Machine Learning Algorithm to Predict Acidemia Using Electronic Fetal Monitoring Recording Parameters.

Javier Esteban-Escaño,Berta Castán,Antonio R Laliena,Sergio Castán,Ricardo Savirón,Luis Mariano Esteban,Gerardo Sanz,Gerardo Sanz-Enguita,Marta Chóliz-Ezquerro,César Asensio

doi:10.3390/e24010068

Abstract

Background: Electronic fetal monitoring (EFM) is the universal method for the surveillance of fetal well-being in intrapartum. Our objective was to predict acidemia from fetal heart signal features using machine learning algorithms. Methods: A case–control 1:2 study was carried out compromising 378 infants, born in the Miguel Servet University Hospital, Spain. Neonatal acidemia was defined as pH < 7.10. Using EFM recording logistic regression, random forest and neural networks models were built to predict acidemia. Validation of models was performed by means of discrimination, calibration, and clinical utility. Results: Best performance was attained using a random forest model built with 100 trees. The discrimination ability was good, with an area under the Receiver Operating Characteristic curve (AUC) of 0.865. The calibration showed a slight overestimation of acidemia occurrence for probabilities above 0.4. The clinical utility showed that for 33% cutoff point, missing 5% of acidotic cases, 46% of unnecessary cesarean sections could be prevented. Logistic regression and neural networks showed similar discrimination ability but with worse calibration and clinical utility. Conclusions: The combination of the variables extracted from EFM recording provided a predictive model of acidemia that showed good accuracy and provides a practical tool to prevent unnecessary cesarean sections.

Highlights

The universal method for the surveillance of intrapartum fetal well-being is the continuous monitoring of fetal heart rate (FHR) and maternal uterine contraction (UC) signals [1]
In the X axis of the graph, we show the predicted probabilities provided by models, for a 60% probability of acidemia, the actual occurrence of acidosis (Y axis) was 40% for logistic regression model, and 30% for neural networks, both models overestimate the real occurrence of acidosis
We found that probabilities of acidemia provided by logistic regression and random forest model are well distributed in a wide range between 0 and 1

Summary

Introduction

The universal method for the surveillance of intrapartum fetal well-being is the continuous monitoring of fetal heart rate (FHR) and maternal uterine contraction (UC) signals [1]. An ultrasound transducer is used for the external FHR monitoring This transducer contains piezoelectric effect crystals that convert electrical energy into ultrasound waves and uses the Doppler effect to detect movements of the cardiac structures [2,3]. Using EFM recording logistic regression, random forest and neural networks models were built to predict acidemia. Logistic regression and neural networks showed similar discrimination ability but with worse calibration and clinical utility. Conclusions: The combination of the variables extracted from EFM recording provided a predictive model of acidemia that showed good accuracy and provides a practical tool to prevent unnecessary cesarean sections

Objectives

Results

Discussion

Conclusion