The iPREFACE score is useful for predicting fetal acidemia: A retrospective cohort study of 113 patients who underwent emergency cesarean section for non-reassuring fetal status during labor.

BACKGROUND: The iPREFACE score may aid in predicting fetal acidemia and neonatal asphyxia in emergency cesarean and vaginal deliveries, which may improve labor management precision in the future. OBJECTIVE: This study aimed to assess the score use of the iPREFACE as an objective indicator of the need for rapid delivery in cases of repeated abnormal waveforms without concurrent indications for immediate medical intervention during labor. STUDY DESIGN: This retrospective cohort study was conducted among term (37+ 0 days to 41+6 days) singleton pregnant women who underwent emergency cesarean delivery owing to a nonreassuring fetal status. The integrated score index to predict fetal acidemia by intrapartum fetal heart rate monitoring-decision of emergency cesarean delivery score, calculated from a 30-minute cardiotocography waveform before the decision to perform emergency cesarean delivery, and the integrated score index to predict fetal acidemia by intrapartum fetal heart rate monitoring-removal of cardiotocography transducer score, calculated from a 30-minute cardiotocography waveform before cardiotocography transducer removal, were employed. The primary outcome was the assessment of the predictive ability of these scores for fetal acidemia, whereas the secondary outcomes were differences in umbilical artery blood gas findings and postnatal outcomes between the 2 groups, divided by the cutoff values of the integrated score index to predict fetal acidemia by intrapartum fetal heart rate monitoring-removal of cardiotocography score. RESULTS: The integrated score index to predict fetal acidemia by intrapartum fetal heart rate monitoring-decision of emergency cesarean delivery and integrated score index to predict fetal acidemia by intrapartum fetal heart rate monitoring-removal of cardiotocography transducer scores demonstrated the capability to predict an umbilical artery blood pH of <7.2. The integrated score index to predict fetal acidemia by intrapartum fetal heart rate monitoring-decision of emergency cesarean delivery and -removal of cardiotocography transducer score, with cutoff values of 37 and 46 points, respectively, exhibited an area under the receiver operating characteristic curve of 0.82 and 0.87, respectively. The integrated score index to predict fetal acidemia by intrapartum fetal heart rate monitoring-removal of cardiotocography transducer group with ≥46 points had higher incidence rates of an umbilical cord artery blood pH of <7.2, <7.1, and <7.0 and neonatal intensive care unit admissions for neonatal asphyxia. CONCLUSION: The integrated score index to predict fetal acidemia by intrapartum fetal heart rate monitoring, derived from cardiotocography during an emergency cesarean delivery, may enable clinicians to predict fetal acidemia in cases of nonreassuring fetal status. Improved prediction of fetal acidemia and facilitation of timely intervention hold promise for enhancing the outcomes of mothers and newborns during childbirth. Prospective studies are warranted to establish precise cutoff values and to validate the clinical application of these scores.

Short-term variation of the fetal heart rate as a marker of intraamniotic infection in pregnancies with preterm prelabor rupture of membranes: a historical cohort study.

INTRODUCTION: Intraamniotic infection (IAI) and subsequent early-onset neonatal sepsis (EONS) are among the main complications associated with preterm prelabor rupture of membranes (PPROM). Currently used diagnostic tools have been shown to have poor diagnostic performance for IAI. This study aimed to investigate whether the exposure to IAI before delivery is associated with short-term variation of the fetal heart rate in pregnancies with PPROM. METHODS: Observational cohort study of 678 pregnancies with PPROM, delivering between 24 + 0 and 33 + 6 gestational weeks from 2012 to 2019 in five labor units in Stockholm County, Sweden. Electronic medical records were examined to obtain background and exposure data. For the exposure IAI, we used the later diagnosis of EONS in the offspring as a proxy. EONS is strongly associated to IAI and was considered a better proxy for IAI than the histological diagnosis of acute chorioamnionitis, since acute chorioamnionitis can be observed in the absence of both positive microbiology and biochemical markers for inflammation. Cardiotocography traces were analyzed by a computerized algorithm for short-term variation of the fetal heart rate, which was the main outcome measure. RESULTS: Twenty-seven pregnancies were categorized as having an IAI, based on the proxy diagnosis of EONS after birth. Fetuses exposed to IAI had significantly lower short-term variation values in the last cardiotocography trace before birth than fetuses who were not exposed (5.25 vs 6.62 ms; unadjusted difference: -1.37, p = 0.009). After adjustment for smoking and diabetes, this difference remained significant. IAI with a later positive blood culture in the neonate (n = 12) showed an even larger absolute difference in STV (-1.65; p = 0.034), with a relative decrease of 23.5%. CONCLUSION: In pregnancies with PPROM, fetuses exposed to IAI with EONS as a proxy have lower short-term variation of the fetal heart rate than fetuses who are not exposed. Short-term variation might be useful as adjunct surveillance in pregnancies with PPROM.

Computer Vision for Identification of Increased Fetal Heart Variability in Cardiotocogram.

INTRODUCTION: Increased fetal heart rate variability (IFHRV), defined as fetal heart rate (FHR) baseline amplitude changes of >25 beats per minute with a duration of ≥1 min, is an early sign of intrapartum fetal hypoxia. This study evaluated the level of agreement of machine learning (ML) algorithms-based recognition of IFHRV patterns with expert analysis. METHODS: Cardiotocographic recordings and cardiotocograms from 4,988 singleton term childbirths were evaluated independently by two expert obstetricians blinded to the outcomes. Continuous FHR monitoring with computer vision analysis was compared with visual analysis by the expert obstetricians. FHR signals were graphically processed and measured by the computer vision model labeled SALKA. RESULTS: In visual analysis, IFHRV pattern occurred in 582 cardiotocograms (11.7%). Compared with visual analysis, SALKA recognized IFHRV patterns with an average Cohen's kappa coefficient of 0.981 (95% CI: 0.972-0.993). The sensitivity of SALKA was 0.981, the positive predictive rate was 0.822 (95% CI: 0.774-0.903), and the false-negative rate was 0.01 (95% CI: 0.00-0.02). The agreement between visual analysis and SALKA in identification of IFHRV was almost perfect (0.993) in cases (N = 146) with neonatal acidemia (i.e., umbilical artery pH <7.10). CONCLUSIONS: Computer vision analysis by SALKA is a novel ML technique that, with high sensitivity and specificity, identifies IFHRV features in intrapartum cardiotocograms. SALKA recognizes potential early signs of fetal distress close to those of expert obstetricians, particularly in cases of neonatal acidemia.

Multicentric intelligent cardiotocography signal interpretation using deep semi-supervised domain adaptation via minimax entropy and domain invariance.

BACKGROUND AND OBJECTIVE: Obstetricians use Cardiotocography (CTG), which is the continuous recording of fetal heart rate and uterine contraction, to assess fetal health status. Deep learning models for intelligent fetal monitoring trained on extensively labeled and identically distributed CTG records have achieved excellent performance. However, creation of these training sets requires excessive time and specialist labor for the collection and annotation of CTG signals. Previous research has demonstrated that multicenter studies can improve model performance. However, models trained on cross-domain data may not generalize well to target domains due to variance in distribution among datasets. Hence, this paper conducted a multicenter study with Deep Semi-Supervised Domain Adaptation (DSSDA) for intelligent interpretation of antenatal CTG signals. This approach helps to align cross-domain distribution and transfer knowledge from a label-rich source domain to a label-scarce target domain. METHODS: We proposed a DSSDA framework that integrated Minimax Entropy and Domain Invariance (DSSDA-MMEDI) to reduce inter-domain gaps and thus achieve domain invariance. The networks were developed using GoogLeNet to extract features from CTG signals, with fully connected, softmax layers for classification. We designed a Dynamic Gradient-driven strategy based on Mutual Information (DGMI) to unify the losses from Minimax Entropy (MME), Domain Invariance (DI), and supervised cross-entropy during iterative learning. RESULTS: We validated our DSSDA model on two datasets collected from collaborating healthcare institutions and mobile terminals as the source and target domains, which contained 16,355 and 3,351 CTG signals, respectively. Compared to the results achieved with deep learning networks without DSSDA, DSSDA-MMEDI significantly improved sensitivity and F1-score by over 6%. DSSDA-MMEDI also outperformed other state-of-the-art DSSDA approaches for CTG signal interpretation. Ablation studies were performed to determine the unique contribution of each component in our DSSDA mechanism. CONCLUSIONS: The proposed DSSDA-MMEDI is feasible and effective for alignment of cross-domain data and automated interpretation of multicentric antenatal CTG signals with minimal annotation cost.

Fetal Heart Rate Preprocessing Techniques: A Scoping Review.

Monitoring fetal heart rate (FHR) through cardiotocography is crucial for the early diagnosis of fetal distress situations, necessitating prompt obstetrical intervention. However, FHR signals are often marred by various contaminants, making preprocessing techniques essential for accurate analysis. This scoping review, following PRISMA-ScR guidelines, describes the preprocessing methods in original research articles on human FHR (or beat-to-beat intervals) signal preprocessing from PubMed and Web of Science, published from their inception up to May 2021. From the 322 unique articles identified, 54 were included, from which prevalent preprocessing approaches were identified, primarily focusing on the detection and correction of poor signal quality events. Detection usually entailed analyzing deviations from neighboring samples, whereas correction often relied on interpolation techniques. It was also noted that there is a lack of consensus regarding the definition of missing samples, outliers, and artifacts. Trends indicate a surge in research interest in the decade 2011-2021. This review underscores the need for standardizing FHR signal preprocessing techniques to enhance diagnostic accuracy. Future work should focus on applying and evaluating these methods across FHR databases aiming to assess their effectiveness and propose improvements.

Intrapartum pyrexia, cardiotocography traces and histologic chorioamnionitis: a case-control study.

OBJECTIVES: To compare characteristics of labor, cardiotocography traces, and maternal and neonatal outcomes, in a cohort of pregnancies at term complicated by maternal intrapartum pyrexia, with or without a histologic diagnosis of chorioamnionitis. METHODS: This is a retrospective case-control study including pregnancies at term with detection of maternal intrapartum pyrexia, delivered between January 2020 and June 2021. Cardiotocography traces were entirely evaluated, since admission till delivery, and classified according to the International Federation of Obstetrics and Gynecology (FIGO) guideline. Maternal and neonatal outcomes were also recorded as secondary outcomes. Placentas have been studied according to the Amniotic Fluid Infection Nosology Committee. RESULTS: Forty four patients met the inclusion criteria and were included in the study cohort. There was a significant association between the use of oxytocin augmentation in labor and the histologic diagnosis of chorioamnionitis. A significative recurrence of loss and/or absence of accelerations at the point of pyrexia was also documented in women with histological chorioamnionitis compared to the others. CONCLUSIONS: Chorioamnionitis appears to be associated with myometrial disfunction, as suggested by the increased use of oxytocin augmentation during active labor of women at term with intrapartum pyrexia and histologic diagnosis of chorioamnionitis.

Labor management and neonatal outcomes in cardiotocography categories II and III (Review).

The safe care of both mothers and fetuses during labor is a primary goal of all health professionals. The assessment of fetal oxygenation and well-being is a key aspect of perinatal care provided. Fetal heart rate (FHR) auscultation became part of daily obstetric practice in a number of countries during the 20th century and remains a key method of fetal monitoring, particularly in low-risk pregnancies. Cardiotocography (CTG) is the continuous monitoring and recording of the FHR and uterine myometrial activity, making it possible to assess the fetal condition. It therefore plays a critical role in the detection of fetal hypoxia during labor, a condition directly related to short- and long-term complications in the newborn. Herein, particular reference is made to the management of CTG category II and III standards, as well as to the handling of childbirth. In addition, specific FHR patterns are associated with immediate neonatal outcomes based on updated studies conducted worldwide. Finally, the prognostic significance of CTG and its potential as a prospective avenue for further investigation are also highlighted herein. Given that the misinterpretation of CTG findings is the most common cause of medical-legal responsibility, this knowledge field requires more emphasis and attention. The aim of the present review was to further deepen the knowledge on issues that mainly concern the safety and monitoring of pregnant women and fetuses during childbirth.

Maternal levels of care during pregnancy influence labor and delivery outcomes - present practices and future priorities.

Neonatal encephalopathy (NE) is a diagnosis that is usually unexpected. Though there are many risk factors for the condition and multiple theories as to its genesis, the majority of cases cannot be predicted prior to the occurrence of the clinical syndrome. Indeed, it is common for a pregnant person to have multiple risk factors and a completely healthy child. Conversely, people with seemingly no risk factors may go on to have a profoundly affected child. In this synopsis we review risk factors, potential mechanisms for encephalopathy, the complicated issue of choosing which morbidity to take on and how the maternal level of care may influence outcomes. The reader should be able to better understand the limitations of current testing and the profound levels of maternal intervention that have been undertaken to prevent or mitigate the rare, but devastating occurrence of NE. Further, we suggest candidate future approaches to prevent the occurrence, and decrease the severity of NE. Any future improvements in the NE syndrome cannot be achieved via obstetric intervention and management alone or conversely, by improvements in treatments offered post-birth. Multidisciplinary approaches that encompass prepregnancy health, pregnancy care, intrapartum management and postpartum care will be necessary.

The utility of fetal heart rate deceleration's descending slope in searching for a non-National Institute of Child Health and Human Development parameter for the detection of fetal acidosis.

OBJECTIVE: To identify new parameters predicting fetal acidemia. METHODS: A retrospective case-control study in a cohort of deliveries from a tertiary referral hospital-based cohort deliveries in Zaragoza, Spain between 2018 and 2021 was performed. To predict fetal acidemia, the NICHD categorizations and non-NICHD parameters were analyzed in the electronic fetal monitoring (EFM). Those included total reperfusion time, total deceleration area and the slope of the descending limb of the fetal heart rate of the last deceleration curve. The accuracy of the parameters was evaluated using the specificity for (80%, 85%, 90%, 95%) sensitivity and the area under the receiver operating characteristic curve (AUC). RESULTS: A total of 10 362 deliveries were reviewed, with 224 cases and 278 controls included in the study. The NICHD categorizations showed reasonable discriminatory ability (AUC = 0.727). The non-NICHD parameters measured during the 30-min fetal monitoring, total deceleration area (AUC = 0.807, 95% CI: 0.770, 0.845) and total reperfusion time (AUC = 0.750, 95% CI: 0.707, 0.792), exhibited higher discriminatory ability. The slope of the descending limb of the fetal heart rate of the last deceleration curve had the best AUC value (0.853, 95% CI: 0.816, 0.889). The combination of total deceleration area or total reperfusion time with the slope demonstrated high discriminatory ability (AUC = 0.908, 95% CI: 0.882, 0.933; specificities of 71.6% and 72.7% for a sensitivity of 90%). CONCLUSIONS: The slope of the descending limb of the fetal heart rate of the last deceleration curve is the strongest predictor of fetal acidosis, but its combination with the total reperfusion time shows better clinical utility.

Inter- and intraobserver agreement of antenatal cardiotocography assessments by maternity care professionals: A prospective study.

OBJECTIVE: In the Netherlands, antenatal cardiotocography (aCTG) to assess fetal well-being is performed in obstetrician-led care. An innovative initiative was started to evaluate whether aCTG for specific indications-reduced fetal movements, external cephalic version, or postdate pregnancy-is feasible in non-obstetrician-led care settings by independent primary care midwives. Quality assessment is essential when reorganizing and shifting tasks and responsibilities. Therefore, we aimed to assess the inter- and intraobserver agreement for aCTG assessments between and within four professional groups involved in Dutch maternity care regarding the overall classification and assessment of the various components of aCTG. METHOD: This was a prospective study among 47 Dutch primary care midwives, hospital-based midwives, residents, and obstetricians. Ten aCTG traces were assessed twice at a 1 month interval. To ensure a representative sample, we used two different sets of 10 aCTG traces each. We calculated the degree of agreement using the proportions of agreement. RESULTS: The proportions of agreement for interobserver agreement on the classification of aCTG between and within the four professional groups varied from 0.82 to 0.94. The proportions of agreement for each professional group were slightly higher for intraobserver (0.86-0.94) than for interobserver agreement. For the various aCTG components, the proportions of agreement for interobserver agreement varied from 0.64 (presence of contractions) to 0.98 (baseline heart frequency). CONCLUSION: The proportion of agreement levels between and within the maternity care professionals in the classification of aCTG traces among healthy women were comparable. This means that these professional groups are equally well able to classify aCTGs in healthy pregnant women.

Machine learning on cardiotocography data to classify fetal outcomes: A scoping review.

INTRODUCTION: Uterine contractions during labour constrict maternal blood flow and oxygen delivery to the developing baby, causing transient hypoxia. While most babies are physiologically adapted to withstand such intrapartum hypoxia, those exposed to severe hypoxia or with poor physiological reserves may experience neurological injury or death during labour. Cardiotocography (CTG) monitoring was developed to identify babies at risk of hypoxia by detecting changes in fetal heart rate (FHR) patterns. CTG monitoring is in widespread use in intrapartum care for the detection of fetal hypoxia, but the clinical utility is limited by a relatively poor positive predictive value (PPV) of an abnormal CTG and significant inter and intra observer variability in CTG interpretation. Clinical risk and human factors may impact the quality of CTG interpretation. Misclassification of CTG traces may lead to both under-treatment (with the risk of fetal injury or death) or over-treatment (which may include unnecessary operative interventions that put both mother and baby at risk of complications). Machine learning (ML) has been applied to this problem since early 2000 and has shown potential to predict fetal hypoxia more accurately than visual interpretation of CTG alone. To consider how these tools might be translated for clinical practice, we conducted a review of ML techniques already applied to CTG classification and identified research gaps requiring investigation in order to progress towards clinical implementation. MATERIALS AND METHOD: We used identified keywords to search databases for relevant publications on PubMed, EMBASE and IEEE Xplore. We used Preferred Reporting Items for Systematic Review and Meta-Analysis for Scoping Reviews (PRISMA-ScR). Title, abstract and full text were screened according to the inclusion criteria. RESULTS: We included 36 studies that used signal processing and ML techniques to classify CTG. Most studies used an open-access CTG database and predominantly used fetal metabolic acidosis as the benchmark for hypoxia with varying pH levels. Various methods were used to process and extract CTG signals and several ML algorithms were used to classify CTG. We identified significant concerns over the practicality of using varying pH levels as the CTG classification benchmark. Furthermore, studies needed to be more generalised as most used the same database with a low number of subjects for an ML study. CONCLUSION: ML studies demonstrate potential in predicting fetal hypoxia from CTG. However, more diverse datasets, standardisation of hypoxia benchmarks and enhancement of algorithms and features are needed for future clinical implementation.

Construction of a comprehensive fetal monitoring database for the study of perinatal hypoxic ischemic encephalopathy.

This article describes the methods used to build a large-scale database of more than 250,000 electronic fetal monitoring (EFM) records linked to a comprehensive set of clinical information about the infant, the mother, the pregnancy, labor, and outcome. The database can be used to investigate how birth outcome is related to clinical and EFM features. The main steps involved in building the database were: (1) Acquiring the raw EFM recording and clinical records for each birth. (2) Assigning each birth to an objectively defined outcome class that included normal, acidosis, and hypoxic-ischemic encephalopathy. (3) Removing all personal health information from the EFM recordings and clinical records. (4) Preprocessing the deidentified EFM records to eliminate duplicates, reformat the signals, combine signals from different sensors, and bridge gaps to generate signals in a format that can be readily analyzed. (5) Post-processing the repaired EFM recordings to extract key features of the fetal heart rate, uterine activity, and their relations. (6) Populating a database that links the clinical information, EFM records, and EFM features to support easy querying and retrieval. •A multi-step process is required to build a comprehensive database linking electronic temporal fetal monitoring signals to a comprehensive set of clinical information about the infant, the mother, the pregnancy, labor, and outcome.•The current database documents more than 250,000 births including almost 4,000 acidosis and 400 HIE cases. This represents more than 80% of the births that occurred in 15 Northern California Kaiser Permanente Hospitals between 2011-2019. This is a valuable resource for studying the factors predictive of outcome.•The signal processing code and schemas for the database are freely available. The database will not be permitted to leave Kaiser firewalls, but a process is in place to allow interested investigators to access it.

Perinatal Outcome in Pregnant Women With Isolated Oligohydramnios Diagnosed With the Single Deepest Pocket Method.

AIM: The aim of this study was to investigate perinatal outcome in singleton pregnancies at term with isolated oligohydramnios, diagnosed by using the single deepest pocket method. PATIENTS AND METHODS: In this historic cohort study, the perinatal outcomes of 196 women with isolated oligohydramnios at term, diagnosed by using the single deepest pocket method, were compared to 8,676 women with normal amniotic fluid volume. The primary outcome measure was the Cesarean section rate. Further outcome parameters included the rate of induction of labor, abnormal cardiotocography, umbilical cord pH and base excess, Apgar, meconium-stained liquor and admission to neonatal intensive care unit. RESULTS: In the group with isolated oligohydramnios, there were significantly more Cesarean sections (p=0.0081) and more abnormal cardiotocographies (p=0.0005). Univariate and multivariate analyses showed that this difference was seen particularly in nulliparous women (p=0.0025 for Cesarean section and 0.0368 for abnormal cardiotocography). Peripartal and perinatal outcome parameters were not different between the two groups. CONCLUSION: In women with isolated oligohydramnios at term, there is no impact on fetal outcome. The influence of isolated oligohydramnios on the rate of cesarean section and abnormal cardiotocography is considered to be less than that of parity.

Large-scale analysis of interobserver agreement and reliability in cardiotocography interpretation during labor using an online tool.

BACKGROUND: While the effectiveness of cardiotocography in reducing neonatal morbidity is still debated, it remains the primary method for assessing fetal well-being during labor. Evaluating how accurately professionals interpret cardiotocography signals is essential for its effective use. The objective was to evaluate the accuracy of fetal hypoxia prediction by practitioners through the interpretation of cardiotocography signals and clinical variables during labor. MATERIAL AND METHODS: We conducted a cross-sectional online survey, involving 120 obstetric healthcare providers from several countries. One hundred cases, including fifty cases of fetal hypoxia, were randomly assigned to participants who were invited to predict the fetal outcome (binary criterion of pH with a threshold of 7.15) based on the cardiotocography signals and clinical variables. After describing the participants, we calculated (with a 95% confidence interval) the success rate, sensitivity and specificity to predict the fetal outcome for the whole population and according to pH ranges, professional groups and number of years of experience. Interobserver agreement and reliability were evaluated using the proportion of agreement and Cohen's kappa respectively. RESULTS: The overall ability to predict a pH level below 7.15 yielded a success rate of 0.58 (95% CI 0.56-0.60), a sensitivity of 0.58 (95% CI 0.56-0.60) and a specificity of 0.63 (95% CI 0.61-0.65). No significant difference in the success rates was observed with respect to profession and number of years of experience. The success rate was higher for the cases with a pH level below 7.05 (0.69) and above 7.20 (0.66) compared to those falling between 7.05 and 7.20 (0.48). The proportion of agreement between participants was good (0.82), with an overall kappa coefficient indicating substantial reliability (0.63). CONCLUSIONS: The use of an online tool enabled us to collect a large amount of data to analyze how practitioners interpret cardiotocography data during labor. Despite a good level of agreement and reliability among practitioners, the overall accuracy is poor, particularly for cases with a neonatal pH between 7.05 and 7.20. Factors such as profession and experience level do not present notable impact on the accuracy of the annotations. The implementation and use of a computerized cardiotocography analysis software has the potential to enhance the accuracy to detect fetal hypoxia, especially for ambiguous cardiotocography tracings.

Correlation between intrapartum CTG findings and interleukin-6 levels in the umbilical cord arterial blood: A prospective cohort study.

OBJECTIVE: to investigate the correlation between the intrapartum CardioTocoGraphic (CTG) findings "suggestive of fetal inflammation" ("SOFI") and the interleukin (IL)-6 level in the umbilical arterial blood. STUDY DESIGN: prospective cohort study conducted at a tertiary maternity unit and including 447 neonates born at term. METHODS: IL-6 levels were systematically measured at birth from a sample of blood taken from the umbilical artery. The intrapartum CTG traces were retrospectively reviewed by two experts who were blinded to the postnatal umbilical arterial IL-6 values as well as to the neonatal outcomes. The CTG traces were classified into "suggestive of fetal inflammation (SOFI)" and "no evidence of fetal inflammation (NEFI) according to the principles of physiologic interpretation the CTG traces. The CTG was classified as "SOFI" if there was a persistent fetal heart rate (FHR) increase > 10 % compared with the observed baseline FHR observed at the admission or at the onset of labor without any preceding repetitive decelerations. The occurrence of Composite Adverse Outcome (CAO) was defined as Neonatal Intensive Care Unit (NICU) or Special Care Baby Unit (SCBU) admission due to one or more of the following: metabolic acidaemia, Apgar score at 5 min ≤ 7, need of neonatal resuscitation, respiratory distress, tachypnoea/polypnea, jaundice requiring phototherapy, hypotension, body temperature instability, poor perinatal adaptation, suspected or confirmed early neonatal sepsis. MAIN OUTCOME MEASURES: To compare the umbilical IL-6 values between the cases with intrapartum CTG traces classified as "SOFI" and those classified as "NEFI"; to assess the correlation of umbilical IL-6 values with the neonatal outcome. RESULTS: 43 (9.6 %) CTG traces were categorized as "SOFI"; IL-6 levels were significantly higher in this group compared with the "NEFI" group (82.0[43.4-325.0] pg/ml vs. 14.5[6.8-32.6] pg/mL; p <.001). The mean FHR baseline assessed 1 h before delivery and the total labor length showed an independent and direct association with the IL-6 levels in the umbilical arterial blood (p <.001 and p = 0.005, respectively). CAO occurred in 33(7.4 %) cases; IL-6 yielded a good prediction of the occurrence of the CAO with an AUC of 0.72 (95 % CI 0.61-0.81). CONCLUSION: Intrapartum CTG findings classified as "SOFI" are associated with higher levels of IL-6 in the umbilical arterial blood.

AI-driven decision support systems and epistemic reliance: a qualitative study on obstetricians' and midwives' perspectives on integrating AI-driven CTG into clinical decision making.

BACKGROUND: Given that AI-driven decision support systems (AI-DSS) are intended to assist in medical decision making, it is essential that clinicians are willing to incorporate AI-DSS into their practice. This study takes as a case study the use of AI-driven cardiotography (CTG), a type of AI-DSS, in the context of intrapartum care. Focusing on the perspectives of obstetricians and midwives regarding the ethical and trust-related issues of incorporating AI-driven tools in their practice, this paper explores the conditions that AI-driven CTG must fulfill for clinicians to feel justified in incorporating this assistive technology into their decision-making processes regarding interventions in labor. METHODS: This study is based on semi-structured interviews conducted online with eight obstetricians and five midwives based in England. Participants were asked about their current decision-making processes about when to intervene in labor, how AI-driven CTG might enhance or disrupt this process, and what it would take for them to trust this kind of technology. Interviews were transcribed verbatim and analyzed with thematic analysis. NVivo software was used to organize thematic codes that recurred in interviews to identify the issues that mattered most to participants. Topics and themes that were repeated across interviews were identified to form the basis of the analysis and conclusions of this paper. RESULTS: There were four major themes that emerged from our interviews with obstetricians and midwives regarding the conditions that AI-driven CTG must fulfill: (1) the importance of accurate and efficient risk assessments; (2) the capacity for personalization and individualized medicine; (3) the lack of significance regarding the type of institution that develops technology; and (4) the need for transparency in the development process. CONCLUSIONS: Accuracy, efficiency, personalization abilities, transparency, and clear evidence that it can improve outcomes are conditions that clinicians deem necessary for AI-DSS to meet in order to be considered reliable and therefore worthy of being incorporated into the decision-making process. Importantly, healthcare professionals considered themselves as the epistemic authorities in the clinical context and the bearers of responsibility for delivering appropriate care. Therefore, what mattered to them was being able to evaluate the reliability of AI-DSS on their own terms, and have confidence in implementing them in their practice.

Impact of an e-learning training for interpreting intrapartum fetal heart rate monitoring to avoid perinatal asphyxia: A before-after multicenter observational study.

INTRODUCTION: Perinatal asphyxia, a condition that results from compromised placental or pulmonary gas exchange during the birth process, is rare but can lead to serious neonatal and long-term consequences. The visual analysis of cardiotocography (CTG) is designed to avoid perinatal asphyxia, but its interpretation can be difficult. Our aim was to test the impact of an e-learning training program for interpreting CTG on the rate of avoidable perinatal asphyxia at term. METHOD: We conducted a retrospective multicenter before-after study comparing two periods, before and after the implementation of e-learning training program from July 1, 2016 to December 31, 2016, in CTG interpretation for midwives and obstetricians in five maternity hospitals in the Paris area, France. The training involved theoretical aspects such as fetal physiology and heart rhythm abnormalities, followed by practical exercises using real case studies to enhance skills in interpreting CTG. We included all term births that occurred between the "before" period (July 1 to December 31, 2014) and the "after period (January 1 to June 30, 2017). We excluded multiple pregnancies, antenatal detection of congenital abnormalities, breech births and all scheduled caesarean sections. Perinatal asphyxia cases were analyzed by a pair of experts consisting of midwives and obstetricians, and avoidability of perinatal asphyxia was estimated. The main criterion was the prevalence of avoidable perinatal asphyxia. RESULTS: The e-learning program was performed by 83 % of the obstetrician-gynecologists and 65 % of the midwives working in the delivery rooms of the five centers. The prevalence of perinatal asphyxia was 0.45 % (29/7902 births) before the training and 0.54 % (35/7722) after. The rate of perinatal asphyxia rated as avoidable was 0.30 % of live births before the training and 0.28 % after (p = 0.870). The main causes of perinatal asphyxia deemed avoidable were delay in reactions to severe CTG anomalies and errors in the analysis and interpretation of the CTG. These causes did not differ between the two periods. CONCLUSION: One session of e-learning training to analyze CTG was not associated with a reduction in avoidable perinatal asphyxia. Other types of e-learning, repeated and implemented over a longer period should be evaluated.

Hybrid-FHR: a multi-modal AI approach for automated fetal acidosis diagnosis.

BACKGROUND: In clinical medicine, fetal heart rate (FHR) monitoring using cardiotocography (CTG) is one of the most commonly used methods for assessing fetal acidosis. However, as the visual interpretation of CTG depends on the subjective judgment of the clinician, this has led to high inter-observer and intra-observer variability, making it necessary to introduce automated diagnostic techniques. METHODS: In this study, we propose a computer-aided diagnostic algorithm (Hybrid-FHR) for fetal acidosis to assist physicians in making objective decisions and taking timely interventions. Hybrid-FHR uses multi-modal features, including one-dimensional FHR signals and three types of expert features designed based on prior knowledge (morphological time domain, frequency domain, and nonlinear). To extract the spatiotemporal feature representation of one-dimensional FHR signals, we designed a multi-scale squeeze and excitation temporal convolutional network (SE-TCN) backbone model based on dilated causal convolution, which can effectively capture the long-term dependence of FHR signals by expanding the receptive field of each layer's convolution kernel while maintaining a relatively small parameter size. In addition, we proposed a cross-modal feature fusion (CMFF) method that uses multi-head attention mechanisms to explore the relationships between different modalities, obtaining more informative feature representations and improving diagnostic accuracy. RESULTS: Our ablation experiments show that the Hybrid-FHR outperforms traditional previous methods, with average accuracy, specificity, sensitivity, precision, and F1 score of 96.8, 97.5, 96, 97.5, and 96.7%, respectively. CONCLUSIONS: Our algorithm enables automated CTG analysis, assisting healthcare professionals in the early identification of fetal acidosis and the prompt implementation of interventions.

Introducing Artificial Intelligence in Interpretation of Foetal Cardiotocography: Medical Dataset Curation and Preliminary Coding-An Interdisciplinary Project.

Artificial intelligence (AI) is gaining increasing interest in the field of medicine because of its capacity to process big data and pattern recognition. Cardiotocography (CTG) is widely used for the assessment of foetal well-being and uterine contractions during pregnancy and labour. It is characterised by inter- and intraobserver variability in interpretation, which depends on the observers' experience. Artificial intelligence (AI)-assisted interpretation could improve its quality and, thus, intrapartal care. Cardiotocography (CTG) raw signals from labouring women were extracted from the database at the University Hospital of Bern between 2006 and 2019. Later, they were matched with the corresponding foetal outcomes, namely arterial umbilical cord pH and 5-min APGAR score. Excluded were deliveries where data were incomplete, as well as multiple births. Clinical data were grouped regarding foetal pH and APGAR score at 5 min after delivery. Physiological foetal pH was defined as 7.15 and above, and a 5-min APGAR score was considered physiologic when reaching ≥7. With these groups, the algorithm was trained to predict foetal hypoxia. Raw data from 19,399 CTG recordings could be exported. This was accomplished by manually searching the patient's identification numbers (PIDs) and extracting the corresponding raw data from each episode. For some patients, only one episode per pregnancy could be found, whereas for others, up to ten episodes were available. Initially, 3400 corresponding clinical outcomes were found for the 19,399 CTGs (17.52%). Due to the small size, this dataset was rejected, and a new search strategy was elaborated. After further matching and curation, 6141 (31.65%) paired data samples could be extracted (cardiotocography raw data and corresponding maternal and foetal outcomes). Of these, half will be used to train artificial intelligence (AI) algorithms, whereas the other half will be used for analysis of efficacy. Complete data could only be found for one-third of the available population. Yet, to our knowledge, this is the most exhaustive and second-largest cardiotocography database worldwide, which can be used for computer analysis and programming. A further enrichment of the database is planned.