Highly comparative fetal heart rate analysis

TL;DR

This study analyzes a large fetal heart rate dataset using over 9000 features to identify indicators of low cord pH, aiming to improve real-time labor intervention decisions.

Contribution

It introduces a highly comparative approach that automatically identifies the most informative features for classifying fetal health status from FHR signals.

Findings

Five features best classify low pH vs. normal pH FHR recordings.

Five features strongly correlate with cord pH across the dataset.

Demonstrates the utility of large-scale feature comparison for biomedical signals.

Abstract

A database of fetal heart rate (FHR) time series measured from 7221 patients during labor is analyzed with the aim of learning the types of features of these recordings that are informative of low cord pH. Our 'highly comparative' analysis involves extracting over 9000 time-series analysis features from each FHR time series, including measures of autocorrelation, entropy, distribution, and various model fits. This diverse collection of features was developed in previous work, and is publicly available. We describe five features that most accurately classify a balanced training set of 59 'low pH' and 59 'normal pH' FHR recordings. We then describe five of the features with the strongest linear correlation to cord pH across the full dataset of FHR time series. The features identified in this work may be used as part of a system for guiding intervention during labor in future. This work successfully demonstrates the utility of comparing across a large, interdisciplinary literature on time-series analysis to automatically contribute new scientific results for specific biomedical signal processing challenges.