Search Results (213)

Prenatal maternal stress alters maternal–fetal heart rate coupling, as demonstrated by the Fetal Stress Index derived from bivariate phase-rectified signal averaging. Here, we extend this framework using information-theoretical measures to elucidate underlying mechanisms. In 118 third-trimester pregnancies (59 stressed, 59 control), we computed entropy rate (ER), sample entropy (SE) and transfer entropy (TE) under multiple conditioning paradigms, employing mixed linear models for repeated measures. We identified dual coupling mechanisms at the short-term (0.5–2.5 s), but not long-term (2.5–5 s) time scales: (1) stress-invariant state-dependent synchronization, with maternal decelerations exerting approximately 60% coupling strength on fetal heart rate complexity—a fundamental coordination conserved across demographics; and (2) stress-sensitive temporal information transfer (TE), showing exploratory associations with maternal cortisol that require replication. A robust sex-by-stress interaction emerged in TE from mixed models, with exploratory female-specific coupling patterns absent in males. Universal acceleration predominance was observed in both maternal and fetal heart rates, stronger in fetuses and independent of sex or stress. We provide insight into the dependence of these findings on the sampling rate of the underlying data, identifying 4 Hz, commonly used for ultrasound-derived fetal heart rate recordings, as a sufficient sampling rate to capture the information flow. Information-theoretical analysis reveals that maternal–fetal coupling operates through complementary pathways with differential stress sensitivity, extending the Fetal Stress Index by elucidating causal foundations. Future studies should explore additional information-theoretical conditional approaches to resolve stress-specific and time-scale-specific differences in information flow. Full article

Objective: The fetal-to-neonatal transition is marked by profound cardio-respiratory changes. Infections emerging within the first 48 h after birth may influence early cardiovascular adaptation. We aimed to evaluate the association between early infection/inflammation markers and vital parameters in neonates during the first 15 min after birth. Methods: This is a secondary outcome parameter post-hoc analysis of data derived from a prospective observation study. Preterm and term neonates with cerebral oxygen saturation (crSO2) monitoring (INVOS 5100C) during the first 15 min after birth and available inflammatory markers (C-reactive protein [CRP], leukocytes, immature-to-total neutrophils ratio [IT ratio]) within 48 h after birth were included. Heart rate (HR) and arterial oxygen saturation (SpO₂) were continuously recorded during the first 15 min. Inflammatory markers obtained at 16–24 and 24–48 h after birth were correlated with crSO₂, SpO₂, and HR at minute 5, 10 and 15. Results: Sixty-eight neonates were included (median (IQR) gestational age 34.0 (32.0; 35.9) weeks, birth weight 1900 (1488; 2542) grams). CRP within the first 24 h correlated negatively with crSO₂ (r = −0.314; p = 0.011) and with SpO₂ (r = −0.393; p = 0.001) at minute 15. IT ratio within 24 h correlated negatively with crSO₂ at minute 5 (r = −0.367; p = 0.005), 10 (r = −0.273; p = 0.035), and 15 (r = −0.306; p = 0.013), and with SpO₂ at minute 5 (r = −0.327; p = 0.008). IT ratio at 24–48 h correlated negatively with crSO₂ at minute 15 (r = −0.384, p = 0.012). No significant correlations were observed with HR. Leukocytes within the first 24 h after birth correlated negatively with crSO2 at minute 5 (r = −0.265; p = 0.046). Conclusions: Early inflammatory markers, particularly CRP and the IT ratio, are associated with cerebral and systemic oxygenation during immediate postnatal transition. These findings suggest a potential association between early inflammatory activation and oxygenation dynamics; however, given the observational design and modest correlation strength, the results should be interpreted cautiously and do not allow conclusions regarding causality or underlying mechanisms. Full article

Accurate assessment of hypoxia-related fetal risk during labour is essential for improving perinatal outcomes while avoiding unnecessary operative interventions. Although deep learning has shown promise for automated fetal risk assessment, most existing approaches rely on cardiotocography (CTG) alone; CTG interpretation is known to suffer from a high false-positive rate and may not fully reflect fetal status without complementary clinical context. To address this limitation, we propose MIRF-Net, a multimodal intrapartum fetal risk assessment framework that jointly models (i) CTG time-series signals, (ii) Gramian Angular Difference Field (GADF) images that encode global correlation structure of fetal heart rate, and (iii) structured maternal metadata. MIRF-Net combines a PatchTST encoder for CTG, a pretrained ResNet101 for GADF images, and an autoencoder for maternal metadata and then performs cross-modal interaction learning with a fusion Transformer for final risk prediction. Using 552 eligible CTG recordings from the public CTU-UHB intrapartum database, which were split into training, validation, and test sets at a ratio of 6:2:2, MIRF-Net outperforms representative baselines on the test set, achieving a quality index (QI) of 74.76%, AUC of 0.7413, and Brier score of 0.2537, indicating improved discrimination and better-calibrated risk probabilities. Ablation studies further confirm the complementary contributions of each modality and show that Transformer-based fusion yields the most consistent overall gains. These results suggest that MIRF-Net provides reliable decision support for intelligent intrapartum monitoring. Full article

Background/Objectives: In Japan, hospital births predominate, with home births comprising only 0.1% of deliveries. This study assessed how documented practices for planned home births attended by independent midwives align with national guidelines and WHO intrapartum care recommendations, and assess maternal and neonatal differences before and after the COVID-19 pandemic. Methods: Records of 430 low-risk pregnant women who received continuous care at a private midwifery home over 25 years were reviewed. After excluding 8 maternal and 22 neonatal transfers, 400 records were analyzed. Descriptive statistics were compared with WHO recommendations and between the pre-pandemic (1999–2019) and post-pandemic (2020–2024) periods. Results: All women experienced spontaneous singleton cephalic labors with intermittent fetal heart rate auscultation. The mean gestational age was 277.3 days and the median labor duration was 303.5 min. Labor onset was spontaneous in 83.5% of cases. Nearly half of the women had no perineal lacerations. Postpartum blood loss ≥500 mL occurred in 14.1% of cases. Family presence was nearly universal. Neonates had a mean birth weight of 3129.0 g and high Apgar scores. Skin-to-skin contact occurred in 52.9%; exclusive breastfeeding reached 93.8% at 1 month. Post-pandemic births showed higher maternal age and higher neonatal birth weight, although these differences should be interpreted cautiously due to the small post-pandemic sample. Conclusions: Independent midwives provided evidence-based, physiologically oriented care, partially aligning with selected WHO intrapartum recommendations during planned home births. Midwife-led home births may support positive childbirth experiences and favorable maternal/neonatal outcomes for low-risk women. Post-pandemic shifts underscore the need for continued monitoring and flexible, community-based perinatal support, while recognizing the limitations of retrospective, single-site data. Full article

Background/Objectives: This study assesses the genetic basis of fetal congenital heart disease (CHD), which exhibits a complex etiology, by using chromosomal microarray analysis (CMA); it also elucidates perinatal outcomes and postnatal development to support prenatal diagnosis and genetic counseling. Methods: Pregnant women (n = 1195) who were diagnosed with fetal CHD based on echocardiography were selected along with those having an interventional prenatal diagnosis, all of whom underwent CMA. Depending on the gestational age, amniotic fluid or umbilical cord blood samples were collected. Patients were included if they were diagnosed with fetal CHD based on echocardiography. Those who could not consent to amniocentesis or umbilical vein puncture or who had contraindications for amniocentesis or umbilical vein puncture were excluded. Patients were studied until May 2025. Results: Of the 1195 fetuses with CHD, 140 had pathogenic copy number variation (pCNV). The pCNV detection rate in cases with a single CHD was 3.17%, whereas it was 13.51% in the group with multiple CHDs. The detection rate for pCNVs in patients with extracardiac abnormalities was 28.62%. The fetal and postnatal mortality rates were highest for fetuses with multiple CHDs. The survival rate was highest for fetuses with a single CHD. Early detection of CHD and timely genetic testing can inform clinical management of CHD-affected pregnancies; however, larger prospective studies are needed to establish their impact on perinatal outcomes. Conclusions: CMA provides valuable information for genetic counselling, as it identifies pathogenic variants associated with CHD. However, prognostic predictions should consider multiple clinical factors. Full article

Over the years, the impact of music on the prenatal and neonatal stages of human life has gained significant scientific attention. This study provides a comprehensive bibliometric review of research investigating how music influences fetal and newborn development. Using the Scopus and Web of Science databases, a search of relevant studies published in English between January 2006 and July 2025 was conducted, whose basic criterion was the use of the following keywords: “music” and “fetus” or “fetal”. Additional terms such as “fetus development”, “fetus heart rate”, “fetus movement”, “mother–fetus relationship”, “newborn”, etc., were also utilized. In result, 75 publications were selected, and their bibliographic data and full sources were retrieved. The included studies were grouped according to two perspectives that consider the impact of music (1) on the development of the fetus and the newborn, and (2) on maternal health and mother–fetus bonding. Using VOSviewer, bibliometric mapping was performed, which allowed to obtain keyword co-occurrence network and co-authorship network. The chosen literature was then quantitatively and qualitatively analyzed. The analysis revealed a sharp upward trend in publications starting in 2015, with a temporary decline in 2020 due to the COVID-19 pandemic. The highest number of publications were from Iran. The most investigated topics were related to the fetus heart and maternal health. The most common publication type and research methodology were, respectively, article and experiment. While the key authors Lordier, L., Filippa, M., Grandjean, D., and Monaci, M.G. lead the field, the co-authorship network remains fragmented into isolated and relatively small research groups. The Journal of Maternal–Fetal and Neonatal Medicine emerged as the leading publication outlet, while the study by Graven et al. entitled “Auditory Development in the Fetus and Infant” remains the most cited work. The keyword co-occurrence network allowed the identification of three main thematic clusters indicating the physiological, clinical, and therapeutic aspects of the impact of music on fetal and neonatal development. A qualitative analysis revealed that music plays a vital role in early human development and maternal well-being, demonstrating positive effects of auditory stimuli on fetal and newborn physiology, as well as on the mother–fetus relationship, while being a non-invasive and non-pharmacological method of intervention. However, the lack of a fully connected global research community and standardized protocols for, e.g., choosing the musical repertoire, sound administration, and the duration of exposure suggests the need for increased international collaboration to further integrate music therapy into standard clinical practices for prenatal and neonatal care. Full article

Fetal cardiotocography (CTG) is widely used to assess fetal health during labor and to screen for fetal acidosis. However, CTG interpretation relies heavily on clinicians’ experience and is affected by subjectivity and inconsistency, which limit diagnostic reliability. Most existing artificial intelligence approaches simplify fetal acid–base assessment into a binary classification, making it difficult to distinguish acidosis severity and restricting information for refined clinical decision-making. To address these limitations, this study formulates a three-class classification task—normal, moderate acidosis, and severe acidosis—based on the CTU-CHB dataset, using umbilical artery blood pH as the reference standard. A signal-first, conditionally enhanced, three-phase training and meta-feature fusion framework is proposed. In stage A, a CNN-BiLSTM-attention network performs end-to-end modeling of fetal heart rate signals, while a recall feedback-driven dynamic weighted loss alleviates class imbalance and identifies difficult samples. Stage B incorporates relevant clinical detection information for these difficult samples and applies multimodal feature fusion to enhance discrimination. Stage C constructs meta-features from the outputs of the first two stages to adaptively fuse classification preferences and uncertainty. Experimental results demonstrate that the proposed framework achieves an accuracy of 82.80 ± 2.82% and an F1 score of 78.84 ± 2.96%, effectively mitigating class imbalance and difficult sample classification, and providing reliable support for clinical decision-making in fetal acidosis. Full article

Fetal heart rate (FHR) monitoring is ubiquitous in antenatal care, yet human visual interpretation poorly predicts adverse pregnancy outcomes. Meanwhile, preterm gestations carry a high burden of stillbirth and severe fetal compromise, where earlier identification of high-risk pregnancies may justify iatrogenic preterm delivery to prevent avoidable fetal death. We analyzed 4867 antepartum FHR recordings from pre-term pregnancies meeting at least one of ten adverse outcome criteria alongside 4014 term uncomplicated controls. Seven clinically validated FHR features were extracted from each trace, and six machine-learning classifiers were trained on 80% of the data (7105 samples) using k-fold cross-validation; the remaining 20% (1776 samples) formed an internal validation cohort. The random forest demonstrated the best performance, achieving an area under the receiver-operating characteristic curve (AUC) of 0.88 (95% confidence interval [CI] 0.87–0.88) during training and 0.88 (95% CI 0.86–0.90) on validation, with good calibration (Brier score 0.14). Median AUC across individual adverse outcomes was 0.85 (interquartile range [IQR] 0.81–0.89) and exceeded 0.80 at all gestational ages assessed; sensitivity and specificity at the Youden threshold were 76.2% and 87.5%, respectively. Decision-curve analysis demonstrated net benefit across a range of clinically relevant probability thresholds. These findings indicate that data-driven interpretation of antepartum FHR can stratify risk in pre-term pregnancies with high accuracy and may support earlier, evidence-based clinical decision-making, particularly in resource-limited settings where specialist expertise is limited. Full article

Congenital heart disease (CHD) is the most common congenital anomaly worldwide and poses significant diagnostic challenges due to its structural complexity and frequent association with extracardiac anomalies and genetic abnormalities. While conventional tests such as karyotyping, quantitative fluorescent polymerase chain reaction (QF-PCR), and chromosomal microarray analysis (CMA) are standard first-tier investigations, many cases remain genetically unexplained. Prenatal whole exome sequencing (WES) has emerged as a valuable tool to detect pathogenic single gene variants underlying CHD. This narrative review synthesizes findings from 28 studies involving over 2000 WES-tested fetuses and more than 10,000 CHD cases. The additional diagnostic yield of WES over CMA ranged from 8.0% to 66.7%, with higher yields in syndromic or non-isolated CHD (10–50%) compared to isolated cases (7.1–27.8%). Trio-based WES outperformed proband-only sequencing by improving accuracy, reducing turnaround time, and lowering the rate of variant of uncertain significance (VUS). Prenatal WES not only clarifies genetic etiology but also reveals syndromic diagnoses, allowing CHD to be interpreted within broader multisystem contexts. Integration of phenotypic and genomic data enhances prenatal counseling, prognostication, delivery planning, and postnatal care—advancing precision medicine in fetal cardiology. Full article

Background/Objectives: Fetal health is essential in prenatal care, influencing both maternal and fetal outcomes. Cardiotocography (CTG) monitors uterine contractions and fetal heart rate, yet manual interpretation exhibits significant inter-examiner variability. Machine learning offers automated alternatives; however, class imbalance in CTG datasets where pathological cases constitute less than 10% leads to poor detection of minority classes. This study aims to provide the first systematic benchmark comparing five resampling strategies across seven classifier families for multi-class CTG classification, evaluated using imbalance-aware metrics rather than overall accuracy alone. Methods: Seven machine learning models were employed: Naïve Bayes (NB), Random Forest (RF), Linear Discriminant Analysis (LDA), k-Nearest Neighbors (KNN), Linear Support Vector Machine (SVM), Multinomial Logistic Regression (MLR), and Multi-Layer Perceptron (MLP). To address class imbalance, we evaluated the original unbalanced dataset (base) and five resampling methods: SMOTE, BSMOTE, ADASYN, NearMiss, and SCUT. Performance was evaluated on a held-out test set using Balanced Accuracy (BACC), Macro-F1, the Macro-Matthews Correlation Coefficient (Macro-MCC), and Macro-Averaged ROC-AUC. We also report per-class ROC curves. Results: Among all models, RF proved most reliable. Training on the original distribution (base) yielded the highest BACC (0.9118), whereas RF combined with BSMOTE provided the strongest class-balanced performance (Macro-MCC = 0.8533, Macro-F1 = 0.9073) with a near-perfect ROC-AUC (approximately 0.986–0.989). Overall, resampling effects proved model dependent. While some classifiers achieved optimal performance on the natural class distribution, oversampling techniques, particularly SMOTE and BSMOTE, demonstrated significant improvements in minority class discrimination and class-balanced metrics across multiple model families. Notably, certain models benefited substantially from resampling, exhibiting enhanced Macro-F1, BACC, and minority class recall without sacrificing overall accuracy. Conclusions: These findings establish robust, model-agnostic baselines for CTG-based fetal health screening. They highlight that strategic oversampling can translate improved minority class discrimination into clinically meaningful performance gains, supporting deployment in cost-sensitive and threshold-aware clinical settings. Full article

Fetal acidemia, caused by impaired gas exchange between the fetus and the mother, is a leading cause of stillbirth and neurologic complications. Early prediction is therefore essential to guide timely clinical intervention. Several strategies rely on cardiotocography (CTG), which combines fetal heart rate (fHR) with uterine contractions and has led to development of clinical guidelines for CTG interpretation and the introduction of different fHR features. Additionally, ST event analysis, investigating changes in the ST segments of the fetal electrocardiogram (fECG), has been proposed as a complementary tool. This narrative review adopts a systematic approach, with comprehensive searches in Embase and PubMed to ensure full coverage of the available literature, and summarizes findings from 30 studies. Clinical guidelines for CTG interpretation frequently lead to intermediate risk level annotations, leaving the final decision regarding fetal management to clinical experience. In contrast, various fHR features can successfully discriminate between fetuses developing acidemia and healthy controls. Evidence regarding the added value of ST events derived from the scalp electrode remains conflicting, due to concerns about invasiveness. Recent studies on machine learning models highlight their ability to integrate multiple fHR features and improve predictive performance, suggesting a promising direction for enhancing acidemia prediction during labor. Full article

Background/Objectives: Pre-hospital delivery is an unpredictable event posing significant challenges for Emergency Medical Services (EMS) teams. Despite advances in perinatal care, emergency deliveries outside the hospital environment remain associated with increased maternal and neonatal risks. This study aimed to identify predictors of out-of-hospital delivery in EMS-attended labor cases and determinants of neonatal condition immediately after delivery. Methods: We conducted a retrospective analysis of 5097 EMS records of laboring women in Poland from August 2021 to January 2022, of which 2927 were included in the final study sample. Multivariate logistic regression models with multiple imputation for missing data were used to identify predictors of pre-hospital delivery and adverse neonatal condition (Apgar ≤ 7) in EMS-managed childbirths. Results: Pre-hospital delivery was strongly associated with second-stage labor (OR ≈ 535; p < 0.0001), ruptured membranes (OR ≈ 8.7; p < 0.0001), and fewer previous pregnancies (OR = 0.86; p = 0.018), and showed a trend with higher maternal heart rate (OR = 1.015; p = 0.083). Neonatal status classified as Apgar ≤ 7 was significantly associated with preterm birth (p < 0.0001), absence of fetal movements (OR ≈ 26.4; p = 0.025), and complications during pregnancy (p = 0.036). Complications during labor and lack of prenatal care were not significantly associated with increased risk of pre-hospital delivery in the model. Conclusions: Rupture of membranes, second-stage labor, and fewer previous pregnancies are significant predictors of pre-hospital delivery in EMS-managed cases. Absence of fetal movements and preterm gestation predict worse neonatal outcomes (Apgar ≤ 7). Early identification of these factors may enhance prehospital perinatal care and improve maternal and neonatal prognosis. Full article

Background/Objectives: Antepartum computerized cardiotocography (cCTG) represents an essential tool for assessing fetal well-being. This study aimed to comparatively evaluate antepartum cCTG-derived indices across high-risk pregnancies to identify distinctive fetal autonomic and reactivity profiles. Methods: A comparative analysis of antepartum cCTG parameters was conducted. The cohort included pregnancies beyond 28 weeks of pregnancy, 169 cases of hypertensive disorders of pregnancy (HDP), 146 of gestational diabetes mellitus (GDM), 86 of intrahepatic cholestasis (ICP), and 87 low-risk pregnancies as controls. Results: Baseline FHR remained within the physiological range across all groups (110–160 bpm; p > 0.05). Dynamic cCTG parameters exhibited clear pathology-dependent alterations. Short-term variability (STV) showed a stepwise decline from controls to ICP and GDM, reaching its lowest values in HDP (mean 1.08 bpm; p < 0.00001), accompanied by an increased proportion of epochs with STV < 1 bpm. Long-term variability suppression (LTV < 5 bpm) was significantly higher in GDM and HDP (p = 0.0077). Acceleration frequency decreased across all pathological groups, with the most pronounced reduction observed in HDP, whereas fetal movements were paradoxically elevated in both GDM and HDP. Total decelerations were more frequent in ICP and HDP; however, repetitive, late, prolonged, and >5 min decelerations remained rare and did not differ significantly between groups. Conclusions: HDP showed the most unfavorable cCTG profiles, consistent with impaired fetal autonomic regulation and chronic subclinical hypoxemia. GDM and ICP had moderate changes, suggesting milder adaptive responses. These findings emphasize the value of quantitative cCTG in differentiating fetal autonomic patterns in high-risk pregnancies and the importance of tailored surveillance strategies. Full article

Total anomalous pulmonary venous connection (TAPVC) is one of the most severe congenital heart defects; however, prenatal diagnosis remains suboptimal. A normal fetal heart has a junction between the pulmonary venous (PV) and left atrium (LA). In contrast, no junctions are observed in patients with TAPVC. In the present study, we attempted to visualize and detect fetal PV-LA connections using artificial intelligence (AI) trained on the fetal cardiac ultrasound videos of 100 normal cases and six TAPVC cases. The PV-LA aggregate area was segmented using the following three-dimensional (3D) segmentation models: SegResNet, Swin UNETR, MedNeXt, and SegFormer3D. The Dice coefficient and 95% Hausdorff distance were used to evaluate segmentation performance. The mean values of the shortest PV-LA distance (PLD) and major axis angle (PLA) in each video were calculated. These methods demonstrated sufficient performance in visualizing and detecting the PV-LA connection. In terms of TAPVC screening performance, MedNeXt-PLD and SegResNet-PLA achieved mean area under the receiver operating characteristic curve values of 0.844 and 0.840, respectively. Overall, this study shows that our approach can support unskilled examiners in capturing the PV-LA connection and has the potential to improve the prenatal detection rate of TAPVC. Full article

Spontaneous hemoperitoneum in pregnancy is rare, and rupture of a superficial uterine fundal vein in an unscarred uterus is exceptionally uncommon. A 37-year-old woman at 27 + 0 weeks presented with left upper quadrant abdominal pain, and imaging revealed a localized hematoma adjacent to the left uterine fundus without active bleeding. During conservative management, she developed sudden severe pain with fetal heart rate decelerations at 27 + 6 weeks, prompting emergency cesarean delivery. Intraoperative findings showed approximately 2400 mL of hemoperitoneum caused by rupture of a superficial fundal vein, with the uterus otherwise intact, and bleeding was controlled with a fibrin sealant patch. Maternal recovery and neonatal outcome were favorable. This case underscores that rupture of superficial uterine veins should be considered in pregnant patients presenting with unexplained hemoperitoneum during pregnancy. Full article