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.

Pregestational body mass index, trimester-specific weight gain and total gestational weight gain: how do they influence perinatal outcomes?

OBJECTIVE: To investigate the association between pre-gestational body mass index (BMI), total gestational weight gain (GWG), and/or trimester-specific weight gain (GWGT) with adverse maternal or perinatal outcomes (AMPOs). MATERIALS AND METHODS: Maternal clinical characteristics and pregnancy and perinatal outcomes were used to predict AMPOs. The predictive ability of BMI, GWG, or GWGT for AMPOs was analyzed using the area under the curve (AUC). Logistic regression models in a univariate and multivariate analysis were performed to estimate the odds ratios (OR) and 95% confidence intervals (CI) to predict maternal outcomes (pregnancy-induced hypertension, preeclampsia or gestational diabetes mellitus) and perinatal outcomes (small for gestational age, large for gestational age, 5-min Apgar score, admission to neonatal intensive care unit or umbilical cord pH <7.15). RESULTS: Women with AMPOs (n = 293) were younger with higher rate of nulliparity (p < .001) and with lower height (p = .018) as compared to controls (n = 134). In the univariate study, GWGT in third trimester was associated with double risk of pregnancy-induced hypertension (OR 2.00; 95% CI, 1.01-3.97). Nonetheless, third-trimester GWG and total GWG have a negative relationship with gestational diabetes mellitus OR 0.32 (95% CI, 0.18-0.58) and OR 0.35 (95% CI, 0.21-0.59), respectively. Women with greater overall and in second trimester, GWG have a lower risk of having SGA neonates, OR 0.62 (95% CI, 0.39-0.98) and OR 0.60 (95% CI, 0.37-0.98), respectively. In the multivariate study, pre-gestational BMI is strongly related to the development of preeclampsia and the area under the curve (AUC) of the combination of pre-gestational BMI and total weight gain was 0.832 (95% CI, 0.63-0.81) for preeclampsia and 0.719 (95% CI, 0.71-0.94) for gestational diabetes mellitus. CONCLUSION: Our results suggest than timing of gestational weight gain influence in maternal and perinatal outcomes. Pre-gestational BMI is a determinant of preeclampsia, maternal weight gain in the third trimester is a determinant of pregnancy-induced hypertension and the increase in total GWG reduces the risk of gestational diabetes mellitus and small for gestational age.

Impact of intertwin interval on short-term neonatal outcomes of the second twin in dichorionic pregnancies with vaginal delivery.

OBJECTIVE: To examine the effect of intertwin interval on umbilical cord pH and Apgar scores of the second twin after vaginal delivery. METHODS: A retrospective study of twin deliveries at a university hospital in Spain between August 2012 and September 2017. Inclusion criteria were vaginal delivery of both twins at 32 gestational weeks or more. Exclusion criteria were monochorionic pregnancies and indication for cesarean delivery. The sample was dichotomized by intertwin interval (<10 and ≥10 minutes). Neonatal outcomes including Apgar scores and umbilical cord pH were evaluated. RESULTS: Overall, 323 twin deliveries were included. Intertwin interval was less than 10 minutes in 277 (85.6%) cases, and 10 minutes or longer in 46 (14.2%). There were no differences in maternal or obstetric characteristics between the groups. Incidence of instrumental delivery (P<0.001) and internal podalic version (P<0.001) for the second twin was higher in the longer interval group. A longer interval was associated with higher frequencies of 1-minute Apgar score below 4 (P=0.009), 5-minute Apgar score below 7 (P<0.001), and umbilical cord pH below 7.15 (P<0.001). CONCLUSION: Second twins with an intertwin interval of 10 minutes or longer are more likely to have poorer Apgar scores and arterial blood pH below 7.15.