Routine first-trimester pre-eclampsia screening and risk of preterm birth

Leveraging Machine Learning to Predict and Assess Disparities in Severe Maternal Morbidity in Maryland

BACKGROUND

Severe maternal morbidity (SMM) is increasing in the United States. The main objective of this study is to test the use of machine learning (ML) techniques to develop models for predicting SMM during delivery hospitalizations in Maryland. Secondarily, we examine disparities in SMM by key sociodemographic characteristics.

METHODS

We used the linked State Inpatient Database (SID) and the American Hospital Association (AHA) Annual Survey data from Maryland for 2016-2019 (N = 261,226 delivery hospitalizations). We first estimated relative risks for SMM across key sociodemographic factors (e.g., race, income, insurance, and primary language). Then, we fitted LASSO and, for comparison, Logit models with 75 and 18 features. The selection of SMM features was based on clinical expert opinion, a literature review, statistical significance, and computational resource constraints. Various model performance metrics, including the area under the receiver operating characteristic curve (AUC), accuracy, precision, and recall values were computed to compare predictive performance.

RESULTS

During 2016-2019, 76 per 10,000 deliveries (1976 of 261,226) were in patients who experienced an SMM event. The Logit model with a full list of 75 features achieved an AUC of 0.71 in the validation dataset, which marginally decreased to 0.69 in the reduced model with 18 features. The LASSO algorithm with the same 18 features demonstrated slightly superior predictive performance and an AUC of 0.80. We found significant disparities in SMM among patients living in low-income areas, with public insurance, and who were non-Hispanic Black or non-English speakers.

CONCLUSION

Our results demonstrate the feasibility of utilizing ML and administrative hospital discharge data for SMM prediction. The low recall score is a limitation across all models we compared, signifying that the algorithms struggle with identifying all SMM cases. This study identified substantial disparities in SMM across various sociodemographic factors. Addressing these disparities requires multifaceted interventions that include improving access to quality care, enhancing cultural competence among healthcare providers, and implementing policies that help mitigate social determinants of health.

First-trimester uterine artery Doppler and hypertensive disorders in twin pregnancies: Use of twin versus singleton references

OBJECTIVE

To determine the association of first-trimester uterine artery Doppler with hypertensive disorders of pregnancy in twin pregnancies.

METHODS

This was a retrospective cohort study of twin pregnancies followed at the University Hospital Center of Central Lisbon, Portugal, between January 2010 and December 2022. First-trimester uterine artery pulsatility index (UtA-PI) was determined and compared between twin pregnancies (n = 454) and singleton pregnancies (n = 908), matched to maternal and pregnancy characteristics. Maternal characteristics and mean UtA-PI were analyzed for gestational age, birth weight, gestational hypertension, early- and late-onset pre-eclampsia, HELLP (hemolysis, elevated liver enzymes, low platelets) syndrome, and preterm birth. Univariable and multivariable logistic regression models were used.

RESULTS

The mean first-trimester UtA-PI was significantly lower in dichorionic twins than in singletons (P < 0.001). To study hypertensive disorders of pregnancy in twins, 390 pregnancies were included: 311 (79.7%) dichorionic and 79 (20.3%) monochorionic twins. The observed rates of early- and late-onset pre-eclampsia, gestational hypertension, and HELLP syndrome were 1.0%, 4.4%, 7.4%, and 1.5%, respectively. We achieved a 100% detection rate for early-onset pre-eclampsia using the UtA-PI 90th centile for twins. However, when singleton references were considered, the detection rate decreased to 50%. UtA-PI at or above the 95th centile was associated with increased odds for preterm birth before 32 weeks (adjusted odds ratio 4.1, 95% confidence interval 1.0-16.7, P = 0.043).

CONCLUSIONS

Unless other major risk factors for hypertensive disorders are present, women with low UtA-PI will probably not benefit from aspirin prophylaxis. Close monitoring of all twin pregnancies for hypertensive disorders is still recommended.

First trimester risk of preeclampsia and rate of spontaneous birth in patients without preeclampsia

BACKGROUND

First-trimester screening for preeclampsia using a combination of maternal risk factors and mean arterial pressure, uterine artery pulsatility index, and placental growth factor, as proposed by the Fetal Medicine Foundation, provides effective prediction of preterm preeclampsia. Placental dysfunction is a potential precursor of spontaneous birth.

OBJECTIVE

The objective of this study was to examine if the estimated risk of preeclampsia is associated with the gestational age at onset of spontaneous delivery in the absence of preeclampsia.

STUDY DESIGN

This was a secondary analysis of the data from the Screening programme for pre-eclampsia trial in which there was a comparison of the performance of first-trimester screening for preterm preeclampsia using the Fetal Medicine Foundation model vs a traditional history-based risk scoring system. A subgroup of women from the trial with spontaneous onset of delivery (labor with intact membranes or preterm prelabor rupture of membranes) was included in this study and was arbitrarily divided into 3 groups according to the risk for preterm preeclampsia as determined by the Fetal Medicine Foundation model at 11 to 13 weeks' gestation as follows: group 1 low risk (˂1/100); group 2 intermediate risk (1/50 to 1/100); and group 3 high risk (˃1/50). A survival analysis was carried out using a Kaplan-Meier estimator and a Cox regression analysis with stratification by the 3 preeclampsia risk groups. Occurrence of spontaneous birth in the study groups was compared using log-rank tests and hazard ratios.

RESULTS

The study population comprised 10,820 cases with delivery after spontaneous onset of labor among the 16,451 cases who participated in the Screening programme for pre-eclampsia trial. There were 9795 cases in group 1, 583 in group 2, and 442 in group 3. The gestational age at delivery was <28, <32, <35, <37, and <40 weeks in 0.29%, 0.64%, 1.68%, 4.52%, and 44.97% of cases, respectively, in group 1; 0.69%, 1.71%, 3.26%, 7.72%, and 55.23% of cases, respectively, in group 2; and 0.45%, 1.81%, 5.66%, 13.80%, and 63.12% of cases, respectively, in group 3. The curve profile of gestational age at spontaneous birth in the 3 study groups was significantly different overall and in pairwise comparisons (P values <.001). The Cox regression analysis showed that risks increased for spontaneous birth by 18% when the intermediate-risk group was compared with the low-risk group (P˂.001) and by 41% when the high-risk group was compared with the low-risk group (P˂.001).

CONCLUSION

In this study that investigated birth after spontaneous onset of labor in women without preeclampsia, there were 2 major findings. First, the duration of pregnancy decreased with increasing first-trimester risk for preeclampsia. Second, in the high-risk group, when compared with the low-risk group, the risk for spontaneous birth was 4 times higher at a gestational age of 24 to 26 weeks, 3 times higher at 28 to 32 weeks, and 2 times higher at 34 to 39 weeks. These differences present major clinical implications for antepartum counselling, monitoring, and interventions in these pregnancies.

Machine learning, advanced data analysis, and a role in pregnancy care? How can we help improve preeclampsia outcomes?

The value of machine learning capacity in maternal health, and in particular prediction of preeclampsia will only be realised when there are high quality clinical data provided, representative populations included, different health systems and models of care compared, and a culture of rapid use and application of real-time data and outcomes. This review has been undertaken to provide an overview of the language, and early results of machine learning in a pregnancy and preeclampsia context. Clinicians of all backgrounds are encouraged to learn the language of Machine Learning (ML) and Artificial intelligence (AI) to better understand their potential and utility to improve outcomes for women and their families. This review will outline some definitions and features of ML that will benefit clinician's knowledge in the preeclampsia discipline, and also outline some of the future possibilities for preeclampsia-focussed clinicians via understanding AI. It will further explore the criticality of defining the risk, and outcome being determined.

Maternal ethnicity and socioeconomic deprivation: influence on adverse pregnancy outcomes

OBJECTIVE

To evaluate the relative importance of ethnicity and socioeconomic deprivation in determining the likelihood and prevalence of placentally derived composite of adverse pregnancy outcomes (CAPO) and composite of severe adverse pregnancy outcomes (CAPO-S).

METHODS

This was a single-center retrospective cohort study of data obtained in a tertiary maternity unit. Data regarding ethnicity and socioeconomic deprivation (as measured with indices of multiple deprivation) were collected for 13 165 singleton pregnancies screened routinely in the first trimester for pre-eclampsia using the Fetal Medicine Foundation combined risk-assessment algorithm. CAPO was defined as the presence of one or more interrelated outcomes associated with placental dysfunction, namely, hypertensive disorders of pregnancy, preterm birth, birth weight ≤ 10th centile and stillbirth. CAPO-S was defined as the presence of one or more of the following: hypertensive disorders of pregnancy at < 37 + 0 weeks, preterm birth at < 34 + 0 weeks, birth weight ≤ 5th centile and stillbirth at < 37 + 0 weeks.

RESULTS

The prevalence of CAPO was 16.3% in white women, 29.3% in black women and 29.3% in South Asian women. However, half (51.7%) of all CAPO cases occurred in white women. There was a strong interaction between ethnicity and socioeconomic deprivation, with a correlation coefficient of -0.223. Both ethnicity and socioeconomic deprivation influenced the prevalence of CAPO and CAPO-S, with the contribution of ethnicity being the strongest.

CONCLUSIONS

Black and Asian ethnicity, as well as socioeconomic deprivation, influence the prevalence of placenta-mediated adverse pregnancy outcomes. Despite this, most adverse pregnancy outcomes occur in white women, who represent the majority of the population and are also affected by socioeconomic deprivation. For these reasons, inclusion of socioeconomic deprivation should be considered in early pregnancy risk assessment for placenta-mediated CAPO. © 2024 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Evaluating the predictive efficacy of first trimester biochemical markers (PAPP-A, fβ-hCG) in forecasting preterm delivery incidences

In this investigation, we explored the correlation between first-trimester biochemical markers and the incidence of preterm birth (PTB), irrespective of the cause, spontaneous preterm birth (sPTB), and preterm premature rupture of membranes (pPROM) within a cohort comprising 1164 patients. It was discovered that diminished levels of Pregnancy-Associated Plasma Protein-A (PAPP-A) between 11 and 13 + 6 weeks of gestation significantly contributed to the risk of preterm deliveries both before 35 and 37 weeks, as well as to pPROM instances. Furthermore, women experiencing sPTB before the 37th week of gestation also exhibited lower concentrations of PAPP-A. Moreover, reduced first-trimester concentrations of free beta-human chorionic gonadotropin (fb-HCG) were identified as a risk factor for deliveries preceding 37 weeks, pPROM, and sPTB before 35 weeks of gestation. Despite these correlations, the area under the curve for these biochemical markers did not surpass 0.7, indicating their limited diagnostic potential. The most significant discriminatory capability was noted for PAPP-A levels, with a threshold of < 0.71 multiples of the median (MoM) predicting PTB before 37 weeks, yielding an odds ratio of 3.11 (95% Confidence Interval [CI] 1.97-4.92). For sPTB, the greatest discriminatory potential was observed for PAPP-A < 0.688, providing an OR of 2.66 (95% CI 1.51-4.66). The cut-off points corresponded to accuracies of 76.05% and 79.1%, respectively. In regression analyses, the combined predictive models exhibited low explanatory power with R2 values of 9.2% for PTB and 7.7% for sPTB below 35 weeks of gestation. In conclusion, while certain biochemical markers demonstrated associations with outcomes of preterm birth, their individual and collective predictive efficacies for foreseeing such events were found to be suboptimal.

Heat exposure induced risks of preterm birth mediated by maternal hypertension

Heat exposure is associated with an increased risk of preterm birth (PTB), with previous work suggesting that maternal blood pressure may play a role in these associations. Here we conducted a cohort study of 197,080 singleton live births across 8 provinces in China from 2015 to 2018. The study first estimated the associations between heat exposure, maternal hypertension and clinical subtypes of PTB, and then quantified the role of maternal hypertension in heat and PTB using mediation analyses. We show that heat exposure (>85th, 90th and 95th percentiles of local temperature distributions) spanning from conception to the 20th gestational week was associated with a 15-21% increase in PTB, and a 20-22% increase in medically indicated PTB. Heat exposure is likely to increase the risk of maternal hypertension and elevated blood pressure. Maternal hypertension mediated 15.7% and 33.9% of the effects of heat exposure (>90th percentile) on PTB and medically indicated PTB, respectively. Based on this large-population study, we found that exposure to heat in early pregnancy can increase the risk of maternal hypertension, thereby affecting the incidence of PTB.

First-trimester serum biomarkers in twin pregnancies and adverse obstetric outcomes-a single center cohort study

PURPOSE

This study aimed to determine the association of first-trimester maternal serum biomarkers with preterm birth (PTB), fetal growth restriction (FGR) and hypertensive disorders of pregnancy (HDP) in twin pregnancies.

METHODS

This is a retrospective cohort study of twin pregnancies followed at Maternidade Dr. Alfredo da Costa, Lisbon, Portugal, between January 2010 and December 2022. We included women who completed first-trimester screening in our unit and had ongoing pregnancies with two live fetuses, and delivered after 24 weeks. Maternal characteristics, pregnancy-associated plasma protein-A (PAPP-A) and β-human chorionic gonadotropin (β-hCG) levels were analyzed for different outcomes: small for gestational age (SGA), gestational hypertension (GH), early and late-onset pre-eclampsia (PE), as well as the composite outcome of PTB associated with FGR and/or HDP. Univariable, multivariable logistic regression analyses and receiver-operating characteristic curve were used.

RESULTS

466 twin pregnancies met the inclusion criteria. Overall, 185 (39.7%) pregnancies were affected by SGA < 5th percentile and/or HDP. PAPP-A demonstrated a linear association with gestational age at birth and mean birth weight. PAPP-A proved to be an independent risk factor for SGA and PTB (< 34 and < 36 weeks) related to FGR and/or HDP. None of the women with PAPP-A MoM > 90th percentile developed early-onset PE or PTB < 34 weeks.

CONCLUSION

A high serum PAPP-A (> 90th percentile) ruled out early-onset PE and PTB < 34 weeks. Unless other major risk factors for hypertensive disorders are present, these women should not be considered candidates for aspirin prophylaxis. Nevertheless, close monitoring of all TwP for adverse obstetric outcomes is still recommended.

Vaginal microbiota and spontaneous preterm birth in pregnant women at high risk of recurrence

We describe vaginal microbiota, including Gardnerella species and sexually transmitted infections (STIs), during pregnancy and their associations with recurrent spontaneous preterm birth (sPTB). We performed a prospective cohort study in a tertiary referral centre in the Netherlands, among pregnant women with previous sPTB <34 weeks' gestation. Participants collected three vaginal swabs in the first and second trimester. Vaginal microbiota was profiled with 16S rDNA sequencing. Gardnerella species and STI's were tested with qPCR. Standard care was provided according to local protocol, including screening and treatment for bacterial vaginosis (BV), routine progesterone administration and screening for cervical length shortening. Of 154 participants, 26 (16.9 %) experienced recurrent sPTB <37 weeks' gestation. Microbiota composition was not associated with sPTB. During pregnancy, the share of Lactobacillus iners-dominated microbiota increased at the expense of diverse microbiota between the first and second trimester. This change coincided with treatment for BV, demonstrating a similar change in microbiota composition after treatment. In this cohort of high-risk women, we did not find an association between vaginal microbiota composition and recurrent sPTB. This should be interpreted with care, as these women were offered additional preventive therapies to reduce sPTB according to national guidelines including progesterone and BV treatment. The increase observed in L. iners dominated microbiota and the decrease in diverse microbiota mid-gestation was most likely mediated by BV treatment. Our findings suggest that in recurrent sPTB occurring despite several preventive therapies, the microbe-related etiologic contribution might be limited.

First-trimester prediction of preterm pre-eclampsia and prophylaxis by aspirin: Effect on spontaneous and iatrogenic preterm birth

OBJECTIVE

To report the predictive performance for preterm birth (PTB) of the Fetal Medicine Foundation (FMF) triple test and National Institute for health and Care Excellence (NICE) guidelines used to screen for pre-eclampsia and examine the impact of aspirin in the prevention of PTB.

DESIGN

Secondary analysis of data from the SPREE study and the ASPRE trial.

SETTING

Multicentre studies.

POPULATION

In SPREE, women with singleton pregnancies had screening for preterm pre-eclampsia at 11-13 weeks of gestation by the FMF method and NICE guidelines. There were 16 451 pregnancies that resulted in delivery at ≥24 weeks of gestation and these data were used to derive the predictive performance for PTB of the two methods of screening. The results from the ASPRE trial were used to examine the effect of aspirin in the prevention of PTB in the population from SPREE.

METHODS

Comparison of performance of FMF method and NICE guidelines for pre-eclampsia in the prediction of PTB and use of aspirin in prevention of PTB.

MAIN OUTCOME MEASURE

Spontaneous PTB (sPTB), iatrogenic PTB for pre-eclampsia (iPTB-PE) and iatrogenic PTB for reasons other than pre-eclampsia (iPTB-noPE).

RESULTS

Estimated incidence rates of sPTB, iPTB-PE and iPTB-noPE were 3.4%, 0.8% and 1.6%, respectively. The corresponding detection rates were 17%, 82% and 25% for the triple test and 12%, 39% and 19% for NICE guidelines, using the same overall screen positive rate of 10.2%. The estimated proportions prevented by aspirin were 14%, 65% and 0%, respectively.

CONCLUSION

Prediction of sPTB and iPTB-noPE by the triple test was poor and poorer by the NICE guidelines. Neither sPTB nor iPTB-noPE was reduced substantially by aspirin.

Adverse pregnancy outcomes in women at increased risk of preterm pre-eclampsia on first-trimester combined screening

OBJECTIVE

Uteroplacental dysfunction may not only result in pre-eclampsia (PE) but also in preterm birth (PTB), small-for-gestational-age (SGA) birth and stillbirth. The aim of this study is to evaluate the positive predictive value (PPV) of first-trimester combined PE screening for all of these placenta-mediated adverse pregnancy outcomes.

DESIGN

Retrospective cohort study.

SETTING

Tertiary referral maternity unit.

SAMPLE

A total of 13 211 singleton pregnancies.

METHODS

First-trimester combined screening for preterm PE using the Fetal Medicine Foundation (FMF) algorithm.

MAIN OUTCOMES MEASURES

Hypertensive disorders of pregnancy (HDP), PTB, SGA birth and stillbirth were combined to assess composite adverse and severe adverse pregnancy outcomes (CAPO and CAPO-S). The PPVs for CAPO and CAPO-S were calculated for women with a combined risk for preterm PE of ≥1 in 50 and ≥1 in 100.

RESULTS

First-trimester combined screening identified 2215 women (16.8%) with a risk of ≥1 in 100 for preterm PE. The PPVs for a risk of ≥1 in 100 for CAPO and CAPO-S were 38.8% and 18.2%, respectively. The equivalent PPVs for a risk of ≥1 in 50 were 45.1% and 21.1%, respectively.

CONCLUSIONS

Women identified at high risk of preterm PE are also at increased risk of other placenta-mediated adverse pregnancy outcomes, such as PTB, SGA birth and stillbirth. Women at high risk for preterm PE after first-trimester screening may benefit from a higher surveillance care pathway, with interventions to mitigate all the adverse outcomes associated with placental dysfunction.

Preterm Birth: Screening and Prediction

Preterm birth (PTB) affects approximately 10% of births globally each year and is the most significant direct cause of neonatal death and of long-term disability worldwide. Early identification of women at high risk of PTB is important, given the availability of evidence-based, effective screening modalities, which facilitate decision-making on preventative strategies, particularly transvaginal sonographic cervical length (CL) measurement. There is growing evidence that combining CL with quantitative fetal fibronectin (qfFN) and maternal risk factors in the extensively peer-reviewed and validated QUanititative Innovation in Predicting Preterm birth (QUiPP) application can aid both the triage of patients who present as emergencies with symptoms of preterm labor and high-risk asymptomatic women attending PTB surveillance clinics. The QUiPP app risk of delivery thus supports shared decision-making with patients on the need for increased outpatient surveillance, in-patient treatment for preterm labor or simply reassurance for those unlikely to deliver preterm. Effective triage of patients at preterm gestations is an obstetric clinical priority as correctly timed administration of antenatal corticosteroids will maximise their neonatal benefits. This review explores the predictive capacity of existing predictive tests for PTB in both singleton and multiple pregnancies, including the QUiPP app v.2. and discusses promising new research areas, which aim to predict PTB through cervical stiffness and elastography measurements, metabolomics, extracellular vesicles and artificial intelligence.

A cross-sectional survey of women's views and preferences for preterm birth screening and treatment

OBJECTIVES

Primary outcomes were to determine; 1) the desire for more patient information from healthcare professionals on preterm birth (PTB) prevention 2) the desire for PTB screening surveillance or participation in research or 3) the acceptability of transvaginal ultrasound (TVUS) or vaginal examinations to predict spontaneous PTB.

METHODS

A 19-question, piloted, self-administered survey was completed by unselected pregnant women in a tertiary maternity hospital in Dublin, Ireland. Data was collected to include maternal socio-demographics, past obstetric history, and current pregnancy details, in addition to views and preferences on PTB screening and preventative treatments. Statistical analysis to include binary and multinomial regression was performed by IBM SPSS Statistics for Windows (Version 29.0).

RESULTS

277 women completed the study survey. 9.4% of women had attended the preterm birth surveillance clinic (PSC). 75.1% of respondents indicated a preference for more information from healthcare professionals about PTB. 65% reported that TVUS and vaginal examinations were acceptable in pregnancy. The acceptability of antenatal examinations was significantly influenced by ethnicity; white European (OR 2.58, CI 1.12-5.95, p = 0.003) and Asian (OR 3.39, CI 1.18-9.67, p = 0.02). Discomfort (25.3%) and vaginal bleeding (11.9%) were the most frequently reported concerns about TVUS. 95.7% of unselected women indicated that they would accept treatment to prevent PTB. Vaginal progesterone (53.8%) was preferred treatment compared to cervical cerclage (15.9%) or cervical pessary (16.6%). 55.6% of respondents stated they attend or wish to attend for additional appointments or research opportunities for PTB screening. Women with a previous PTB or second trimester miscarriage were more likely to attend or wish to attend for PTB screening (OR 3.23, CI 1.34-7.79, p = 0.009).

CONCLUSION

PTB is an important healthcare priority for pregnant women in Ireland. However, women require more information, counselling and reassurance about the utility and safety of TVUS in PSCs.

First Trimester of Pregnancy as the Sensitive Period for the Association between Prenatal Mosquito Coil Smoke Exposure and Preterm Birth

Mosquito coils are efficient mosquito repellents and mosquito coil smoke (MCS) contributes to indoor air pollution. However, no prior population-based study has investigated whether prenatal MCS exposure is a risk factor for preterm birth (PTB) and whether exposure to MCS in different trimesters of pregnancy is associated with different levels of risk. The sample involved 66,503 mother-child dyads. Logistic regression models were used to examine the relationships between prenatal MCS exposure during different trimesters of pregnancy and PTB. We found that prenatal MCS exposure was associated with a greater likelihood of PTB (OR = 1.12, 95%CI: 1.05-1.20). The prenatal MCS exposure during the first trimester was associated with 1.17 (95%CI: 1.09-1.25) times the odds of being PTB, which was higher than exposure during the second trimester (OR = 1.11, 95%CI: 1.03-1.19) and during the third trimester (OR = 1.08, 95%CI: 1.01-1.16). In the stratified analysis, prenatal MCS exposure significantly increased PTB risk among girls but not among boys. Our results indicated that maternal MCS exposure during pregnancy was associated with PTB and that the first trimester might be the sensitive period. In light of these findings, public health interventions are needed to reduce prenatal exposure to MCS, particularly during the first trimester of pregnancy.