A deep feature fusion network for fetal state assessment

PatchCTG: A Patch Cardiotocography Transformer for Antepartum Fetal Health Monitoring

Antepartum Cardiotocography (CTG) is a biomedical sensing technology widely used for fetal health monitoring. While the visual interpretation of CTG traces is highly subjective, with the inter-observer agreement as low as 29% and a false positive rate of approximately 60%, the Dawes-Redman system provides an automated approach to fetal well-being assessments. However, it is primarily designed to rule out adverse outcomes rather than detect them, resulting in a high specificity (90.7%) but low sensitivity (18.2%) in identifying fetal distress. This paper introduces PatchCTG, an AI-enabled biomedical time series transformer for CTG analysis. It employs patch-based tokenisation, instance normalisation, and channel-independent processing to capture essential local and global temporal dependencies within CTG signals. PatchCTG was evaluated on the Oxford Maternity (OXMAT) dataset, which comprises over 20,000 high-quality CTG traces from diverse clinical outcomes, after applying the inclusion and exclusion criteria. With extensive hyperparameter optimisation, PatchCTG achieved an AUC of 0.77, with a specificity of 88% and sensitivity of 57% at Youden's index threshold, demonstrating its adaptability to various clinical needs. Its robust performance across varying temporal thresholds highlights its potential for both real-time and retrospective analysis in sensor-driven fetal monitoring. Testing across varying temporal thresholds showcased it robust predictive performance, particularly with finetuning on data closer to delivery, achieving a sensitivity of 52% and specificity of 88% for near-delivery cases. These findings suggest the potential of PatchCTG to enhance clinical decision-making in antepartum care by providing a sensor-based, AI-driven, objective tool for reliable fetal health assessment.

Comparison and verification of detection accuracy for late deceleration with and without uterine contractions signals using convolutional neural networks

Introduction

Cardiotocography (CTG) is used to monitor and evaluate fetal health by recording the fetal heart rate (FHR) and uterine contractions (UC) over time. Among these, the detection of late deceleration (LD), the early marker of fetal mild hypoxemia, is important, and the temporal relationship between FHR and UC is an essential factor in deciphering it. However, there is a problem with UC signals generally tending to have poor signal quality due to defects in installation or obesity in pregnant women. Since obstetricians evaluate potential LD signals only from the FHR signal when the UC signal quality is poor, we hypothesized that LD could be detected by capturing the morphological features of the FHR signal using Artificial Intelligence (AI). Therefore, this study compares models using FHR only (FHR-only model) and FHR with UC (FHR + UC model) constructed using a Convolutional Neural Network (CNN) to examine whether LD could be detected using only the FHR signal.

Methods

The data used to construct the CNN model were obtained from the publicly available CTU-UHB database. We used 86 cases with LDs and 440 cases without LDs from the database, confirmed by expert obstetricians.

Results

The results showed high accuracy with an area under the curve (AUC) of 0.896 for the FHR-only model and 0.928 for the FHR + UC model. Furthermore, in a validation using 23 cases in which obstetricians judged that the UC signals were poor and the FHR signal had an LD-like morphology, the FHR-only model achieved an AUC of 0.867.

Conclusion

This indicates that using only the FHR signal as input to the CNN could detect LDs and potential LDs with high accuracy. These results are expected to improve fetal outcomes by promptly alerting obstetric healthcare providers to signs of nonreassuring fetal status, even when the UC signal quality is poor, and encouraging them to monitor closely and prepare for emergency delivery.

Machine learning on cardiotocography data to classify fetal outcomes: A scoping review

INTRODUCTION

Uterine contractions during labour constrict maternal blood flow and oxygen delivery to the developing baby, causing transient hypoxia. While most babies are physiologically adapted to withstand such intrapartum hypoxia, those exposed to severe hypoxia or with poor physiological reserves may experience neurological injury or death during labour. Cardiotocography (CTG) monitoring was developed to identify babies at risk of hypoxia by detecting changes in fetal heart rate (FHR) patterns. CTG monitoring is in widespread use in intrapartum care for the detection of fetal hypoxia, but the clinical utility is limited by a relatively poor positive predictive value (PPV) of an abnormal CTG and significant inter and intra observer variability in CTG interpretation. Clinical risk and human factors may impact the quality of CTG interpretation. Misclassification of CTG traces may lead to both under-treatment (with the risk of fetal injury or death) or over-treatment (which may include unnecessary operative interventions that put both mother and baby at risk of complications). Machine learning (ML) has been applied to this problem since early 2000 and has shown potential to predict fetal hypoxia more accurately than visual interpretation of CTG alone. To consider how these tools might be translated for clinical practice, we conducted a review of ML techniques already applied to CTG classification and identified research gaps requiring investigation in order to progress towards clinical implementation.

MATERIALS AND METHOD

We used identified keywords to search databases for relevant publications on PubMed, EMBASE and IEEE Xplore. We used Preferred Reporting Items for Systematic Review and Meta-Analysis for Scoping Reviews (PRISMA-ScR). Title, abstract and full text were screened according to the inclusion criteria.

RESULTS

We included 36 studies that used signal processing and ML techniques to classify CTG. Most studies used an open-access CTG database and predominantly used fetal metabolic acidosis as the benchmark for hypoxia with varying pH levels. Various methods were used to process and extract CTG signals and several ML algorithms were used to classify CTG. We identified significant concerns over the practicality of using varying pH levels as the CTG classification benchmark. Furthermore, studies needed to be more generalised as most used the same database with a low number of subjects for an ML study.

CONCLUSION

ML studies demonstrate potential in predicting fetal hypoxia from CTG. However, more diverse datasets, standardisation of hypoxia benchmarks and enhancement of algorithms and features are needed for future clinical implementation.

A multimodal model in the prediction of the delivery mode using data from a digital twin-empowered labor monitoring system

Objective

This study aims to address the limitations of current clinical methods in predicting delivery mode by constructing a multimodal neural network-based model. The model utilizes data from a digital twin-empowered labor monitoring system, including computerized cardiotocography (cCTG), ultrasound (US) examination data, and electronic health records (EHRs) of pregnant women.

Methods

The model integrates three modalities of data from 105 pregnant women (76 vaginal deliveries and 29 cesarean deliveries) at the Department of Obstetrics and Gynecology of The First Affiliated Hospital of Jinan University, Guangzhou, China. It employs a hybrid architecture of a convolutional neural network (CNN) and bi-directional long short-term memory (BiLSTM) to compress the data into a single feature vector for each patient.

Results

The designed model achieves a cross-validation accuracy of 93.33%, an F1-score of 86.26%, an area under the receiver operating characteristic curve of 97.10%, and a Brier Score of 6.67%. Importantly, while cCTG and EHRs are crucial for labor management, the integration of US imaging data significantly enhances prediction accuracy.

Conclusion

The findings of this study suggest that the developed multimodal model is a promising tool for predicting delivery mode and provides a comprehensive approach to intrapartum maternal and fetal health monitoring. The integration of multi-source data, including real-time information, holds potential for further improving the algorithm's predictive accuracy as the volume of analyzed data increases. This could be highly beneficial for dynamically fusing data from different sources throughout the maternal and fetal health lifecycle, from pregnancy to delivery.