• Feature selection using genetic algorithms for fetal heart rate analysis.

    3 April 2018

    The fetal heart rate (FHR) is monitored on a paper strip (cardiotocogram) during labour to assess fetal health. If necessary, clinicians can intervene and assist with a prompt delivery of the baby. Data-driven computerized FHR analysis could help clinicians in the decision-making process. However, selecting the best computerized FHR features that relate to labour outcome is a pressing research problem. The objective of this study is to apply genetic algorithms (GA) as a feature selection method to select the best feature subset from 64 FHR features and to integrate these best features to recognize unfavourable FHR patterns. The GA was trained on 404 cases and tested on 106 cases (both balanced datasets) using three classifiers, respectively. Regularization methods and backward selection were used to optimize the GA. Reasonable classification performance is shown on the testing set for the best feature subset (Cohen's kappa values of 0.45 to 0.49 using different classifiers). This is, to our knowledge, the first time that a feature selection method for FHR analysis has been developed on a database of this size. This study indicates that different FHR features, when integrated, can show good performance in predicting labour outcome. It also gives the importance of each feature, which will be a valuable reference point for further studies.

  • Relation of fetal heart rate signals with unassignable baseline to poor neonatal state at birth.

    12 February 2018

    Electronic fetal heart rates (FHR) are used to monitor fetal health during labour. The paper records are visually assessed by clinicians, but automated alternatives are being developed. Interpretation, visual or computerised, depends on assigning a baseline to identify key features such as accelerations and decelerations. However, when the FHR is unstable the baseline may be unassignable, making conventional analysis unreliable. Such instability may reflect on fetal health. If true, these segments should not be discarded but quantified, for which we have developed a numerical method. In 7,568 labours, the association between unassignable baseline and umbilical arterial blood pH ≤ 7.05 at birth (evidence of poor health) was studied retrospectively. We found a consistent increase of the risk for acidaemia with longer intervals of unassignable baseline. This is detectable at the end of the first stage of labour, but stronger at the end of the second stage: in the last 30 min of labour, the odds ratios (with respect to baseline assignable throughout this period) increased from 1.99 (15 min unassignable) to 4.9 (30 min unassignable). Computerised analysis of the FHR becomes unreliable when the baseline cannot be assigned; however, this pattern is itself a pathological feature associated with acidaemia at birth.

  • Phase-rectified signal averaging for intrapartum electronic fetal heart rate monitoring is related to acidaemia at birth.

    29 March 2018

    OBJECTIVE: Recent studies suggest that phase-rectified signal averaging (PRSA), measured in antepartum fetal heart rate (FHR) traces, may sensitively indicate fetal status; however, its value has not been assessed during labour. We determined whether PRSA relates to acidaemia in labour, and compare its performance to short-term variation (STV), a related computerised FHR feature. DESIGN: Historical cohort. SETTING: Large UK teaching hospital. POPULATION: All 7568 Oxford deliveries that met the study criteria from April 1993 to February 2008. METHODS: We analysed the last 30 minutes of the FHR and associated outcomes of infants. We used computerised analysis to calculate PRSA decelerative capacity (DC(PRSA)), and its ability to predict umbilical arterial blood pH ≤ 7.05 using receiver operator characteristic (ROC) curves and event rate estimates (EveREst). We compared DC(PRSA) with STV calculated on the same traces. MAIN OUTCOME MEASURE: Umbilical arterial blood pH ≤ 7.05. RESULTS: We found that PRSA could be measured in all cases. DC(PRSA) predicted acidaemia significantly better than STV: the area under the ROC curve was 0.665 (95% CI 0.632-0.699) for DC(PRSA), and 0.606 (0.573-0.639) for STV (P = 0.007). EveREst plots showed that in the worst fifth centile of cases, the incidence of low pH was 17.75% for DC(PRSA) but 11.00% for STV (P < 0.001). DC(PRSA) was not highly correlated with STV. CONCLUSIONS: DC(PRSA) of the FHR can be measured in labour, and appears to predict acidaemia more accurately than STV. Further prospective evaluation is warranted to assess whether this could be clinically useful. The weak correlation between DC(PRSA) and STV suggests that they could be combined in multivariate FHR analyses.

  • Monitoring fetal maturation-objectives, techniques and indices of autonomic function.

    3 April 2018

    Monitoring the fetal behavior does not only have implications for acute care but also for identifying developmental disturbances that burden the entire later life. The concept, of 'fetal programming', also known as 'developmental origins of adult disease hypothesis', e.g. applies for cardiovascular, metabolic, hyperkinetic, cognitive disorders. Since the autonomic nervous system is involved in all of those systems, cardiac autonomic control may provide relevant functional diagnostic and prognostic information. The fetal heart rate patterns (HRP) are one of the few functional signals in the prenatal period that relate to autonomic control and, therefore, is predestinated for its evaluation. The development of sensitive markers of fetal maturation and its disturbances requires the consideration of physiological fundamentals, recording technology and HRP parameters of autonomic control. Based on the ESGCO2016 special session on monitoring the fetal maturation we herein report the most recent results on: (i) functional fetal autonomic brain age score (fABAS), Recurrence Quantitative Analysis and Binary Symbolic Dynamics of complex HRP resolve specific maturation periods, (ii) magnetocardiography (MCG) based fABAS was validated for cardiotocography (CTG), (iii) 30 min recordings are sufficient for obtaining episodes of high variability, important for intrauterine growth restriction (IUGR) detection in handheld Doppler, (iv) novel parameters from PRSA to identify Intra IUGR fetuses, (v) evaluation of fetal electrocardiographic (ECG) recordings, (vi) correlation between maternal and fetal HRV is disturbed in pre-eclampsia. The reported novel developments significantly extend the possibilities for the established CTG methodology. Novel HRP indices improve the accuracy of assessment due to their more appropriate consideration of complex autonomic processes across the recording technologies (CTG, handheld Doppler, MCG, ECG). The ultimate objective is their dissemination into routine practice and studies of fetal developmental disturbances with implications for programming of adult diseases.

  • The effect of augmentation of labour with syntocinon on the fetal CTG using objective computerised analysis: a nested case-control study.

    6 April 2018

    OBJECTIVE: To investigate the effect of syntocinon augmentation on the fetal cardiotocogram (CTG) using computerised analysis. We hypothesised that syntocinon will have no direct effects on the fetal heart rate if used correctly. STUDY DESIGN: A retrospective, nested case-control study. SETTING: Intrapartum CTG records from the digital archive at the John Radcliffe Hospital, Oxford, UK. SUBJECTS: 110 women with singleton pregnancies of >36 weeks gestation, no known congenital abnormality, spontaneous onset of labour and syntocinon augmentation for failure to progress, with start time of syntocinon recorded, from between August 1998 and December 1999, extensively matched to 110 controls who had normally progressing labours. METHODS: Eight different CTG features were measured during four time points with OxSys, a computerised numerical analysis system. STATISTICAL ANALYSIS: Differences in the CTG features over time in cases and controls using ANOVA and Friedman's ANOVA and at each time point between case-control pairs using Student's t-test and the Wilcoxon signed rank test. RESULTS: After administration, syntocinon increased the frequency, decreased the duration and decreased the resting time between contractions (p<0.001), resulting in no significant difference between normally progressing labours and those requiring augmentation. The case group had a significantly higher signal stability index (SSI) and fewer decelerations compared to the control group - differences which disappeared after augmentation was commenced (p=0.025 and 0.033 respectively). Syntocinon did not affect the baseline heart rate, short term variability (STV) or phase rectified signal averaging (PRSA) (p=0.518, 0.215 and 0.138) in comparison with controls. There was a significant increase in the PRSA in babies born with acidaemia (arterial pH≤7.05) 60-120min after syntocinon was commenced that was not seen with in babies with a normal pH (p=0.002). CONCLUSION: Syntocinon "normalises" ineffective uterine activity without any direct effect on the fetal heart rate. Therefore its administration does not confound objective computerised analysis. There may be a specific response in PRSA shortly after commencing syntocinon augmentation in the fetus which is subsequently born acidaemic which requires further investigation.