A comparison between computerised (mean range) and clinical visual cardiotocographic assessment

Artificial intelligence based cardiotocogram assessment during labor

OBJECTIVE

To assess whether artificial intelligence, inspired by clinical decision-making procedures in delivery rooms, can correctly interpret cardiotocographic tracings and distinguish between normal and pathological events.

STUDY DESIGN

A method based on artificial intelligence was developed to determine whether a cardiotocogram shows a normal response of the fetal heart rate to uterine activity (UA). For a given fetus and given the UA and previous FHR, the method predicts a fetal heart rate response, under the assumption that the fetus is still in good condition and based on how that specific fetus has responded so far. We hypothesize that this method, when having only learned from fetuses born in good condition, is incapable of predicting the response of a compromised fetus or an episode of transient fetal distress. The (in)capability of the method to predict the fetal heart rate response would then yield a method that can help to assess fetal condition when the obstetrician is in doubt. Cardiotocographic data of 678 deliveries during labor were selected based on a healthy outcome just after birth. The method was trained on the cardiotocographic data of 548 fetuses of this group to learn their heart rate response. Subsequently it was evaluated on 87 fetuses, by assessing whether the method was able to predict their heart rate responses. The remaining 43 cardiotocograms were segment-by-segment annotated by three experienced gynecologists, indicating normal, suspicious, and pathological segments, while having access to the full recording and neonatal outcome. This future knowledge makes the expert annotations of a quality that is unachievable during live interpretation.

RESULTS

The comparison between abnormalities detected by the method (only using past and present input) and the annotated CTG segments by gynecologists (also looking at future input) yields an area under the curve of 0.96 for the distinction between normal and pathological events in majority-voted annotations.

CONCLUSION

The developed method can distinguish between normal and pathological events in near real-time, with a performance close to the agreement between three gynecologists with access to the entire CTG tracing and fetal outcome. The method has a strong potential to support clinicians in assessing fetal condition in clinical practice.

Diagnosis and management of fetal growth restriction

Fetal growth restriction (FGR) remains a leading contributor to perinatal mortality and morbidity and metabolic syndrome in later life. Recent advances in ultrasound and Doppler have elucidated several mechanisms in the evolution of the disease. However, consistent classification and characterization regarding the severity of FGR is lacking. There is no cure, and management is reliant on a structured antenatal surveillance program with timely intervention. Hitherto, the time to deliver is an enigma. In this paper, the challenges in the diagnosis and management of FGR are discussed. The biophysical profile, Doppler, biochemical and molecular technologies that may refine management are reviewed. Finally, a model pathway for the clinical management of pregnancies complicated by FGR is presented.

Fetal brain sonography and fetal heart rate patterns in the preterm fetus

OBJECTIVE

The objective of the study was to study whether peri- and intraventricular echodensities in the brain of fetuses at risk for preterm birth are associated with changes in fetal heart rate (FHR) parameters.

STUDY DESIGN

Twenty preterm fetuses with peri- and intraventricular echodensities detected by transvaginal ultrasonography were matched with 20 fetuses without echodensities for gestational age, growth parameters, clinical disease, and maternal medication. Baseline FHR, long- and short-term variability, and the presence of accelerations and decelerations were analyzed with a computerized system and compared with the Wilcoxon matched-pairs signed-rank test. Both cases and controls were compared with a normal population.

RESULTS

No statistical differences in FHR parameters were found between cases with and controls without peri- and intraventricular echodensities. Both cases and controls had lower long- and short-term variabilities than the normal population.

CONCLUSION

No association between the presence of peri- and intraventricular echodensities and specific FHR changes was demonstrated.

Management of fetal growth restriction

Fetal growth restriction (FGR) is challenging because of the difficulties in reaching a definitive diagnosis of the cause and planning management. FGR is associated not only with a marked increased risk in perinatal mortality and morbidity but also with long-term outcome risks. Combinations of fetal biometry, amniotic fluid volume, heart rate patterns, arterial and venous Doppler, and biophysical variables allow a comprehensive fetal evaluation of FGR. However, no evidence supports that the use of cardiotocography or the biophysical profile improves perinatal outcome. Therefore, obstetricians aim to identify fetuses with early FGR so delivery can be planned according to gestational age and severity of the condition. The balance of risks and the need for the availability of services mean that the involvement of neonatologists in FGR management is vital. In this review, the focus is on the pathophysiology and management of FGR caused by placental diseases.

Effect of Betamethasone Administration on Fetal Heart Rate Tracing: A Blinded Longitudinal Study

OBJECTIVE

Computerized fetal heart rate (FHR) analysis revealed that antenatal corticosteroids transiently suppress multiple parameters of fetal well-being, potentially leading to the erroneous diagnosis of fetal distress and to unnecessary iatrogenic delivery of premature infants. Our aim was to determine whether clinicians who visually analyze FHR tracings detect these suppressive effects, thereby potentially affecting their clinical management decisions.

METHODS

Singleton pregnancies admitted for preterm labor between 26 and 34 weeks' gestation received two doses of betamethasone, 24 h apart, and were monitored daily between 16:00 and 19:00 h for 5 days. FHR tracings were randomly coded and presented in a non-consecutive order to four clinicians, who were unaware of the time of steroid administration. FHR baseline, FHR variability, number of accelerations and amplitude of maximal FHR acceleration were determined. Variability was scored semiquantitatively based on a modified Hon score. Analysis of variance (ANOVA) with repeated measures was used for primary analysis and followed up with the Wald test of significance. Corrections for multiple comparisons were made and only p < 0.005 considered significant. ANOVA was also used to assess the uniformity of trend in the interpretation by the four examiners for each given day.

RESULTS

Baseline FHR was elevated, FHR variability was decreased, and the number of accelerations decreased on day 1 (p < 0.0001; p < 0.0001; p < 0.0001) and day 2 (p > 0.0001; p < 0.0001; p < 0.0001) in comparison to day 0. On day 3, the FHR baseline, variability and number of accelerations returned to pre-exposure values (p = NS). The maximal amplitude of FHR accelerations showed a trend towards reduction (p = 0.08). Subgroup analysis by gestational age (group I = 26-30 weeks and group II = 30-34 weeks) showed the same response patterns and significance levels for both groups.

CONCLUSIONS

Betamethasone causes profound, but transient, suppression of FHR parameters, which can mimic fetal distress. This effect is clinically recognized by visual FHR analysis. Clinicians need to be aware of this phenomenon, in order to avoid unwarranted iatrogenic delivery.

Application of artificial neural networks for detection of abnormal fetal heart rate pattern: a comparison with conventional algorithms

Cardiotocography signals were sampled during labour in 53 patients. A recurrent artificial neural network with hidden layer feedback was trained and performance was compared with that of several conventional systems. Correct and false positive rates of all systems tested were calculated. To ensure that the performance of neural networks was not just caused by using different cut-off levels, the threshold used for conventional methods were also adapted and optimised. The correct positives rate of neural networks was between 0.72 and 0.9, and the false positive rate between 0.2 and 0.4. Before optimising, conventional algorithms produced a very low correct positive (0.02-0.5) and a low false positive rate (0.0-0.08). After adjusting the parameters, the tested neural networks still performed better than optimised conventional systems.

Developments in CTG analysis

FHR monitoring has been the subject of many debates. The technique, in itself, can be considered to be accurate and reliable both in the antenatal period, when using the Doppler signal in combination with autocorrelation techniques, and during the intrapartum period, in particular when the FHR signal can be obtained from a fetal ECG electrode placed on the presenting part. The major problems with FHR monitoring relate to the reading and interpretation of the CTG tracings. Since the FHR pattern is primarily an expression of the activity of the control by the central and peripheral nervous system over cardiovascular haemodynamics, it is possibly too indirect a signal. In other specialities such as neonatology, anaesthesiology and cardiology, monitoring and graphic display of heart rate patterns have not gained wide acceptance among clinicians. Digitized archiving, numerical analysis and even more advanced techniques, as described in this chapter, have primarily found a place in obstetrics. This can be easily explained, since the obstetrician is fully dependent on indirectly collected information regarding the fetal condition, such as (a) movements experienced by the mother, observed with ultrasound or recorded with kinetocardiotocography (Schmidt, 1994), (b) perfusion of various vessels, as assessed by Doppler velocimetry, (c) the amount of amniotic fluid or (d) changes reflected in the condition of the mother, such as the development of gestation-induced hypertension and (e) the easily, continuously obtainable FHR signal. It is of particular comfort to the obstetrician that a normal FHR tracing reliably predicts the birth of the infant in a good condition, which makes cardiotocography so attractive for widespread application. However, in the intrapartum period, many traces cannot fulfil the criteria of normality, especially in the second stage. In this respect, cardiotocography remains primarily a screening and not so much a diagnostic method. As long as continuous monitoring of fetal acid-base balance has not been extensively tested in clinical practice, microblood sampling of the fetal presenting part (Saling, 1994) is a useful adjunct. The problem with non-normal tracings is that their significance is very often unclear. They may indicate serious fetal distress, finally resulting in preventable destruction of critical areas in the fetal brain and damage to various organs; or, on the contrary, they may indicate temporary changes in cardiovascular control as a reaction to the intermittent effects on fetal haemodynamics of, for example, uterine contractions, whether or not in combination with partial or complete compression of umbilical cord vessels or the vessels on the chorionic plate (van Geijn, 1994). Many factors influence the FHR and its variability, which further complicates the interpretation of FHR patterns; some have been discussed here in some detail. Undoubtedly, there is a need for quantitative and objective FHR analysis, as long as it does not lead to erroneous results. Close collaboration between engineers and clinicians is a prerequisite for further advances in this field. Decision support systems certainly have a future but only if they are able to take into account a large set of clinical data and can combine it with data obtained from FHR signals and other parameters referring to the fetal condition, such as fetal growth, Doppler velocimetry, amniotic fluid volume and biochemical and biophysical data obtained from the mother. Basic technical concepts inherent in computerized CTG analysis, such as sampling rate (Chang et al, 1995), signal loss, artefact detection (van Geijn et al, 1980), further processing of intervals, archiving in digitized format and monitor display, should receive considerable attention. There is still a long way to go until decision support systems find their way into obstetric practice. Further developments can only be achieved thanks to efforts of many basic and clinical researchers, wo

Improvements in computerized fetal heart rate analysis antepartum

The continued development of a computerised system for measuring the pattern of the antepartum fetal heart rate (FHR) is described. Previous work had established that measurement of FHR variation objectively detects chronic fetal hypoxaemia and the onset of metabolic acidaemia antepartum. The normal centiles were calculated for the amplitude of long-term FHR variation, in episodes of high and low variation, week by week from 24-42 weeks gestation. Reference to these (automatically by the computer) improved discrimination between normal and questionable records in 38% of records, with a small saving of time. Two types of sinusoidal rhythm were described (slow, 1 in 2-5 minutes, incidence 0.16% of subjects; and faster, 2-5 per minute, incidence 0.025%) with methods for their detection. Both may be of sufficient amplitude to induce an episode of high FHR variation. The different effects of maternal steroid (betamethasone or dexamethasone) administration of FHR variation were compared, and the clinical consequences considered. The frequency distribution of basal FHR in normal and abnormal records was measured, and the effects on basal FHR outside the normal range (120-160 bpm) on FHR variation described. Adjustment of the FHR baseline was undertaken when, exceptionally, large abrupt changes in heart rate occurred during a record. The duration and frequency of FHR record acquisition in clinical practice were reviewed, and new policies recommended. With adequate safeguards, measurement by a computer offers reliable objective information from which fetal health may be assessed, more objectively and accurately than by visual inspection.

Case-control study of antenatal and intrapartum risk factors for cerebral palsy in very preterm singleton babies

The increase in survival of very preterm babies during the 1980s was accompanied by a sharp increase in the rate of cerebral palsy in this group. The relation between antenatal and intrapartum factors and cerebral palsy in such babies has not been well defined. To identify adverse and protective antenatal and intrapartum factors we undertook a case-control study of 59 very preterm babies who developed cerebral palsy, identified from a population-based register, and 234 randomly selected controls. The frequency of cerebral palsy decreased with increasing gestational age and birthweight. Antenatal complications occurred in 215 (73%) of the women with preterm deliveries. Factors associated with an increased risk of cerebral palsy after adjustment for gestational age were chorioamnionitis (odds ratio 4.2 [95% CI 1.4-12.0]) prolonged rupture of membranes (2.3 [1.2-4.2]), and maternal infection (2.3 [1.2-4..5]). Pre-eclampsia was associated with a reduced risk of cerebral palsy (0.4 [0.2-0.9]), as was delivery without labour (0.3 [0.2-0.7]). There was no increased risk of cerebral palsy with intrauterine growth retardation (1.0 [0.9-1.1]). The effect of rigorous management of adverse antenatal factors on the frequency of cerebral palsy in very preterm babies should be tested in randomised controlled trials.

Prediction of morbidity in small and normally grown fetuses by fetal heart rate variability, biophysical profile score and umbilical artery Doppler studies

OBJECTIVE

To assess the ability of noninvasive tests of fetal wellbeing to predict hypoxic morbidity independent of fetal size.

DESIGN

A prospectively planned, longitudinal, observational study.

SETTING

Fetal Surveillance Unit, King's College Hospital, London.

SUBJECTS

One hundred and ninety-one pregnant women with singleton pregnancies who were delivered after 32 weeks' gestation who were seen in the Fetal Surveillance Unit within seven days of delivery.

INTERVENTIONS

Fetal surveillance by fetal abdominal circumference, heart rate variability (mean range), biophysical profile score and umbilical artery pulsatility index measurements.

MAIN OUTCOME MEASURES

Birthweight was classified as > or < or = 2.5th centile (AGA or SGA) for gestational age and sex. Morbidity was defined as at least one of the following at birth: delivery by emergency caesarean section for fetal distress, umbilical venous blood pH less than 7.15, 5 min Apgar score less than 7 or admission to the Special Care Baby Unit (SCBU).

RESULTS

Fetal abdominal circumference was the best indicator of which fetuses (n = 30) would be SGA. Fourteen of the 30 (47%) SGA fetuses had morbidity at birth and abnormal umbilical Doppler studies significantly predicted this (chi 2 = 2.93, P = 0.003). By contrast, fetal heart rate variability and the biophysical profile score did not. Twenty-seven of the 161 (17%) AGA fetuses had morbidity at birth, but this was not significantly predicted by heart rate variability, biophysical profile score or umbilical Doppler studies.

CONCLUSIONS

None of the antenatal testing techniques studied predicted morbidity in normally grown fetuses but Doppler studies indicated whether a small fetus was 'sick small' or 'normal small'.