Predicting singleton antepartum stillbirth by the demographic Fetal Medicine Foundation Risk Calculator-A retrospective case-control study

The utility of complete blood parameter indices to predict stillbirths

OBJECTIVE

In this study, we aimed to investigate the relationship between unexplained stillbirth (SB) cases and the complete blood parameter indices and we compared them with uncomplicated healthy cases.

METHODS

Patients diagnosed with unexplained SB cases in a tertiary center between 2019-2022 were included in this retrospective case-control study. The gestational age threshold for SBs was accepted as births after the 20th week of pregnancy. Consecutive patients with no adverse obstetric outcomes were accepted as the control group. Patients' complete blood parameter results at the time of the first admission to the hospital until 14 weeks were labeled as "1'' and at the time of delivery were labeled as "2'' and recorded. As inflammatory parameters, neutrophile-lymphocyte ratio, derivated neutrophile-lymphocyte ratio, platelet-lymphocyte ratio, lymphocyte-monocyte ratio (LMR), and hemoglobin-lymphocyte ratio (HLR) were calculated from complete blood results and recorded.

RESULTS

There were statistically significant differences between the groups' LMR1 (p = .040). Additionally, whereas HLR1 of the study group was 0.693 (0.38-2.72), it was 0.645 (0.15-1.82) in the control group (p = .026). However, the HLR2 of the study group was significantly lower than the control group (p = .021).

CONCLUSION

Necessary precautions such as fetal biophysical profile examination can be taken more frequently in the antenatal follow-up in patients considered to be at high risk of SB by using HLR. It is a novel marker that can be easily accessible and calculated from the complete blood parameters.

Identifying risk of stillbirth using machine learning

BACKGROUND

Previous predictive models using logistic regression for stillbirth do not leverage the advanced and nuanced techniques involved in sophisticated machine learning methods, such as modeling nonlinear relationships between outcomes.

OBJECTIVE

This study aimed to create and refine machine learning models for predicting stillbirth using data available before viability (22-24 weeks) and throughout pregnancy, as well as demographic, medical, and prenatal visit data, including ultrasound and fetal genetics.

STUDY DESIGN

This is a secondary analysis of the Stillbirth Collaborative Research Network, which included data from pregnancies resulting in stillborn and live-born infants delivered at 59 hospitals in 5 diverse regions across the United States from 2006 to 2009. The primary aim was the creation of a model for predicting stillbirth using data available before viability. Secondary aims included refining models with variables available throughout pregnancy and determining variable importance.

RESULTS

Among 3000 live births and 982 stillbirths, 101 variables of interest were identified. Of the models incorporating data available before viability, the random forests model had 85.1% accuracy (area under the curve) and high sensitivity (88.6%), specificity (85.3%), positive predictive value (85.3%), and negative predictive value (84.8%). A random forests model using data collected throughout pregnancy resulted in accuracy of 85.0%; this model had 92.2% sensitivity, 77.9% specificity, 84.7% positive predictive value, and 88.3% negative predictive value. Important variables in the previability model included previous stillbirth, minority race, gestational age at the earliest prenatal visit and ultrasound, and second-trimester serum screening.

CONCLUSION

Applying advanced machine learning techniques to a comprehensive database of stillbirths and live births with unique and clinically relevant variables resulted in an algorithm that could accurately identify 85% of pregnancies that would result in stillbirth, before they reached viability. Once validated in representative databases reflective of the US birthing population and then prospectively, these models may provide effective risk stratification and clinical decision-making support to better identify and monitor those at risk of stillbirth.

Prediction of stillbirth low resource setting in Northern Uganda

Background

Women of Afro-Caribbean and Asian origin are more at risk of stillbirths. However, there are limited tools built for risk-prediction models for stillbirth within sub-Saharan Africa. Therefore, we examined the predictors for stillbirth in low resource setting in Northern Uganda.

Methods

Prospective cohort study at St. Mary’s hospital Lacor in Northern Uganda. Using Yamane’s 1967 formula for calculating sample size for cohort studies using finite population size, the required sample size was 379 mothers. We doubled the number (to > 758) to cater for loss to follow up, miscarriages, and clients opting out of the study during the follow-up period. Recruited 1,285 pregnant mothers at 16–24 weeks, excluded those with lethal congenital anomalies diagnosed on ultrasound. Their history, physical findings, blood tests and uterine artery Doppler indices were taken, and the mothers were encouraged to continue with routine prenatal care until the time for delivery. While in the delivery ward, they were followed up in labour until delivery by the research team. The primary outcome was stillbirth 24 + weeks with no signs of life. Built models in RStudio. Since the data was imbalanced with low stillbirth rate, used ROSE package to over-sample stillbirths and under-sample live-births to balance the data. We cross-validated the models with the ROSE-derived data using K (10)-fold cross-validation and obtained the area under curve (AUC) with accuracy, sensitivity and specificity.

Results

The incidence of stillbirth was 2.5%. Predictors of stillbirth were history of abortion (aOR = 3.07, 95% CI 1.11—8.05, p = 0.0243), bilateral end-diastolic notch (aOR = 3.51, 95% CI 1.13—9.92, p = 0.0209), personal history of preeclampsia (aOR = 5.18, 95% CI 0.60—30.66, p = 0.0916), and haemoglobin 9.5 – 12.1 g/dL (aOR = 0.33, 95% CI 0.11—0.93, p = 0.0375). The models’ AUC was 75.0% with 68.1% accuracy, 69.1% sensitivity and 67.1% specificity.

Conclusion

Risk factors for stillbirth include history of abortion and bilateral end-diastolic notch, while haemoglobin of 9.5—12.1 g/dL is protective.