Platelet Count in First Trimester of Pregnancy as a Predictor of Perinatal Outcome

The Association Between the Maternal Pre-pregnancy Platelet Count and Fecundability in Mainland China: A Population-based Cohort Study

BACKGROUND

Currently, awareness about platelet count (PC) and its consequences for perinatal outcome have increased, but there is little reliable evidence on fecundability.

METHODS

Based on the National Free Pre-conception Check-up Projects supported by the Chinese government, 5,524,886 couples met the inclusion criteria and were included in this cohort study. Cox regression models were adopted to estimate fecundability ratios (FRs) and their 95% confidence intervals (CIs) for pre-pregnancy PC quintiles. Restricted cubic splines were used to flexibly model and visualize the relationship of PC with FRs. Microsoft SQL server and R software were used for data management and analysis.

RESULTS

The median of pre-pregnancy PC among women was 221.00 × 109/L. The first (<177.00 × 109/L) and second quintile (177.00-207.99 × 109/L) of PC showed slightly increased fecundability (Q1: adjusted FR 1.05; 95% CI, 1.04-1.06; Q2: adjusted FR 1.04; 95% CI, 1.03-1.05), while higher quintals (Q4: 236.00-271.99 × 109/L; Q5: ≥272.00 × 109/L) were related to reduction of fecundability, when compared with the third quintile of PC (208.00-235.99 × 109/L) (Q4: adjusted FR 0.96; 95% CI, 0.95-0.97; Q5: adjusted FR 0.88; 95% CI, 0.87-0.89). In the first quintiles (<177.00 × 109/L), only 20.93% women had PC below 129.94 × 109/L. An inverse-U-shaped association was consistently observed among women such that the lower PC within the normal range (<118.03 × 109/L) and higher PC (>223.06 × 109/L) were associated with the risk of reduced female fecundability (P for non-linearity < 0.01).

CONCLUSION

PC is associated with female fecundability. Further classification of PC levels may deepen our understanding of the early warnings and significance of female fecundability.

Development and Evaluation of a Machine Learning Prediction Model for Small-for-Gestational-Age Births in Women Exposed to Radiation before Pregnancy

Exposure to radiation has been associated with increased risk of delivering small-for-gestational-age (SGA) newborns. There are no tools to predict SGA newborns in pregnant women exposed to radiation before pregnancy. Here, we aimed to develop an array of machine learning (ML) models to predict SGA newborns in women exposed to radiation before pregnancy. Patients’ data was obtained from the National Free Preconception Health Examination Project from 2010 to 2012. The data were randomly divided into a training dataset (n = 364) and a testing dataset (n = 91). Eight various ML models were compared for solving the binary classification of SGA prediction, followed by a post hoc explainability based on the SHAP model to identify and interpret the most important features that contribute to the prediction outcome. A total of 455 newborns were included, with the occurrence of 60 SGA births (13.2%). Overall, the model obtained by extreme gradient boosting (XGBoost) achieved the highest area under the receiver-operating-characteristic curve (AUC) in the testing set (0.844, 95% confidence interval (CI): 0.713–0.974). All models showed satisfied AUCs, except for the logistic regression model (AUC: 0.561, 95% CI: 0.355–0.768). After feature selection by recursive feature elimination (RFE), 15 features were included in the final prediction model using the XGBoost algorithm, with an AUC of 0.821 (95% CI: 0.650–0.993). ML algorithms can generate robust models to predict SGA newborns in pregnant women exposed to radiation before pregnancy, which may thus be used as a prediction tool for SGA newborns in high-risk pregnant women.

First-Trimester Platelet Count as a Predictive Biomarker for Neonatal Birth Weight Among Pregnant Women at Advanced Maternal Age

The aim of this study was to investigate the association between first-trimester platelet count and neonatal birth weight in pregnant woman at advanced maternal age. Our study included 148 pregnancy women of advanced maternal age, the clinical and laboratory materials were retrospective obtained from medical record system. The neonatal birth weight was positively correlated with maternal body mass index and fetus gestational age (r = 0.332, P < .001; r = 0.469, P < .001), even more interestingly, the neonatal birth weight was positively correlated with first-trimester platelet count in pregnant women of advanced maternal age (r = 0.203, P = .013). Multiple linear regression analysis revealed that neonatal birth weight had an independently association with first-trimester platelet count in pregnant women of advanced maternal age (multiple-adjusted r values 0.167, P = .013). First-trimester platelet count is positively associated with neonatal birth weight, suggesting that first-trimester platelet count may be a predictive biomarker for neonatal birth weight in pregnant women of advanced maternal age.