Use of Deep Learning to Detect the Maternal Heart Rate and False Signals on Fetal Heart Rate Recordings

Abstract

We have developed deep learning models for automatic identification of the maternal heart rate (MHR) and, more generally, false signals (FSs) on fetal heart rate (FHR) recordings. The models can be used to preprocess FHR data prior to automated analysis or as a clinical alert system to assist the practitioner. Three models were developed and used to detect (i) FSs on the MHR channel (the FSMHR model), (ii) the MHR and FSs on the Doppler FHR sensor (the FSDop model), and (iii) FSs on the scalp ECG channel (the FSScalp model). The FSDop model was the most useful because FSs are far more frequent on the Doppler FHR channel. All three models were based on a multilayer, symmetric, GRU, and were trained on data recorded during the first and second stages of delivery. The FSMHR and FSDop models were also trained on antepartum recordings. The training dataset contained 1030 expert-annotated periods (mean duration: 36 min) from 635 recordings. In an initial evaluation of routine clinical practice, 30 fully annotated recordings for each sensor type (mean duration: 5 h for MHR and Doppler sensors, and 3 h for the scalp ECG sensor) were analyzed. The sensitivity, positive predictive value (PPV) and accuracy were respectively 62.20%, 87.1% and 99.90% for the FSMHR model, 93.1%, 95.6% and 99.68% for the FSDop model, and 44.6%, 87.2% and 99.93% for the FSScalp model. We built a second test dataset with a more solid ground truth by selecting 45 periods (lasting 20 min, on average) on which the Doppler FHR and scalp ECG signals were recorded simultaneously. Using scalp ECG data, the experts estimated the true FHR value more reliably and thus annotated the Doppler FHR channel more precisely. The models achieved a sensitivity of 53.3%, a PPV of 62.4%, and an accuracy of 97.29%. In comparison, two experts (blinded to the scalp ECG data) respectively achieved a sensitivity of 15.7%, a PPV of 74.3%, and an accuracy of 96.91% and a sensitivity of 60.7%, a PPV of 83.5% and an accuracy of 98.24%. Hence, the models performed at expert level (better than one expert and worse than the other), although a well-trained expert with good knowledge of FSs could probably do better in some cases. The models and datasets have been included in the Fetal Heart Rate Morphological Analysis open-source MATLAB toolbox and can be used freely for research purposes.

Comparison of Machine Learning Algorithms for Heartbeat Detection Based on Accelerometric Signals Produced by a Smart Bed

“…Accurate time positioning of detected peaks is relevant to the evaluation of heart rate variability and in detecting some arrhythmias; hence, we apply the ML algorithms to accomplish precise heartbeat time tracking and evaluate system accuracy on such a basis. This research explores the utilization of both conventional ML and sophisticated Deep Learning (DL—a subset of machine learning methods) [ 31 , 32 , 33 , 34 ] to identify heart pulses.…”

The Development and Implementation of Innovative Blind Source Separation Techniques for Real-Time Extraction and Analysis of Fetal and Maternal Electrocardiogram Signals

“…Subha T.D et al [16] presented a method for extracting fetal electrocardiograms (FECGs) from maternal abdominal signals using an adaptive leastmean-square (LMS) filter, LabVIEW, and Spartan 3 FPGA. Boudet, S. et al [17] developed deep learning models to detect maternal heart rate (MHR) and false signals (FSs) on fetal heart rate (FHR) recordings, achieving good performance levels and integrated these models into an open-source MATLAB toolbox for morphological analysis of fetal heart rates. There are also algorithms based on ANNs designed to process the signal and extract useful information, as in the case of [18,19].…”

Extracting fetal heart signals from Doppler using semi-supervised convolutional neural networks

“…Within obstetrics, some studies have directly assessed fetal hypoxia using CTG input and AI to determine whether the arterial cord blood pH level is below a certain threshold ( Ogasawara et al, 2021 ; Liang Y. et al, 2022 ; Gude and Corns, 2022 ; Spairani et al, 2022 ; Liang and Lu, 2023 ). Other studies have investigated DL models that could determine whether the bpm displayed on CTG is maternal or fetal, which is not supported by existing CTG analysis systems ( Signorini et al, 2003 ; Magawa et al, 2021 ; Boudet et al, 2022 ). In addition, some studies have also used DL models to filter maternal ECG signals and extract fetal ECG signals ( Hasan et al, 2009 ; Fotiadou et al, 2021 ; Ghonchi and Abolghasemi, 2022 ; Mohebbian et al, 2023 ).…”