BOOST ENSEMBLE LEARNING FOR CLASSIFICATION OF CTG SIGNALS.

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 show that most applied methods improved their performances considerably when boost ensemble was used.

UNSUPERVISED CLUSTERING AND ANALYSIS OF CONTRACTION-DEPENDENT FETAL HEART RATE SEGMENTS.

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.

IMPROVING PHASE-RECTIFIED SIGNAL AVERAGING FOR FETAL HEART RATE ANALYSIS.

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.

Cardiotocography analysis by empirical dynamic modeling and Gaussian processes.

Introduction: During labor, fetal heart rate (FHR) and uterine activity (UA) can be continuously monitored using Cardiotocography (CTG). This is the most widely adopted approach for electronic fetal monitoring in hospitals. Both FHR and UA recordings are evaluated by obstetricians for assessing fetal well-being. Due to the complex and noisy nature of these recordings, the evaluation by obstetricians suffers from high interobserver and intraobserver variability. Machine learning is a field that has seen unprecedented advances in the past two decades and many efforts have been made in computerized analysis of CTG using machine learning methods. However, in the literature, the focus is often only on FHR signals unlike in evaluations performed by obstetricians where the UA signals are also taken into account. Methods: Machine learning is a field that has seen unprecedented advances in the past two decades and many efforts have been made in computerized analysis of CTG using machine learning methods. However, in the literature, the focus is often only on FHR signals unlike in evaluations performed by obstetricians where the UA signals are also taken into account. In this paper, we propose to model intrapartum CTG recordings from a dynamical system perspective using empirical dynamic modeling with Gaussian processes, which is a Bayesian nonparametric approach for estimation of functions. Results and Discussion: In the context of our paper, Gaussian processes are capable for simultaneous estimation of the dimensionality of attractor manifolds and reconstructing of attractor manifolds from time series data. This capacity of Gaussian processes allows for revealing causal relationships between the studied time series. Experimental results on real CTG recordings show that FHR and UA signals are causally related. More importantly, this causal relationship and estimated attractor manifolds can be exploited for several important applications in computerized analysis of CTG recordings including estimating missing FHR samples, recovering burst errors in FHR tracings and characterizing the interactions between FHR and UA signals.

IDENTIFICATION OF UTERINE CONTRACTIONS BY AN ENSEMBLE OF GAUSSIAN PROCESSES.

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.

CLASS-IMBALANCED CLASSIFIERS USING ENSEMBLES OF GAUSSIAN PROCESSES AND GAUSSIAN PROCESS LATENT VARIABLE MODELS.

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.

Unsupervised Detection of Anomalies in Fetal Heart Rate Tracings using Phase Space Reconstruction.

Detection of anomalies in time series is still a challenging problem. In this paper, we provide a new approach to unsupervised detection of anomalies in time series based on the concept of phase space reconstruction and manifolds. We propose a rotation-insensitive metric for quantifying the similarity of manifolds and a method that uses it for estimating the probability of an outlier. The proposed method does not rely on any features and can be used for signals with variable lengths. We tested it on both synthetic signals and real fetal heart rate tracings. The method has promising performance and can be used for interpreting the severity of fetal asphyxia.

Estimation of Consecutively Missed Samples in Fetal Heart Rate Recordings.

During labor, fetal heart rate (FHR) is monitored externally using Doppler ultrasound. This is done continuously, but for various reasons (e.g., fetal or maternal movements) the system does not record any samples for varying periods of time. In many settings, it would be quite beneficial to estimate the missing samples. In this paper, we propose a (deep) Gaussian process-based approach for estimation of consecutively missing samples in FHR recordings. The method relies on similarities in the state space and on exploiting the concept of attractor manifolds. The proposed approach was tested on a short segment of real FHR recordings. The experimental results indicate that the proposed approach is able to provide more reliable results in comparison to several interpolation methods that are commonly applied for processing of FHR signals.

DISCOVERING CAUSALITIES FROM CARDIOTOCOGRAPHY SIGNALS USING IMPROVED CONVERGENT CROSS MAPPING WITH GAUSSIAN PROCESSES.

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.

Detecting Causality using Deep Gaussian Processes.

Convergent cross mapping (CCM) is a state space reconstruction (SSR)-based method designed for causal discovery in coupled time series, where Granger causality may not be applicable due to a separability assumption. However, CCM requires a large number of observations and is not robust to observation noise which limits its applicability. Moreover, in CCM and its variants, the SSR step is mostly implemented with delay embedding where the parameters for reconstruction usually need to be selected using grid search-based methods. In this paper, we propose a Bayesian version of CCM using deep Gaussian processes (DGPs), which are naturally connected with deep neural networks. In particular, we adopt the framework of SSR-based causal discovery and carry out the key steps using DGPs within a non-parametric Bayesian probabilistic framework in a principled manner. The proposed approach is first validated on simulated data and then tested on data used in obstetrics for monitoring the well-being of fetuses, i.e., fetal heart rate (FHR) and uterine activity (UA) signals in the last two hours before delivery. Our results indicate that UA affects the FHR, which agrees with recent clinical studies.

EXTRACTING INTERPRETABLE FEATURES FOR FETAL HEART RATE RECORDINGS WITH GAUSSIAN PROCESSES.

During labor, fetal heart rate (FHR) and uterine activity (UA) are continuously monitored with Cardiotocography (CTG). The FHR and UA signals are visually inspected by obstetricians to assess the fetal well-being. However, due to the subjectivity of the visual inspection, the evaluations of CTG recordings performed by obstetricians have high inter- and intra-variability. The computerized analysis of FHR relies on features either hand-crafted by experts or automatically learned by machine learning methods. However, the popular interpretable FHR features, in general, have low correlation with the pH value of the umbilical cord blood at birth, which is the current gold standard for labeling FHRs in the computerized analysis of FHRs. The features found by machine learning methods, by contrast, usually have limited interpretability. In this paper, in a follow up of our previous work on FHR analysis using Gaussian processes (GPs), we explore the possibility of using the hyperparameters of GPs as interpretable features. Our results indicate that some GP features achieve high correlation with the pH values, while at the same time they are not highly correlated with other popular features.

INFERENCE ABOUT CAUSALITY FROM CARDIOTOCOGRAPHY SIGNALS USING GAUSSIAN PROCESSES.

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.

Placental Alpha Microglobulin-1 Compared With Fetal Fibronectin to Predict Preterm Delivery in Symptomatic Women.

OBJECTIVE: To compare the rapid bedside test for placental α microglobulin-1 with the instrumented fetal fibronectin test for prediction of imminent spontaneous preterm delivery among women with symptoms of preterm labor. METHODS: We conducted a prospective observational study on pregnant women with signs or symptoms suggestive of preterm labor between 24 and 35 weeks of gestation with intact membranes and cervical dilatation less than 3 cm. Participants were prospectively enrolled at 15 U.S. academic and community centers. Placental α microglobulin-1 samples did not require a speculum examination. Health care providers were blinded to placental α microglobulin-1 results. Fetal fibronectin samples were collected through speculum examination per manufacturer requirements and sent to a certified laboratory for testing using a cutoff of 50 ng/mL. The coprimary endpoints were positive predictive value (PPV) superiority and negative predictive value (NPV) noninferiority of placental α microglobulin-1 compared with fetal fibronectin for the prediction of spontaneous preterm birth within 7 days and within 14 days. RESULTS: Of 796 women included in the study cohort, 711 (89.3%) had both placental α microglobulin-1 and fetal fibronectin results and valid delivery outcomes available for analysis. The overall rate of preterm birth was 2.4% (17/711) within 7 days of testing and 4.2% (30/711) within 14 days of testing with respective rates of spontaneous preterm birth of 1.3% (9/703) and 2.9% (20/701). Fetal fibronectin was detected in 15.5% (110/711), and placental α microglobulin-1 was detected in 2.4% (17/711). The PPVs for spontaneous preterm delivery within 7 days or less among singleton gestations (n=13) for placental α microglobulin-1 and fetal fibronectin were 23.1% (3/13) and 4.3% (4/94), respectively (P<.025 for superiority). The NPVs were 99.5% (619/622) and 99.6% (539/541) for placental α microglobulin-1 and fetal fibronectin, respectively (P<.001 for noninferiority). CONCLUSION: Although placental α microglobulin-1 performed the same as fetal fibronectin in ruling out spontaneous preterm delivery among symptomatic women, it demonstrated statistical superiority in predicting it.

Dynamic classification of fetal heart rates by hierarchical Dirichlet process mixture models.

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.

FETAL HEART RATE CLASSIFICATION BY NON-PARAMETRIC BAYESIAN METHODS.

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.

Fetal heart rate classification using generative models.

This paper presents novel methods for classification of fetal heart rate (FHR) signals into categories that are meaningful for clinical implementation. They are based on generative models (GMs) and Bayesian theory. Instead of using scalar features that summarize information obtained from long-duration data, the models allow for explicit use of feature sequences derived from local patterns of FHR evolution. We compare our methods with a deterministic expert system for classification and with a support vector machine approach that relies on system-identification and heart rate variability features. We tested the classifiers on 83 retrospectively collected FHR records, with the gold-standard true diagnosis defined using umbilical cord pH values. We found that our methods consistently performed as well as or better than these, suggesting that the use of GMs and the Bayesian paradigm can bring significant improvement to automatic FHR classification approaches.

A delicate subject: The impact of cultural factors on neonatal and perinatal decision making.

The neonatal intensive care unit (NICU) is a high-stress environment for both families and health care providers that can sometimes make appropriate medical decisions challenging. We present a review article of non-medical barriers to effective decision making in the NICU, including: miscommunication, mixed messages, denial, comparative social and cultural influences, and the possible influence of perceived legal issues and family reliance on information from the Internet. As examples of these barriers, we describe and discuss two cases that occurred simultaneously in the same NICU where decisions were influenced by social and cultural differences that were misunderstood by both medical staff and patients' families. The resulting stress and emotional discomfort created an environment with sub-optimal relationships between patients' families and health care providers. We provide background on the sources of conflict in these particular cases. We also offer suggestions for possible amelioration of similar conflicts with the twin goals of facilitating compassionate decision making in NICU settings and promoting enhanced well-being of both families and providers.

Elective delivery before 39 weeks' gestation: reconciling maternal, fetal, and family interests in challenging circumstances.

We present the case of a 36-year-old woman who has experienced three lost pregnancies; during the most recent loss, a full term pregnancy, she almost died from complications of placental abruption. She is now completing the 34th week of gestation and is experiencing symptoms similar to those under which she lost the previous pregnancy. Despite a lack of specific medical indications, the patient and her husband firmly but politely request that the attending obstetrician/perinatologist perform an immediate cesarean section in order to alleviate the couple's anxiety about possibly never having a family. Discussing the case are an experienced perinatologist, a neonatologist, a regional perinatal center coordinator, and a clinical ethicist.

Morphometric changes in the human pulmonary acinus during inflation.

Despite decades of research into the mechanisms of lung inflation and deflation, there is little consensus about whether lung inflation occurs due to the recruitment of new alveoli or by changes in the size and/or shape of alveoli and alveolar ducts. In this study we use in vivo (3)He lung morphometry via MRI to measure the average alveolar depth and alveolar duct radius at three levels of inspiration in five healthy human subjects and calculate the average alveolar volume, surface area, and the total number of alveoli at each level of inflation. Our results indicate that during a 143 ± 18% increase in lung gas volume, the average alveolar depth decreases 21 ±5%, the average alveolar duct radius increases 7 ± 3%, and the total number of alveoli increases by 96 ± 9% (results are means ± SD between subjects; P < 0.001, P < 0.01, and P < 0.00001, respectively, via paired t-tests). Thus our results indicate that in healthy human subjects the lung inflates primarily by alveolar recruitment and, to a lesser extent, by anisotropic expansion of alveolar ducts.