Obstetrics and Gynaecology - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 18
-
ItemNo Preview AvailableThe Effect of Fetal Heart Rate Segment Selection on Deep Learning Models for Fetal Compromise Detection(Institute of Electrical and Electronics Engineers, 2023)Monitoring the fetal heart rate (FHR) is common practice in obstetric care to assess the risk of fetal compromise. Unfortunately, human interpretation of FHR recordings is subject to inter-observer variability with high false positive rates. To improve the performance of fetal compromise detection, deep learning methods have been proposed to automatically interpret FHR recordings. However, existing deep learning methods typically analyse a fixed-length segment of the FHR recording after removing signal gaps, where the influence of this segment selection process has not been comprehensively assessed. In this work, we develop a novel input length invariant deep learning model to determine the effect of FHR segment selection for detecting fetal compromise. Using this model, we perform five times repeated five-fold cross-validation on an open-access database of 552 FHR recordings and assess model performance for FHR segment lengths between 15 and 60 minutes. We show that the performance after removing signal gaps improves with increasing segment length from 15 minutes (AUC = 0.50) to 60 minutes (AUC = 0.74). Additionally, we demonstrate that using FHR segments without removing signal gaps achieves superior performance across signal lengths from 15 minutes (AUC = 0.68) to 60 minutes (AUC = 0.76). These results show that future works should carefully consider FHR segment selection and that removing signal gaps might contribute to the loss of valuable information.
-
ItemNo Preview AvailableComputerised Cardiotocography Analysis for the Automated Detection of Fetal Compromise during Labour: A Review(MDPI, 2023-09)The measurement and analysis of fetal heart rate (FHR) and uterine contraction (UC) patterns, known as cardiotocography (CTG), is a key technology for detecting fetal compromise during labour. This technology is commonly used by clinicians to make decisions on the mode of delivery to minimise adverse outcomes. A range of computerised CTG analysis techniques have been proposed to overcome the limitations of manual clinician interpretation. While these automated techniques can potentially improve patient outcomes, their adoption into clinical practice remains limited. This review provides an overview of current FHR and UC monitoring technologies, public and private CTG datasets, pre-processing steps, and classification algorithms used in automated approaches for fetal compromise detection. It aims to highlight challenges inhibiting the translation of automated CTG analysis methods from research to clinical application and provide recommendations to overcome them.
-
ItemNo Preview AvailablePlasma lipids are dysregulated preceding diagnosis of preeclampsia or delivery of a growth restricted infant(ELSEVIER, 2023-08)BACKGROUND: Lipids serve as multifunctional metabolites that have important implications for the pregnant mother and developing fetus. Abnormalities in lipids have emerged as potential risk factors for pregnancy diseases, such as preeclampsia and fetal growth restriction. The aim of this study was to assess the potential of lipid metabolites for detection of late-onset preeclampsia and fetal growth restriction. METHODS: We used a case-cohort of 144 maternal plasma samples at 36 weeks' gestation from patients before the diagnosis of late-onset preeclampsia (n = 22), delivery of a fetal growth restricted infant (n = 55, defined as <5th birthweight centile), gestation-matched controls (n = 72). We performed liquid chromatography-tandem mass spectrometry (LC-QQQ) -based targeted lipidomics to identify 421 lipids, and fitted logistic regression models for each lipid, correcting for maternal age, BMI, smoking, and gestational diabetes. FINDINGS: Phosphatidylinositol 32:1 (AUC = 0.81) and cholesterol ester 17:1 (AUC = 0.71) best predicted the risk of developing preeclampsia or delivering a fetal growth restricted infant, respectively. Five times repeated five-fold cross validation demonstrated the lipids alone did not out-perform existing protein biomarkers, soluble tyrosine kinase-1 (sFlt-1) and placental growth factor (PlGF) for the prediction of preeclampsia or fetal growth restriction. However, lipids combined with sFlt-1 and PlGF measurements improved disease prediction. INTERPRETATION: This study successfully identified 421 lipids in maternal plasma collected at 36 weeks' gestation from participants who later developed preeclampsia or delivered a fetal growth restricted infant. Our results suggest the predictive capacity of lipid measurements for gestational disorders holds the potential to improve non-invasive assessment of maternal and fetal health. FUNDING: This study was funded by a grant from National Health and Medical Research Council.
-
ItemNo Preview AvailableCirculating Chemerin Is Elevated in Women With Preeclampsia(ENDOCRINE SOC, 2023-03-13)BACKGROUND: Preeclampsia is a severe complication of pregnancy. Chemerin is an adipokine secreted from adipose tissue and highly expressed in placenta. This study evaluated the biomarker potential of circulating chemerin to predict preeclampsia. METHODS: Maternal plasma and placenta were collected from women with early-onset preeclampsia (<34 weeks), with preeclampsia and eclampsia, or before preeclampsia diagnosis (36 weeks). Human trophoblast stem cells were differentiated into syncytiotrophoblast or extravillous trophoblasts across 96 hours. Cells were cultured in 1% O2 (hypoxia) or 5% O2 (normoxia). Chemerin was measured by enzyme-linked immunosorbent assay (ELISA) and RARRES2 (gene coding chemerin) by reverse transcription-quantitative polymerase chain reaction. RESULTS: Circulating chemerin was increased in 46 women with early-onset preeclampsia (<34 weeks) compared to 17 controls (P < .0006). Chemerin was increased in placenta from 43 women with early-onset preeclampsia compared to 24 controls (P < .0001). RARRES2 was reduced in placenta from 43 women with early-onset preeclampsia vs 24 controls (P < .0001). Chemerin was increased in plasma from 26 women with established preeclampsia (P = .006), vs 15 controls. Circulating chemerin was increased in 23 women who later developed preeclampsia vs 182 who did not (P = 3.23 × 10-6). RARRES2 was reduced in syncytiotrophoblast (P = .005) or extravillous trophoblasts (P < .0001). Hypoxia increased RARRES2 expression in syncytiotrophoblast (P = .01) but not cytotrophoblast cells. CONCLUSIONS: Circulating chemerin was elevated in women with early-onset preeclampsia, established preeclampsia, and preceding preeclampsia diagnosis of preeclampsia. RARRES2 was dysregulated in placenta complicated by preeclampsia and may be regulated through hypoxia. Chemerin may have potential as a biomarker for preeclampsia but would need to be combined with other biomarkers.
-
ItemDetection of fetal arrhythmias in non-invasive fetal ECG recordings using data-driven entropy profiling(IOP Publishing Ltd, 2022-02-28)Objective.Fetal arrhythmias are a life-threatening disorder occurring in up to 2% of pregnancies. If identified, many fetal arrhythmias can be effectively treated using anti-arrhythmic therapies. In this paper, we present a novel method of detecting fetal arrhythmias in short length non-invasive fetal electrocardiography (NI-FECG) recordings.Approach.Our method consists of extracting a fetal heart rate time series from each NI-FECG recording and computing an entropy profile using a data-driven range of the entropy tolerance parameterr. To validate our approach, we apply our entropy profiling method to a large clinical data set of 318 NI-FECG recordings.Main Results.We demonstrate that our method (TotalSampEn) provides strong performance for classifying arrhythmic fetuses (AUC of 0.83) and outperforms entropy measures such asSampEn(AUC of 0.68) andFuzzyEn(AUC of 0.72). We also find that NI-FECG recordings incorrectly classified using the investigated entropy measures have significantly lower signal quality, and that excluding recordings of low signal quality (13.5% of recordings) increases the classification performance ofTotalSampEn(AUC of 0.90).Significance.The superior performance of our approach enables automated detection of fetal arrhythmias and warrants further investigation in a prospective clinical trial.
-
ItemNo Preview AvailableManagement of late preterm preeclampsia: a comparison of maternal and fetal indications for delivery(TAYLOR & FRANCIS LTD, 2022-01-01)OBJECTIVE: To investigate delivery indications for women with late preterm preeclampsia and evaluate whether disease characteristics at presentation are predictive of delivery indication. METHODS: We conducted a retrospective case-control study at the Mercy Hospital for Women (a tertiary hospital in Melbourne, Australia). Indication for delivery was assessed among women presenting with preeclampsia between 30+0 and 36+0 weeks' gestation. Baseline maternal and disease characteristics, preeclampsia features at delivery and postnatal outcomes were compared between patients delivering for maternal, fetal, or for both maternal and fetal indications. RESULTS: 173 women were diagnosed with preeclampsia between 30+0 and 36+0 weeks' gestation. Maternal baseline characteristics were similar between the groups. We found that 55.5% of women were delivered on maternal grounds compared to 27.2% requiring delivery for fetal indications; and 17.3% for both maternal and fetal indications (p < .0001). At diagnosis, intrauterine growth restriction and abnormal Dopplers increased the risk of requiring delivery for fetal indications by 3.5 times and 2.4 times respectively. CONCLUSION: Women presenting with late preterm preeclampsia primarily required delivery for maternal disease progression rather than fetal compromise.
-
ItemNo Preview AvailableInfluence of the photopolymerization matrix on the indicator response of optical fiber pH sensors(ELSEVIER SCIENCE SA, 2023-02-01)
-
Item
-
ItemThe L-NAME mouse model of preeclampsia and impact to long-term maternal cardiovascular health(LIFE SCIENCE ALLIANCE LLC, 2022-12)Preeclampsia affects ∼2-8% of pregnancies worldwide. It is associated with increased long-term maternal cardiovascular disease risk. This study assesses the effect of the vasoconstrictor N(ω)-nitro-L-arginine methyl ester (L-NAME) in modelling preeclampsia in mice, and its long-term effects on maternal cardiovascular health. In this study, we found that L-NAME administration mimicked key characteristics of preeclampsia, including elevated blood pressure, impaired fetal and placental growth, and increased circulating endothelin-1 (vasoconstrictor), soluble fms-like tyrosine kinase-1 (anti-angiogenic factor), and C-reactive protein (inflammatory marker). Post-delivery, mice that received L-NAME in pregnancy recovered, with no discernible changes in measured cardiovascular indices at 1-, 2-, and 4-wk post-delivery, compared with matched controls. At 10-wk post-delivery, arteries collected from the L-NAME mice constricted significantly more to phenylephrine than controls. In addition, these mice had increased kidney Mmp9:Timp1 and heart Tnf mRNA expression, indicating increased inflammation. These findings suggest that though administration of L-NAME in mice certainly models key characteristics of preeclampsia during pregnancy, it does not appear to model the adverse increase in cardiovascular disease risk seen in individuals after preeclampsia.
-
ItemActions of Esomeprazole on the Maternal Vasculature in Lean and Obese Pregnant Mice with Impaired Nitric Oxide Synthesis: A Model of Preeclampsia(MDPI, 2022-08)Preeclampsia is a devastating, multisystem disorder of pregnancy. It has no cure except delivery, which if premature can impart significant neonatal morbidity. Efforts to repurpose pregnancy-safe therapeutics for the treatment of preeclampsia have led to the assessment of the proton pump inhibitor, esomeprazole. Preclinically, esomeprazole reduced placental secretion of anti-angiogenic sFlt-1, improved endothelial dysfunction, promoted vasorelaxation, and reduced maternal hypertension in a mouse model. Our understanding of the precise mechanisms through which esomeprazole works to reduce endothelial dysfunction and enhance vasoreactivity is limited. Evidence from earlier studies suggested esomeprazole might work via the nitric oxide pathway, upregulating endothelial nitric oxide synthase (eNOS). Here, we investigated the effect of esomeprazole in a mouse model of L-NAME-induced hypertension (decreased eNOS activity). We further antagonised the model by addition of diet-induced obesity, which is relevant to both preeclampsia and the nitric oxide pathway. Esomeprazole did not decrease blood pressure in this model, nor were there any alterations in vasoreactivity or changes in foetal outcomes in lean mice. We observed similar findings in the obese mouse cohort, except esomeprazole treatment enhanced ex vivo acetylcholine-induced vasorelaxation. As acetylcholine induces nitric oxide production, these findings hint at a function for esomeprazole in the nitric oxide pathway.