# The Prediction of Pre‐Eclampsia Using Low Fetal Fraction in a Machine Learning Model

## TL;DR

This study shows that a machine learning model can accurately predict pre-eclampsia risk based on low fetal fraction and other factors in prenatal testing.

## Contribution

The study introduces an XGBoost model with high accuracy for early pre-eclampsia prediction using NIPT data.

## Key findings

- Pregnancies with low fetal fraction had a significantly higher risk of pre-eclampsia.
- The XGBoost model achieved 95.6% AUC in predicting pre-eclampsia.
- Systolic and diastolic blood pressure were the top predictors in the model.

## Abstract

To investigate the association between low fetal fraction (FF) in non‐invasive prenatal testing (NIPT) and pregnancy complications or adverse pregnancy outcomes.

Sixty‐four pregnant women undergoing NIPT at the Second Affiliated Hospital of Wenzhou Medical University between 13 June 2019 and 6 January 2023 had an initial NIPT failure due to low FF. Three cases were lost to follow‐up, leaving 61 cases in the failure group (Group A). Group A was subdivided into 37 cases with a valid result after redraw (Group A1) and 24 cases remaining unsuccessful after redraw (Group A2). Concurrently, 119 pregnancies with successful NIPT (normal FF, no fetal chromosomal abnormalities) were randomly selected as controls (Group C). Logistic regression and XGBoost models were established, and their area under the curve (AUC), sensitivity, and specificity were calculated and compared.

The incidence of pre‐eclampsia was significantly higher in Group A than in Group C (p < 0.05). No significant difference in the incidence of pre‐eclampsia was found between Groups A1 and A2. A logistic regression model incorporating FF predicted pre‐eclampsia with an AUC of 0.750 (95% CI: 0.639–0.860), sensitivity of 0.875, and specificity of 0.727. An XGBoost model incorporating 10 factors (FF, age, weight, BMI, gestational age, systolic/diastolic blood pressure at sampling, ART history, delivery history, heparin use history) demonstrated superior performance (AUC = 0.956, 95% CI: 0.868–1.000; accuracy = 0.944). The top three important factors were systolic blood pressure, diastolic blood pressure, and FF.

Low FF in NIPT may indicate an increased risk of pre‐eclampsia. Regardless of the success of redraw, pregnancies with initial NIPT failure due to low FF warrant vigilance for pre‐eclampsia development. The XGBoost machine learning model demonstrates good efficacy for predicting pre‐eclampsia and has potential as an adjunctive prenatal screening tool for early diagnosis.

What's already known about this topic?◦Low FF may be associated with an increased risk of pregnancy complications and adverse outcomes including pre‐eclampsia.What does this study add?◦This study indicates that the XGBoost machine learning model predicted pre‐eclampsia with high accuracy, demonstrating its potential as a beneficial adjunct to prenatal screening for early diagnosis.

What's already known about this topic?

Low FF may be associated with an increased risk of pregnancy complications and adverse outcomes including pre‐eclampsia.

What does this study add?

This study indicates that the XGBoost machine learning model predicted pre‐eclampsia with high accuracy, demonstrating its potential as a beneficial adjunct to prenatal screening for early diagnosis.