A prospective study on first trimester prediction of ischemic placental diseases

Prediction of Preeclampsia and Intrauterine Growth Restriction: Development of Machine Learning Models on a Prospective Cohort

BACKGROUND

Preeclampsia and intrauterine growth restriction are placental dysfunction-related disorders (PDDs) that require a referral decision be made within a certain time period. An appropriate prediction model should be developed for these diseases. However, previous models did not demonstrate robust performances and/or they were developed from datasets with highly imbalanced classes.

OBJECTIVE

In this study, we developed a predictive model of PDDs by machine learning that uses features at 24-37 weeks' gestation, including maternal characteristics, uterine artery (UtA) Doppler measures, soluble fms-like tyrosine kinase receptor-1 (sFlt-1), and placental growth factor (PlGF).

METHODS

A public dataset was taken from a prospective cohort study that included pregnant women with PDDs (66/95, 69%) and a control group (29/95, 31%). Preliminary selection of features was based on a statistical analysis using SAS 9.4 (SAS Institute). We used Weka (Waikato Environment for Knowledge Analysis) 3.8.3 (The University of Waikato, Hamilton, NZ) to automatically select the best model using its optimization algorithm. We also manually selected the best of 23 white-box models. Models, including those from recent studies, were also compared by interval estimation of evaluation metrics. We used the Matthew correlation coefficient (MCC) as the main metric. It is not overoptimistic to evaluate the performance of a prediction model developed from a dataset with a class imbalance. Repeated 10-fold cross-validation was applied.

RESULTS

The classification via regression model was chosen as the best model. Our model had a robust MCC (.93, 95% CI .87-1.00, vs .64, 95% CI .57-.71) and specificity (100%, 95% CI 100-100, vs 90%, 95% CI 90-90) compared to each metric of the best models from recent studies. The sensitivity of this model was not inferior (95%, 95% CI 91-100, vs 100%, 95% CI 92-100). The area under the receiver operating characteristic curve was also competitive (0.970, 95% CI 0.966-0.974, vs 0.987, 95% CI 0.980-0.994). Features in the best model were maternal weight, BMI, pulsatility index of the UtA, sFlt-1, and PlGF. The most important feature was the sFlt-1/PlGF ratio. This model used an M5P algorithm consisting of a decision tree and four linear models with different thresholds. Our study was also better than the best ones among recent studies in terms of the class balance and the size of the case class (66/95, 69%, vs 27/239, 11.3%).

CONCLUSIONS

Our model had a robust predictive performance. It was also developed to deal with the problem of a class imbalance. In the context of clinical management, this model may improve maternal mortality and neonatal morbidity and reduce health care costs.

Blood-based biomarkers in the maternal circulation associated with fetal growth restriction

Fetal growth restriction (FGR) is associated with threefold to fourfold increased risk of stillbirth. Identifying FGR, through its commonly used surrogate-the small-for-gestational-age (SGA, estimated fetal weight and/or abdominal circumference <10th centile) fetus-and instituting fetal surveillance and timely delivery decrease stillbirth risk. Methods available to clinicians for antenatal identification of SGA fetuses have surprisingly poor sensitivity. About 80% of cases remain undetected. Measuring the symphysis-fundal height detects only 20% of SGA fetuses, and even universal third trimester ultrasound detects, at best, 57% of those born SGA. There is an urgent need to find better ways to identify this at-risk cohort. This review summarises efforts to identify molecular biomarkers (proteins, metabolites, or ribonucleic acids) that could be used to better predict FGR. Most studies examining potential biomarkers to date have utilised case-control study designs without proceeding to validation in independent cohorts. To develop a robust test for FGR, large prospective studies are required with a priori validation plans and cohorts. Given that current clinical care detects 20% of SGA fetuses, even a screening test with ≥60% sensitivity at 90% specificity could be clinically useful, if developed. This may be an achievable aspiration. If discovered, such a test may decrease stillbirth.