Fetal heart rate changes and labor neuraxial analgesia: a machine learning approach.
Ontology highlight
ABSTRACT: Background
Neuraxial labor analgesia has been associated with fetal heart rate changes. Fetal bradycardia is multifactorial, and predicting it poses a significant challenge to clinicians. Machine learning algorithms may assist the clinician to predict fetal bradycardia and identify predictors associated with its presentation.Methods
A retrospective analysis of 1077 healthy laboring parturients receiving neuraxial analgesia was conducted. We compared a principal components regression model with tree-based random forest, ridge regression, multiple regression, a general additive model, and elastic net in terms of prediction accuracy and interpretability for inference purposes.Results
Multiple regression identified combined spinal-epidural (CSE) (p = 0.02), interaction between CSE and dose of phenylephrine (p < 0.0001), decelerations (p < 0.001), and the total dose of bupivacaine (p = 0.03) as associated with decrease in fetal heart rate. Random forest exhibited good predictive accuracy (mean standard error of 0.92).Conclusion
Use of CSE, presence of decelerations, total dose of bupivacaine, and total dose of vasopressors after CSE are associated with decreases in fetal heart rate in healthy parturients during labor. Prediction of changes in fetal heart rate can be approached with a tree-based random forest model with good accuracy with important variables that are key for the prediction, such as CSE, BMI, duration of stage 1 of labor, and dose of bupivacaine.
SUBMITTER: Riveros-Perez E
PROVIDER: S-EPMC10201770 | biostudies-literature | 2023 May
REPOSITORIES: biostudies-literature
Publications
Fetal heart rate changes and labor neuraxial analgesia: a machine learning approach.
Riveros-Perez Efrain E Polania-Gutierrez Javier Jose JJ Avella-Molano Bibiana B
BMC pregnancy and childbirth 20230522 1
<h4>Background</h4>Neuraxial labor analgesia has been associated with fetal heart rate changes. Fetal bradycardia is multifactorial, and predicting it poses a significant challenge to clinicians. Machine learning algorithms may assist the clinician to predict fetal bradycardia and identify predictors associated with its presentation.<h4>Methods</h4>A retrospective analysis of 1077 healthy laboring parturients receiving neuraxial analgesia was conducted. We compared a principal components regress ...[more]
Similar Datasets
Project description:PurposeTo compare the effects of epidural analgesia (EA) and combined spinal epidural analgesia (SEA) on labor and maternal-fetal outcomes.MethodsWe retrospectively identified and included 1499 patients with a single cephalic fetus who delivered at the study center from January 2015 to December 2018 and received neuraxial analgesia at the beginning of the active phase of labor (presence of regular painful contractions and cervical dilatation between 4 and 6 cm). Data including analgesia, labor characteristics, and maternal-fetal outcomes were retrieved from the prospectively collected delivery room database and medical records.ResultsSEA was associated with a shorter first stage of labor than EA, with a median difference of 60 min. On multivariable ordinal logistic regression analysis, neuraxial analgesia, gestational age, fetal weight, labor induction, and parity were independently associated with the first stage length: patients in the EA group were 1.32 times more likely to have a longer first stage of labor (95% CI 1.06-1.64, p = 0.012) than those in the SEA group. Additionally, a significantly lower incidence of fundal pressure was performed among patients who underwent SEA (OR 0.55, 95% CI 0.34-0.9, p = 0.017). No associations were observed between the used neuraxial analgesia technique and other outcomes.ConclusionsSEA was associated with a shorter length of the first stage of labor and a lower rate of fundal pressure use than EA. Further studies confirming the effects of SEA on labor management and clarifying differences in maternal-fetal outcomes will allow concluding about the superiority of one technique upon the other.
| S-EPMC10023596 | biostudies-literature
Project description:BackgroundLabor neuraxial analgesia may reduce the odds of postpartum hemorrhage, the leading indication for maternal blood transfusion during childbirth. This study tested the hypothesis that labor neuraxial analgesia is associated with reduced odds of maternal blood transfusion overall.MethodsU.S. birth certificate data in the Natality File of the National Vital Statistics System for all 50 states from 2015 to 2018 for vaginal and intrapartum cesarean deliveries were analyzed. The exposure was labor neuraxial analgesia. The primary outcome was maternal blood transfusion, recorded on the birth certificate, which has low sensitivity for this outcome. Adjusted odds ratios and 95% CIs of blood transfusion associated with neuraxial analgesia were estimated using propensity score matching. The adjusted odds ratios were estimated overall and according to delivery mode, and treatment effect was compared between vaginal and intrapartum cesarean deliveries using an interaction term. Sensitivity analyses were performed using inverse propensity score weighting and quantitative bias analysis for outcome misclassification.ResultsOf the 12,503,042 deliveries analyzed, 9,479,291 (75.82%) were with neuraxial analgesia, and 42,485 (0.34%) involved maternal blood transfusion. After propensity score matching, the incidence of blood transfusion was 0.30% in women without neuraxial analgesia (7,907 of 2,589,493) and 0.20% in women with neuraxial analgesia (5,225 of 2,589,493), yielding an adjusted odds ratio of 0.87 (95% CI, 0.82 to 0.91) overall. For intrapartum cesarean deliveries, the adjusted odds ratio was 0.55 (95% CI, 0.48 to 0.64), and for vaginal deliveries it was 0.93 (95% CI,. 0.88 to 0.98; P value for the interaction term < 0.001). The results were consistent in the sensitivity analyses, although the quantitative bias analysis demonstrated wide variation in potential effect size point estimates.ConclusionsLabor neuraxial analgesia may be associated with reduced odds of maternal blood transfusion in intrapartum cesarean deliveries and, to a lesser extent, vaginal deliveries. The specific effect size varies widely by delivery mode and is unclear given the poor sensitivity of the data set for the maternal transfusion primary outcome.Editor’s perspective
| S-EPMC10841247 | biostudies-literature
Project description:IntroductionNeuraxial labor analgesia has become an integral part of modern obstetric anesthetic practice. Presence of a familiar person during its placement may be beneficial to the patient. A survey was sent to anesthesiologists practicing obstetric anesthesia in the USA to determine their views.MethodsThe survey queried the following: existence of a written policy; would they allow a visitor; visitor's view, sitting or standing; reasons to allow or not allow a visitor; and influence by other staff on the decision. The responses were analyzed using multiple chi-square analyses.ResultsMost practitioners supported allowing a visitor during placement. Reduction of patient anxiety and fulfillment of patient request were the major reasons for allowing a visitor. Sitting position and no view of the workspace were preferred. Visitor interference and safety were cited as the major reasons for precluding a visitor. Nonanesthesia providers rarely influenced the decision. Epidural analgesia was the preferred technique. Essentially no bias was found in the responses; there was statistical uniformity regardless of procedures done per week, years in practice, professional certification, geographic region (rural, urban, or suburban), or academic, private, or government responders.ConclusionThe practice of visitor presence during the placement of neuraxial labor analgesia is gaining acceptance.
| S-EPMC5985117 | biostudies-literature
Project description:ImportanceAddressing severe maternal morbidity (SMM) is a public health priority in the US. Use of labor neuraxial analgesia for vaginal delivery is suggested to reduce the risk of postpartum hemorrhage (PPH), the leading cause of preventable severe maternal morbidity.ObjectiveTo assess the association between the use of labor neuraxial analgesia for vaginal delivery and SMM.Design, setting, and participantsIn this population-based cross-sectional study, women aged 15 to 49 years undergoing their first vaginal delivery were included. Data were taken from hospital discharge records from New York between January 2010 and December 2017. Data were analyzed from November 2020 to November 2021.ExposuresNeuraxial analgesia (ie, epidural or combined spinal-epidural) vs no neuraxial analgesia.Main outcomes and measuresThe primary outcome was SMM, as defined by the US Centers for Disease Control and Prevention, and the secondary outcome was PPH. Adjusted odds ratios (aORs) and 95% CIs of SMM associated with neuraxial analgesia were estimated using the inverse propensity score-weighting method and stratified according to race and ethnicity (non-Hispanic White vs racial and ethnic minority women, including non-Hispanic Asian or Pacific Islander, non-Hispanic Black, Hispanic, and other race and ethnicity) and to the comorbidity index for obstetric patients (low-risk vs high-risk women). The proportion of the association of neuraxial analgesia with the risk of SMM mediated through PPH was estimated using mediation analysis.ResultsOf 575 524 included women, the mean (SD) age was 28 (6) years, and 46 065 (8.0%) were non-Hispanic Asian or Pacific Islander, 88 577 (15.4%) were non-Hispanic Black, 104 866 (18.2%) were Hispanic, 258 276 (44.9%) were non-Hispanic White, and 74 534 (13.0%) were other race and ethnicity. A total of 400 346 women (69.6%) were in the low-risk group and 175 178 (30.4%) in the high-risk group, and 272 921 women (47.4%) received neuraxial analgesia. SMM occurred in 7712 women (1.3%), of which 2748 (35.6%) had PPH. Before weighting, the incidence of SMM was 1.3% (3486 of 272 291) with neuraxial analgesia compared with 1.4% (4226 of 302 603) without neuraxial analgesia (risk difference, -0.12 per 100; 95% CI, -0.17 to -0.07). After weighting, the aOR of SMM associated with neuraxial analgesia was 0.86 (95% CI, 0.82-0.90). Decreased risk of SMM associated with neuraxial analgesia was similar between non-Hispanic White women and racial and ethnic minority women and between low-risk and high-risk women. More than one-fifth (21%; 95% CI, 14-28) of the observed association of neuraxial analgesia with the risk of SMM was mediated through the decreased risk of PPH.Conclusions and relevanceFindings from this study suggest that use of neuraxial analgesia for vaginal delivery is associated with a 14% decrease in the risk of SMM. Increasing access to and utilization of labor neuraxial analgesia may contribute to improving maternal health outcomes.
| S-EPMC8864505 | biostudies-literature
Project description:ImportanceRecent studies have reported conflicting findings regarding a potential association between analgesia used during labor and autism spectrum disorder in the offspring.ObjectiveTo evaluate whether neuraxial labor analgesia increases the risk of autism spectrum disorder in the offspring.Design, setting, and participantsThis cohort study included mother-child dyads who underwent vaginal delivery and were exposed to neuraxial labor analgesia. Delivery data were collected from the Medicaid Analytic eXtract (2005-2014) for mothers with public insurance and the IBM Health MarketScan Research Database (2005-2015) for mothers with private insurance. Data analysis was conducted from January to October 2021.ExposuresPresence of a procedure code indicating neuraxial labor analgesia.Main outcomes and measuresChildren with autism spectrum disorder, identified using a validated algorithm (positive predictive value: 94% [95% CI, 83%-99%]). Cumulative incidence curves stratified by exposure were assessed using Kaplan-Meier analyses. Hazard ratios were estimated through Cox proportional hazards regression, using propensity-score fine stratification for confounding control. Estimates from both insurance cohorts were combined through fixed-effects meta-analysis. Subsequently, results from these analyses were combined with existing published studies.ResultsThe cohort of mother-child dyads with public insurance consisted of 910 696 deliveries (mean [SD] maternal age, 24.3 [5.7] years; 286 025 [31.4%] Black mothers; 374 282 [41.1%] White mothers), with 484 752 (53.2%) being exposed to neuraxial labor analgesia. The cohort of mother-child dyads with private insurance included 696 883 deliveries (mean [SD] maternal age, 31.0 [4.5] years; race and ethnicity data not available), with 513 347 (73.7%) being exposed. Cumulative incidence of autism spectrum disorder by 10 years of age was 1.93% (95% CI, 1.73%-2.13%) among children in the exposed group vs 1.64% (95% CI, 1.51%-1.76%) among children in the unexposed group in the publicly insured cohort. Respective numbers were 1.33% (95% CI, 1.19%-1.46%) and 1.19% (95% CI, 0.99%-1.38%) in the privately insured cohort. Adjusting for potential confounders and pooling across both cohorts resulted in a hazard ratio of 1.08 (95% CI, 1.02-1.15). Results were consistent when additionally adjusting for empirically identified variables through high-dimensional propensity score analyses (pooled hazard ratio, 1.07; 95% CI, 1.00-1.14) or expanding the cohorts to include cesarean deliveries and assisted vaginal deliveries (pooled hazard ratio, 1.07; 95% CI, 1.03-1.12). Meta-analysis of this study and recently published observational studies yielded similar findings with a pooled hazard ratio of 1.10 (95% CI, 1.06-1.13).Conclusions and relevanceAlthough a small increase in risk cannot be ruled out, the combined evidence from observational studies does not support the notion that neuraxial labor analgesia is associated with an increased risk of autism spectrum disorder.
| S-EPMC8696569 | biostudies-literature
Project description:ImportanceNeuraxial labor analgesia is recognized as the most effective method of providing pain relief during labor. Little is known about variation in the rates of neuraxial analgesia across US states. Identifying the presence and extent of variation may provide insights into practice variation and may indicate where access to neuraxial analgesia is inadequate.ObjectiveTo test the hypothesis that variation exists in neuraxial labor analgesia use among US states.Design, setting, and participantsRetrospective, population-based, cross-sectional analysis using US birth certificate data. Participants were 2 625 950 women who underwent labor in 2015.Main outcomes and measuresState-specific prevalence of neuraxial analgesia per 100 women who underwent labor and variability in neuraxial analgesia use among states, assessed using multilevel multivariable regression modeling with the median odds ratio and the intraclass correlation coefficient to evaluate variation by state.ResultsIn the study population of 2 625 950 women, 0.1% (n = 2010) were younger than 15 years, 7.0% (n = 183 546) were between the ages of 15 and 19 years, 23.6% (n = 620 118) were between the ages of 20 and 24 years, 29.6% (n = 777 957) were between the ages of 25 and 29 years, 26.0% (n = 683 656) were between the ages of 30 and 34 years, 11.4% (n = 298 237) were between the ages of 35 and 39 years, 2.2% (n = 57 130) were between the ages of 40 and 44 years, and 0.1% (n = 3296) were between the ages of 45 and 54 years. More than 90% were privately insured or insured with Medicaid. Neuraxial analgesia was used by 73.1% (n = 1 920 368) of women. After adjustment for antepartum, obstetric, and intrapartum factors, Maine had the lowest neuraxial analgesia prevalence (36.6%; 95% CI, 33.2%-40.1%) and Nevada the highest (80.1%; 95% CI, 78.3%-81.7%). The adjusted median odds ratio was 1.5 (95% CI, 1.4-1.6), and the intraclass correlation coefficient was 5.4% (95% CI, 4.0%-7.9%).Conclusions and relevanceResults of this study suggest that a small portion of the overall variation in neuraxial analgesia use is explained by US states. Unmeasured patient-level and hospital-level factors likely account for a large portion of the variation between states. Efforts should be made to understand what the main reasons are for this variation and whether the variation influences maternal or perinatal outcomes.
| S-EPMC6324365 | biostudies-literature
Project description:BackgroundProviding continuous health insurance coverage during the perinatal period may increase access to and utilization of labor neuraxial analgesia. This study tested the hypothesis that implementation of the 2010 Dependent Coverage Provision of the Patient Protection and Affordable Care Act, requiring private health insurers to allow young adults to remain on their parent's plan until age 26 yr, was associated with increased labor neuraxial analgesia use.MethodsThis study used a natural experiment design and birth certificate data for spontaneous vaginal deliveries in 28 U.S. states between 2009 and 2013. The intervention was the Dependent Coverage Provision, categorized into pre- and postintervention periods (January 2009 to August 2010 and September 2010 to December 2013, respectively). The exposure was women's age, categorized as exposed (21 to 25 yr) and unexposed (27 to 31 yr). The outcome was the labor neuraxial analgesia utilization rate.ResultsOf the 4,515,667 birth certificates analyzed, 3,033,129 (67.2%) indicated labor neuraxial analgesia use. For women aged 21 to 25 yr, labor neuraxial analgesia utilization rates were 64.9% during the preintervention period and 68.9% during the postintervention period (difference, 4.0%; 95% CI, 3.9 to 4.2). For women aged 27 to 31 yr, labor neuraxial analgesia utilization rates were 64.9% during the preintervention period and 67.7% during the postintervention period (difference, 2.8%; 95% CI, 2.7 to 2.9). After adjustment, implementation of the Dependent Coverage Provision was associated with a 1.0% (95% CI, 0.8 to 1.2) absolute increase in labor neuraxial analgesia utilization rate among women aged 21 to 25 yr compared with women aged 27 to 31 yr. The increase was statistically significant for White and Hispanic women but not for Black and Other race and ethnicity women.ConclusionsImplementation of the Dependent Coverage Provision was associated with a statistically significant increase in labor neuraxial analgesia use, but the small effect size is unlikely of clinical significance.Editor’s perspective
| S-EPMC10527099 | biostudies-literature
Project description:Background Few data are available on the intensity of pain that women experience during the first five days after vaginal childbirth. Moreover, it is unknown if the use of neuraxial labor analgesia has any impact on the level of postpartum pain. Methods We performed a retrospective cohort study based on chart review of all women who delivered vaginally at an urban teaching hospital between April 2017 and April 2019. The primary outcome was the area under the curve of pain score on numeric rating scale (NRS) documented in electronic medical records for five days postpartum (NRS-AUC5days). Secondary outcomes included peak NRS score, doses of oral and intravenous analgesics consumed during the first five days postpartum, and relevant obstetric outcomes. Logistic regression was used to examine the associations between the use of neuraxial labor analgesia and pain-related outcomes adjusting for potential confounders. Results During the study period, 778 women (38.6%) underwent vaginal delivery with neuraxial analgesia and 1240 women (61.4%) delivered without neuraxial analgesia. Median (Interquartile range) of NRS-AUC5days was 0.17 (0.12–0.24) among women who received neuraxial analgesia and 0.13 (0.08–0.19) among women who did not (p<0.001). Women who received neuraxial analgesia were more likely to require the first- and second-line analgesics postpartum than women who did not: diclofenac (87.9% vs. 73.0%, p< 0.001, respectively); acetaminophen (40.7% vs. 21.0%, p< 0.001, respectively). The use of neuraxial labor analgesia was independently associated with increased odds of having NRS-AUC5days in the highest 20 percentile (adjusted odds ratio [aOR] 2.03; 95% confidence interval [CI] 1.55–2.65), having peak NRS ≥ 4 (aOR 1.54; 95% CI 1.25–1.91) and developing hemorrhoids during the postpartum hospitalization (aOR 2.13; 95% CI 1.41–3.21) after adjusting for relevant confounders. Conclusion Although women who used neuraxial labor analgesia had slightly higher pain scores and increased analgesic requirement during postpartum hospitalization, pain after vaginal childbirth was overall mild. The small elevation in the pain burden in neuraxial group does not seem to be clinically relevant and should not influence women’s choice to receive labor analgesia.
| S-EPMC10112800 | biostudies-literature
Project description:The availability of safe, effective analgesia during labor has become an expectation for women in most of the developed world over the past two or three decades. More than 60% of women in the United States now receive some kind of neuraxial procedure during labor. This article is a brief review of the advantages and techniques of neuraxial labor analgesia along with the recent advances and controversies in the field of labor analgesia. For the most part, we have aimed the discussion at the non-anesthesiologist to give other practitioners a sense of the state of the art and science of labor analgesia in the second decade of the 21st century.
| S-EPMC5531153 | biostudies-other
Project description:ObjectiveTo develop a machine learning algorithm utilizing heart rate variability (HRV) and salivary cortisol to detect the presence of acute stress among pregnant women that may be applied to future clinical research.MethodsECG signals and salivary cortisol were analyzed from 29 pregnant women as part of a crossover study involving a standardized acute psychological stress exposure and a control non-stress condition. A filter-based features selection method was used to identify the importance of different features [heart rate (HR), time- and frequency-domain HRV parameters and salivary cortisol] for stress assessment and reduce the computational complexity. Five machine learning algorithms were implemented to assess the presence of stress with and without salivary cortisol values.ResultsOn graphical visualization, an obvious difference in heart rate (HR), HRV parameters and cortisol were evident among 17 participants between the two visits, which helped the stress assessment model to distinguish between stress and non-stress exposures with greater accuracy. Eight participants did not display a clear difference in HR and HRV parameters but displayed a large increase in cortisol following stress compared to the non-stress conditions. The remaining four participants did not demonstrate an obvious difference in any feature. Six out of nine features emerged from the feature selection method: cortisol, three time-domain HRV parameters, and two frequency-domain parameters. Cortisol was the strongest contributing feature, increasing the assessment accuracy by 10.3% on average across all five classifiers. The highest assessment accuracy achieved was 92.3%, and the highest average assessment accuracy was 76.5%.ConclusionSalivary cortisol contributed a significant increase in accuracy of the assessment model compared to using a range of HRV parameters alone. Our machine learning model demonstrates acceptable accuracy in detection of acute stress among pregnant women when combining salivary cortisol with HR and HRV parameters.
| S-EPMC9462678 | biostudies-literature