• Insight and inference for DVARS.

    3 April 2018

    Estimates of functional connectivity using resting state functional Magnetic Resonance Imaging (rs-fMRI) are acutely sensitive to artifacts and large scale nuisance variation. As a result much effort is dedicated to preprocessing rs-fMRI data and using diagnostic measures to identify bad scans. One such diagnostic measure is DVARS, the spatial root mean square of the data after temporal differencing. A limitation of DVARS however is the lack of concrete interpretation of the absolute values of DVARS, and finding a threshold to distinguish bad scans from good. In this work we describe a sum of squares decomposition of the entire 4D dataset that shows DVARS to be just one of three sources of variation we refer to as D-var (closely linked to DVARS), S-var and E-var. D-var and S-var partition the sum of squares at adjacent time points, while E-var accounts for edge effects; each can be used to make spatial and temporal summary diagnostic measures. Extending the partitioning to global (and non-global) signal leads to a rs-fMRI DSE table, which decomposes the total and global variability into fast (D-var), slow (S-var) and edge (E-var) components. We find expected values for each component under nominal models, showing how D-var (and thus DVARS) scales with overall variability and is diminished by temporal autocorrelation. Finally we propose a null sampling distribution for DVARS-squared and robust methods to estimate this null model, allowing computation of DVARS p-values. We propose that these diagnostic time series, images, p-values and DSE table will provide a succinct summary of the quality of a rs-fMRI dataset that will support comparisons of datasets over preprocessing steps and between subjects.

  • Highly comparative fetal heart rate analysis.

    3 April 2018

    A database of fetal heart rate (FHR) time series measured from 7 221 patients during labor is analyzed with the aim of learning the types of features of these recordings that are informative of low cord pH. Our 'highly comparative' analysis involves extracting over 9 000 time-series analysis features from each FHR time series, including measures of autocorrelation, entropy, distribution, and various model fits. This diverse collection of features was developed in previous work [1]. We describe five features that most accurately classify a balanced training set of 59 'low pH' and 59 'normal pH' FHR recordings. We then describe five of the features with the strongest linear correlation to cord pH across the full dataset of FHR time series. The features identified in this work may be used as part of a system for guiding intervention during labor in future. This work successfully demonstrates the utility of comparing across a large, interdisciplinary literature on time-series analysis to automatically contribute new scientific results for specific biomedical signal processing challenges.

  • Computerized intrapartum electronic fetal monitoring: analysis of the decision to deliver for fetal distress.

    3 April 2018

    We applied computerized methods to assess the Electronic Fetal Monitoring (EFM) in labor. We analyzed retrospectively the last hour of EFM for 1,370 babies, delivered by emergency Cesarean sections before the onset of pushing (data collected at the John Radcliffe Hospital, Oxford, UK). There were two cohorts according to the reason for intervention: (a) fetal distress, n(1) = 524 and (b) failure to progress and/or malpresentation, n(2) = 846. The cohorts were compared in terms of classical EFM features (baseline, decelerations, variability and accelerations), computed by a dedicated Oxford system for automated analysis--OxSys. In addition, OxSys was employed to simulate current clinical guidelines for the classification of fetal monitoring, i.e. providing in real time a three-tier grading system of the EFM (normal, indeterminate, or abnormal). The computerized features and the simulated guidelines corresponded well to the clinical management and to the actual labor outcome (measured by umbilical arterial pH).

  • Computerised electronic foetal heart rate monitoring in labour: automated contraction identification.

    12 February 2018

    The foetal heart rate (FHR) response to uterine contractions is crucial to detect foetal distress by electronic FHR monitoring during labour. We are developing a new automated system (OxSys) for decision support in labour, using the Oxford database of intrapartum FHR records. We describe here a novel technique for automated detection of uterus contractions. In addition, we present a comparison of the new method with four other computerised approaches. During training, OxSys achieved sensitivity above 95% and positive predictive value (PPV) of up to 90% for traces of good quality. During testing, OxSys achieved sensitivity = 87% and PPV = 75%. For comparison, a second clinical expert obtained sensitivity = 93% and PPV = 80%, and all other computerised approaches achieved lower values. It was concluded that the proposed method can be employed with confidence in our study on foetal health assessment in labour and future OxSys development.

  • Doppler-based fetal heart rate analysis markers for the detection of early intrauterine growth restriction.

    6 March 2018

    One indicator for fetal risk of mortality is intrauterine growth restriction (IUGR). Whether markers reflecting the impact of growth restriction on the cardiovascular system, computed from a Doppler-derived heart rate signal, would be suitable for its detection antenatally was studied.We used a cardiotocography archive of 1163 IUGR cases and 1163 healthy controls, matched for gestation and gender. We assessed the discriminative power of short-term variability and long-term variability of the fetal heart rate, computed over episodes of high and low variation aiming to separate growth-restricted fetuses from controls. Metrics characterizing the sleep state distribution within a trace were also considered for inclusion into an IUGR detection model.Significant differences in the risk markers comparing growth-restricted with healthy fetuses were found. When used in a logistic regression classifier, their performance for identifying IUGR was considerably superior before 34 weeks of gestation. Long-term variability in active sleep was superior to short-term variability [area under the receiver operator curve (AUC) of 72% compared with 71%]. Most predictive was the number of minutes in high variation per hour (AUC of 75%). A multivariate IUGR prediction model improved the AUC to 76%.We suggest that heart rate variability markers together with surrogate information on sleep states can contribute to the detection of early-onset IUGR.

  • Computerized fetal heart rate analysis in labor: detection of intervals with un-assignable baseline.

    3 April 2018

    The fetal heart rate (FHR) is monitored during labor to assess fetal health. Both visual and computerized interpretations of the FHR depend on assigning a baseline to detect key features such as accelerations or decelerations. However, it is sometimes impossible to assign a baseline reliably, by eye or by numerical methods. To address this issue, we used the Oxford Intrapartum FHR Database to derive an algorithm based on the distribution of the FHR that detects heart rate intervals without a clear baseline. We aimed to recognize when a fetus cannot maintain its heart rate baseline and use this to assist computerized FHR analysis. Twenty-three FHR windows (15 min long) were used to develop the method. The algorithm was then validated by comparison with experts who classified 50 FHR windows into two groups: baseline assignable or un-assignable. The average agreement between experts (κ = 0.76) was comparable to the agreement between method and experts (κ = 0.67). The algorithm was used in 22 559 patients with intrapartum FHR records to retrospectively determine the incidence of intervals (defined as 15 min windows) that had un-assignable baselines. Sixty-six percent had one or more such episodes at some stage, most commonly after the onset of pushing (55%) and least commonly pre-labor (16%). These episodes are therefore relatively common. Their detection should improve the reliability of computerized analysis and allow further studies of what they signify clinically.

  • Computerized data-driven interpretation of the intrapartum cardiotocogram: a cohort study.

    3 April 2018

    Continuous intrapartum fetal monitoring remains a significant clinical challenge. We propose using cohorts of routinely collected data. We aim to combine non-classical (data-driven) and classical cardiotocography features with clinical features into a system (OxSys), which generates automated alarms for the fetus at risk of intrapartum hypoxia. We hypothesize that OxSys can outperform clinical diagnosis of "fetal distress", when optimized and tested over large retrospective data sets.We studied a cohort of 22 790 women in labor (≥36 weeks of gestation). Paired umbilical blood analyses were available. Perinatal outcomes were defined by objective criteria (normal; severe, moderate or mild compromise). We used the data retrospectively to develop a prototype of OxSys, by relating its alarms to perinatal outcome, and comparing its performance against standards achieved by bedside diagnosis.OxSys1.5 triggers an alarm if the initial trace is nonreactive or the decelerative capacity (a nonclassical cardiotocography feature), exceeds a threshold, adjusted for preeclampsia and thick meconium. There were 187 newborns with severe, 613 with moderate and 3197 with mild compromise; and 18 793 with normal outcome. OxSys1.5 increased the sensitivity for compromise detection: 43.3% vs. 38.0% for severe (p = 0.3) and 36.1% vs. 31.0% for moderate (p = 0.06); and reduced the false-positive rate (14.4% vs. 16.3%, p < 0.001).Large historic cohorts can be used to develop and optimize computerized cardiotocography monitoring, combining clinical and cardiotocography risk factors. Our simple prototype has demonstrated the principle of using such data to trigger alarms, and compares well with clinical judgment.