification error over the dataset. We then iteratively select the most informative majority data samples according to this distribution. In our work, in addition to addressing the imbalanced problem, we also experimented with features that are not commonly used in obstetrics. We extracted a large number of statistical features of fetal heart tracings and uterine activity signals and used only the most informative ones. For classification, we implemented several methods: Random Forest, AdaBoost, k-Nearest Neighbors, Support Vector Machine, and Decision Trees. The paper provides a comparison in the performance of these methods on fetal heart rate tracings available from a public database. Our results on the publicly available Czech database show that most applied methods improved their performances considerably when boost ensemble was used.

Low umbilical artery pH is a marker for neonatal acidosis and is associated with an increased risk for neonatal complications. The phase-rectified signal averaging (PRSA) features have demonstrated superior discriminatory or diagnostic ability and good interpretability in many biomedical applications including fetal heart rate analysis. However, the performance of PRSA method is sensitive to values of the selected parameters which are usually either chosen based on a grid search or empirically in the literature. In this paper, we examine PRSA method through the lens of dynamical systems theory and reveal the intrinsic connection between state space reconstruction and PRSA. From this perspective, we then introduce a new feature that can better characterize dynamical systems comparing with PRSA. Our experimental results on an open-access intrapartum Cardiotocography database demonstrate that the proposed feature outperforms state-of-the-art PRSA features in pH-based fetal heart rate analysis.

The computer-aided interpretation of fetal heart rate (FHR) and uterine contraction (UC) has not been developed well enough for wide use in delivery rooms. The main challenges still lie in the lack of unclear and nonstandard labels for cardiotocography (CTG) recordings, and the timely prediction of fetal state during monitoring. Rather than traditional supervised approaches to FHR classification, this paper demonstrates a way to understand the UC-dependent FHR responses in an unsupervised manner. In this work, we provide a complete method for FHR-UC segment clustering and analysis via the Gaussian process latent variable model, and density-based spatial clustering. We map the UC-dependent FHR segments into a space with a visual dimension and propose a trajectory-based FHR interpretation method. Three metrics of FHR trajectory are defined and an open-access CTG database is used for testing the proposed method.

Identifying uterine contractions with the aid of machine learning methods is necessary vis-á-vis their use in combination with fetal heart rates and other clinical data for the assessment of a fetus wellbeing. In this paper, we study contraction identification by processing noisy signals due to uterine activities. We propose a complete four-step method where we address the imbalanced classification problem with an ensemble Gaussian process classifier, where the Gaussian process latent variable model is used as a decision-maker. The results of both simulation and real data show promising performance compared to existing methods.

Classification with imbalanced data is a common and challenging problem in many practical machine learning problems. Ensemble learning is a popular solution where the results from multiple base classifiers are synthesized to reduce the effect of a possibly skewed distribution of the training set. In this paper, binary classifiers based on Gaussian processes are chosen as bases for inferring the predictive distributions of test latent variables. We apply a Gaussian process latent variable model where the outputs of the Gaussian processes are used for making the final decision. The tests of the new method in both synthetic and real data sets show improved performance over standard approaches.

Convergent cross mapping (CCM) is designed for causal discovery in coupled time series, where Granger causality may not be applicable because of a separability assumption. However, CCM is not robust to observation noise which limits its applicability on signals that are known to be noisy. Moreover, the parameters for state space reconstruction need to be selected using grid search methods. In this paper, we propose a novel improved version of CCM using Gaussian processes for discovery of causality from noisy time series. Specifically, we adopt the concept of CCM and carry out the key steps using Gaussian processes within a non-parametric Bayesian probabilistic framework in a principled manner. The proposed approach is first validated on simulated data, and then used for understanding the interaction between fetal heart rate and uterine activity in the last two hours before delivery and of interest in obstetrics. Our results indicate that uterine activity affects the fetal heart rate, which agrees with recent clinical studies.

In this paper, we propose a novel and simple method for discovery of Granger causality from noisy time series using Gaussian processes. More specifically, we adopt the concept of Granger causality, but instead of using autoregressive models for establishing it, we work with Gaussian processes. We show that information about the Granger causality is encoded in the hyper-parameters of the used Gaussian processes. The proposed approach is first validated on simulated data, and then used for understanding the interaction between fetal heart rate and uterine activity in the last two hours before delivery and of interest in obstetrics. Our results indicate that uterine activity affects fetal heart rate, which agrees with recent clinical studies.

In this paper, we propose an application of non-parametric Bayesian (NPB) models to classification of fetal heart rate recordings. More specifically, the models are used to discriminate between fetal heart rate recordings that belong to fetuses that may have adverse asphyxia outcomes and those that are considered normal. In our work we rely on models based on hierarchical Dirichlet processes. Two mixture models were inferred from recordings that represent healthy and unhealthy fetuses, respectively. The models were then used to classify new recordings. We compared the classification performance of the NPB models with that of support vector machines on real data and concluded that the NPB models achieved better performance.

In this paper, we propose to analyze fetal heart rate (FHR) signals by hierarchical Dirichlet process (HDP) mixture models. We investigate whether the clustering results of real-world FHR time series obtained by these models are informative in terms of determining the health status of a fetus. The FHR signals are divided into two groups, healthy and unhealthy, according to the umbilical arterial blood pH values of the fetuses. We computed the frequencies of clusters appearing in each of the groups, and applied the MannWhitney U test to compare the frequencies. The results showed that the frequencies of appearance of certain clusters are statistically significantly different across the two groups. This indicates that certain clusters may relate to pathological fetal heart rate patterns.

We study the problem of accurate automatic classification of fetal heart rate (FHR) signals using three different classification methods. FHR time series data are segmented into short (15s) spans of data, and features are extracted from them. These features include some established metrics of FHR trends such as acceleration and deceleration durations as well as a new set of features derived from the sequence of beat-to-beat percentage changes of the FHR signals. In total, we use 10 different features and demonstrate the feasibility of using them for classifying short segments into one of two suitably defined classes denoted as normal or abnormal. Classification is achieved using three different methods: support vector machine, a parametric Bayesian method and a non-parametric Bayesian method utilizing a neighbour-counting procedure for class-conditional density estimation. The performances of these methods are demonstrated on a database of physician-annotated recordings from which 580 short epochs of FHR patterns were extracted.