Machine Learning Algorithm to Predict Acidemia Using Electronic Fetal Monitoring Recording Parameters

Background: Electronic fetal monitoring (EFM) is the universal method for the surveillance of fetal well-being in intrapartum. Our objective was to predict acidemia from fetal heart signal features using machine learning algorithms. Methods: A case–control 1:2 study was carried out compromising 378 infants, born in the Miguel Servet University Hospital, Spain. Neonatal acidemia was defined as pH < 7.10. Using EFM recording logistic regression, random forest and neural networks models were built to predict acidemia. Validation of models was performed by means of discrimination, calibration, and clinical utility. Results: Best performance was attained using a random forest model built with 100 trees. The discrimination ability was good, with an area under the Receiver Operating Characteristic curve (AUC) of 0.865. The calibration showed a slight overestimation of acidemia occurrence for probabilities above 0.4. The clinical utility showed that for 33% cutoff point, missing 5% of acidotic cases, 46% of unnecessary cesarean sections could be prevented. Logistic regression and neural networks showed similar discrimination ability but with worse calibration and clinical utility. Conclusions: The combination of the variables extracted from EFM recording provided a predictive model of acidemia that showed good accuracy and provides a practical tool to prevent unnecessary cesarean sections.

What Do Women Want? Consent for the Use of Electronic Fetal Monitoring

BACKGROUNDGuidelines published by professional associations of midwives, obstetricians, and nurses in the United States recommend against using continuous cardiotocography (CTG) in low-risk patients. In the United States, CTG or electronic fetal/uterine monitoring (EFM) rather than auscultation with a fetoscope or Pinard horn is the norm. Interpretation of the fetal heart rate (FHR) and uterine activity (UA) tracings provided by continuous EFM may be associated with the decision for a cesarean birth. Typically, consent is not sought in the decision about type of monitoring. No studies were identified where women's attitudes about the need to consent to the type of fetal monitoring used during labor have been explored. Therefore, the purpose of this research was to examine women's attitudes about the use of EFM in a healthcare setting.METHODSWe asked a sample of women aged 18–50 years to respond to one of three monitoringscenarios. The scenarios were used to distinguish between attitudes about monitoring in general, monitoring the health of a mother in labor, and monitoring the health of the fetus during labor. Wemeasured their level of interest in being monitored and their opinions about whether healthcare providers should be required to obtain consent for the monitoring described in the scenario.RESULTSInterest in receiving monitoring (across all three scenarios) was moderate, with the highest level of interest in monitoring the fetus during labor and the least interest in monitoring a general health context. Across all scenarios, 82% of respondents believed that practitioners should obtain consent for monitoring, 14% were unsure, and 4% said there should not be a requirement for consent. While low (6%), the percentage responding that consent was not needed was highest in monitoring a fetus in labor.CONCLUSIONSWomen in our study expressed a strong preference for the opportunity to consent to the use of monitoring regardless of the healthcare scenario. There is findings suggest the need for further research exploring what women do and do not know about CTG and what their informed performance are a pressing need to rethink the role of a pressing need to rethink the role of shared decision-making and informed consent about the type of monitoring use during labor.

Characteristics of Heart Rate Tracings in Preterm Fetus

Background and Objectives: Prematurity is currently a serious public health issue worldwide, because of its high associated morbidity and mortality. Optimizing the management of these pregnancies is of high priority to improve perinatal outcomes. One tool frequently used to determine the degree of fetal wellbeing is cardiotocography (CTG). A review of the available literature on fetal heart rate (FHR) monitoring in preterm fetuses shows that studies are scarce, and the evidence thus far is unclear. The lack of reference standards for CTG patterns in preterm fetuses can lead to misinterpretation of the changes observed in electronic fetal monitoring (EFM). The aims of this narrative review were to summarize the most relevant concepts in the field of CTG interpretation in preterm fetuses, and to provide a practical approach that can be useful in clinical practice. Materials and Methods: A MEDLINE search was carried out, and the published articles thus identified were reviewed. Results: Compared to term fetuses, preterm fetuses have a slightly higher baseline FHR. Heart rate is faster in more immature fetuses, and variability is lower and increases in more mature fetuses. Transitory, low-amplitude decelerations are more frequent during the second trimester. Transitory increases in FHR are less frequent and become more frequent and increase in amplitude as gestational age increases. Conclusions: The main characteristics of FHR tracings changes as gestation proceeds, and it is of fundamental importance to be aware of these changes in order to correctly interpret CTG patterns in preterm fetuses.