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.

[Electrohysterography, a promising alternative for uterine monitoring: 5 years later]. / Elektrohysterografie veelbelovend alternatief voor weeënregistratie.

Electrohysterography monitors the electrical activity of the uterine muscle through electrodes on the maternal abdominal wall. It is a non-invasive method for uterine contraction monitoring and has a strong correlation with the invasive intra-uterine pressure catheter. A prospective validation study showed a significant higher sensitivity of electrohysterography compared to external tocodynamometry for uterine contraction detection (p-value < 0.001). Moreover, the sensitivity of electrohysterography appears to be less affected by maternal obesity compared to external tocodynamometry. A clinical pilotstudy comparing electrohysterography and external tocodynamometry during labor, showed no negative effect of electrohysterography on labor outcomes. Recently, technical improvements have been made and electrohysterography has become available in an adhesive electrode patch together with fetal and maternal electrocardiography. Therefore, we expect a successful implementation of electrohysterography in the near future.

Correction to: Intrauterine resuscitation during the second stage of term labour by maternal hyperoxygenation versus conventional care: study protocol for a randomised controlled trial (INTEREST O2).

Following publication of the original article [1], the authors noticed that the sample size for the study group was incorrectly reported in the Methods section.

Intrauterine resuscitation during the second stage of term labour by maternal hyperoxygenation versus conventional care: study protocol for a randomised controlled trial (INTEREST O2).

BACKGROUND: Perinatal asphyxia is, even in developed countries, one the major causes of neonatal morbidity and mortality. Therefore, if foetal distress during labour is suspected, one should try to restore foetal oxygen levels or aim for immediate delivery. However, studies on the effect of intrauterine resuscitation during labour are scarce. We designed a randomised controlled trial to investigate the effect of maternal hyperoxygenation on the foetal condition. In this study, maternal hyperoxygenation is induced for the treatment of foetal distress during the second stage of term labour. METHODS/DESIGN: This study is a single-centre randomised controlled trial being performed in a tertiary hospital in The Netherlands. From among cases of a suboptimal or abnormal foetal heart rate pattern during the second stage of term labour, a total of 116 patients will be randomised to the control group, where normal care is provided, or to the intervention group, where before normal care 100% oxygen is supplied to the mother by a non-rebreathing mask until delivery. The primary outcome is change in foetal heart rate pattern. Secondary outcomes are Apgar score, mode of delivery, admission to the neonatal intensive care unit and maternal side effects. In addition, blood gas values and malondialdehyde are determined in umbilical cord blood. DISCUSSION: This study will be the first randomised controlled trial to investigate the effect of maternal hyperoxygenation for foetal distress during labour. This intervention should be recommended only as a treatment for intrapartum foetal distress, when improvement of the foetal condition is likely and outweighs maternal and neonatal side effects. TRIAL REGISTRATION: EudraCT, 2015-001654-15; registered on 3 April 2015. Dutch Trial Register, NTR5461; registered on 20 October 2015.

Different patterns of depressive symptoms during pregnancy.

Recently, the US Preventive Services Task Force has advocated to screen pregnant and postpartum women for depression. However, we questioned the meaning of a single elevated depression score: does it represent just one episode of depression or do these symptoms persist throughout the entire pregnancy? This study assessed depressive symptoms at each trimester in a cohort of 1813 pregnant women and evaluated whether women with different patterns of depressive symptoms showed other characteristics. Depending on the trimester, elevated depression scores were prevalent in 10-15% of the pregnant women. Up to 4% reported persistent symptoms of depression throughout pregnancy. Different patterns of depressive symptoms were observed, for which persistent symptoms were related to other characteristics than incidentally elevated symptoms. Besides a previous history of mental health problems as best overall predictor, incidentally elevated depression scores were related to major life events. Furthermore, persistently depressive symptoms were related to unplanned pregnancy and multiparity. An EDS assessment at 12 weeks of gestation including three additional items (history of mental health problems, unplanned pregnancy and multiparity) enabled us to identify 83% of the women with persistent depressive symptoms. A depression screening strategy in pregnant women should take into account the potential chronicity of depressive symptoms by repeated assessments in order to offer an intervention to the most vulnerable women.

Fetal heart rate variability during pregnancy, obtained from non-invasive electrocardiogram recordings.

OBJECTIVE: Non-invasive spectral analysis of fetal heart rate variability is a promising new field of fetal monitoring. To validate this method properly, we studied the relationship between gestational age and the influence of fetal rest-activity state on spectral estimates of fetal heart rate variability. DESIGN: Prospective longitudinal study. SETTING: Tertiary care teaching hospital. POPULATION: Forty healthy women with an uneventful singleton pregnancy. METHODS: Non-invasive fetal electrocardiogram measurements via the maternal abdomen were performed at regular intervals between 14 and 40 weeks of gestation and processed to detect beat-to-beat fetal heart rate. Simultaneous ultrasound recordings were performed to assess fetal rest-activity state. MAIN OUTCOME MEASURES: Absolute and normalized power of fetal heart rate variability in the low (0.04-0.15 Hz) and high (0.4-1.5 Hz) frequency band were obtained, using Fourier Transform. RESULTS: 14% of all measurements and 3% of the total amount of abdominal data (330 segments) was usable for spectral analysis. During 21-30 weeks of gestation, a significant increase in absolute low and high frequency power was observed. During the active state near term, absolute and normalized low frequency power were significantly higher and normalized high frequency power was significantly lower compared with the quiet state. CONCLUSIONS: The observed increase in absolute spectral estimates in preterm fetuses was probably due to increased sympathetic and parasympathetic modulation and might be a sign of autonomic development. Further improvements in signal processing are needed before this new method of fetal monitoring can be introduced in clinical practice.