Deep neural network-based classification of cardiotocograms outperformed conventional algorithms

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

Cardiotocography (CTG) measurements are critical for assessing fetal wellbeing during monitoring, and accurate assessment requires well-traceable CTG signals. The current FHR calculation algorithm, based on autocorrelation to Doppler ultrasound (DUS) signals, often results in periods of loss owing to its inability to differentiate signals. We hypothesized that classifying DUS signals by type could be a solution and proposed that an artificial intelligence (AI)-based approach could be used for classification. However, limited studies have incorporated the use of AI for DUS signals because of the limited data availability. Therefore, this study focused on evaluating the effectiveness of semi-supervised learning in enhancing classification accuracy, even in limited datasets, for DUS signals. Data comprising fetal heartbeat, artifacts, and two other categories were created from non-stress tests and labor DUS signals. With labeled and unlabeled data totaling 9,600 and 48,000 data points, respectively, the semi-supervised learning model consistently outperformed the supervised learning model, achieving an average classification accuracy of 80.9%. The preliminary findings indicate that applying semi-supervised learning to the development of AI models using DUS signals can achieve high generalization accuracy and reduce the effort. This approach may enhance the quality of fetal monitoring.

Rapid detection of fetal compromise using input length invariant deep learning on fetal heart rate signals

Standard clinical practice to assess fetal well-being during labour utilises monitoring of the fetal heart rate (FHR) using cardiotocography. However, visual evaluation of FHR signals can result in subjective interpretations leading to inter and intra-observer disagreement. Therefore, recent studies have proposed deep-learning-based methods to interpret FHR signals and detect fetal compromise. These methods have typically focused on evaluating fixed-length FHR segments at the conclusion of labour, leaving little time for clinicians to intervene. In this study, we propose a novel FHR evaluation method using an input length invariant deep learning model (FHR-LINet) to progressively evaluate FHR as labour progresses and achieve rapid detection of fetal compromise. Using our FHR-LINet model, we obtained approximately 25% reduction in the time taken to detect fetal compromise compared to the state-of-the-art multimodal convolutional neural network while achieving 27.5%, 45.0%, 56.5% and 65.0% mean true positive rate at 5%, 10%, 15% and 20% false positive rate respectively. A diagnostic system based on our approach could potentially enable earlier intervention for fetal compromise and improve clinical outcomes.

Intrapartum electronic fetal heart rate monitoring to predict acidemia at birth with the use of deep learning

BACKGROUND

Electronic fetal monitoring is used in most US hospital births but has significant limitations in achieving its intended goal of preventing intrapartum hypoxic-ischemic injury. Novel deep learning techniques can improve complex data processing and pattern recognition in medicine.

OBJECTIVE

This study aimed to apply deep learning approaches to develop and validate a model to predict fetal acidemia from electronic fetal monitoring data.

STUDY DESIGN

The database was created using intrapartum electronic fetal monitoring data from 2006 to 2020 from a large, multisite academic health system. Data were divided into training and testing sets with equal distribution of acidemic cases. Several different deep learning architectures were explored. The primary outcome was umbilical artery acidemia, which was investigated at 4 clinically meaningful thresholds: 7.20, 7.15, 7.10, and 7.05, along with base excess. The receiver operating characteristic curves were generated with the area under the receiver operating characteristic assessed to determine the performance of the models. External validation was performed using a publicly available Czech database of electronic fetal monitoring data.

RESULTS

A total of 124,777 electronic fetal monitoring files were available, of which 77,132 had <30% missingness in the last 60 minutes of the electronic fetal monitoring tracing. Of these, 21,041 were matched to a corresponding umbilical cord gas result, of which 10,182 were time-stamped within 30 minutes of the last electronic fetal monitoring reading and composed the final dataset. The prevalence rates of the outcomes in the data were 20.9% with a pH of <7.2, 9.1% with a pH of <7.15, 3.3% with a pH of <7.10, and 1.3% with a pH of <7.05. The best performing model achieved an area under the receiver operating characteristic of 0.85 at a pH threshold of <7.05. When predicting the joint outcome of both pH of <7.05 and base excess of less than -10 meq/L, an area under the receiver operating characteristic of 0.89 was achieved. When predicting both pH of <7.20 and base excess of less than -10 meq/L, an area under the receiver operating characteristic of 0.87 was achieved. At a pH of <7.15 and a positive predictive value of 30%, the model achieved a sensitivity of 90% and a specificity of 48%.

CONCLUSION

The application of deep learning methods to intrapartum electronic fetal monitoring analysis achieves promising performance in predicting fetal acidemia. This technology could help improve the accuracy and consistency of electronic fetal monitoring interpretation.

Computer Vision for Identification of Increased Fetal Heart Variability in Cardiotocogram

INTRODUCTION

Increased fetal heart rate variability (IFHRV), defined as fetal heart rate (FHR) baseline amplitude changes of >25 beats per minute with a duration of ≥1 min, is an early sign of intrapartum fetal hypoxia. This study evaluated the level of agreement of machine learning (ML) algorithms-based recognition of IFHRV patterns with expert analysis.

METHODS

Cardiotocographic recordings and cardiotocograms from 4,988 singleton term childbirths were evaluated independently by two expert obstetricians blinded to the outcomes. Continuous FHR monitoring with computer vision analysis was compared with visual analysis by the expert obstetricians. FHR signals were graphically processed and measured by the computer vision model labeled SALKA.

RESULTS

In visual analysis, IFHRV pattern occurred in 582 cardiotocograms (11.7%). Compared with visual analysis, SALKA recognized IFHRV patterns with an average Cohen's kappa coefficient of 0.981 (95% CI: 0.972-0.993). The sensitivity of SALKA was 0.981, the positive predictive rate was 0.822 (95% CI: 0.774-0.903), and the false-negative rate was 0.01 (95% CI: 0.00-0.02). The agreement between visual analysis and SALKA in identification of IFHRV was almost perfect (0.993) in cases (N = 146) with neonatal acidemia (i.e., umbilical artery pH <7.10).

CONCLUSIONS

Computer vision analysis by SALKA is a novel ML technique that, with high sensitivity and specificity, identifies IFHRV features in intrapartum cardiotocograms. SALKA recognizes potential early signs of fetal distress close to those of expert obstetricians, particularly in cases of neonatal acidemia.

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.

The Effect of Fetal Heart Rate Segment Selection on Deep Learning Models for Fetal Compromise Detection

Monitoring the fetal heart rate (FHR) is common practice in obstetric care to assess the risk of fetal compromise. Unfortunately, human interpretation of FHR recordings is subject to inter-observer variability with high false positive rates. To improve the performance of fetal compromise detection, deep learning methods have been proposed to automatically interpret FHR recordings. However, existing deep learning methods typically analyse a fixed-length segment of the FHR recording after removing signal gaps, where the influence of this segment selection process has not been comprehensively assessed. In this work, we develop a novel input length invariant deep learning model to determine the effect of FHR segment selection for detecting fetal compromise. Using this model, we perform five times repeated five-fold cross-validation on an open-access database of 552 FHR recordings and assess model performance for FHR segment lengths between 15 and 60 minutes. We show that the performance after removing signal gaps improves with increasing segment length from 15 minutes (AUC = 0.50) to 60 minutes (AUC = 0.74). Additionally, we demonstrate that using FHR segments without removing signal gaps achieves superior performance across signal lengths from 15 minutes (AUC = 0.68) to 60 minutes (AUC = 0.76). These results show that future works should carefully consider FHR segment selection and that removing signal gaps might contribute to the loss of valuable information.

Prediction of Fetal Blood Pressure during Labour with Deep Learning Techniques

Our objective is to develop a model for the prediction of minimum fetal blood pressure (FBP) during fetal heart rate (FHR) decelerations. Experimental data from umbilical occlusions in near-term fetal sheep (2698 occlusions from 57 near-term lambs) were used to train a convolutional neural network. This model was then used to estimate FBP for decelerations extracted from the final 90 min of 53,445 human FHR signals collected using cardiotocography. Minimum sheep FBP was predicted with a mean absolute error of 6.7 mmHg (25th, 50th, 75th percentiles of 2.3, 5.2, 9.7 mmHg), mean absolute percentage errors of 17.3% (5.5%, 12.5%, 23.9%) and a coefficient of determination R2=0.36. While the model was unable to clearly predict severe compromise at birth in humans, there is positive evidence that such a model could predict human FBP with further development. The neural network is capable of predicting FBP for many of the sheep decelerations accurately but performed far from satisfactory at identifying FHR segments that correspond to the highest or lowest minimum FBP. These results indicate that with further work and a larger, more variable training dataset, the model could achieve higher accuracy.

Multimodal Deep Learning for Predicting Adverse Birth Outcomes Based on Early Labour Data

Cardiotocography (CTG) is a widely used technique to monitor fetal heart rate (FHR) during labour and assess the health of the baby. However, visual interpretation of CTG signals is subjective and prone to error. Automated methods that mimic clinical guidelines have been developed, but they failed to improve detection of abnormal traces. This study aims to classify CTGs with and without severe compromise at birth using routinely collected CTGs from 51,449 births at term from the first 20 min of FHR recordings. Three 1D-CNN and LSTM based architectures are compared. We also transform the FHR signal into 2D images using time-frequency representation with a spectrogram and scalogram analysis, and subsequently, the 2D images are analysed using a 2D-CNNs. In the proposed multi-modal architecture, the 2D-CNN and the 1D-CNN-LSTM are connected in parallel. The models are evaluated in terms of partial area under the curve (PAUC) between 0-10% false-positive rate; and sensitivity at 95% specificity. The 1D-CNN-LSTM parallel architecture outperformed the other models, achieving a PAUC of 0.20 and sensitivity of 20% at 95% specificity. Our future work will focus on improving the classification performance by employing a larger dataset, analysing longer FHR traces, and incorporating clinical risk factors.

DeepCTG® 1.0: an interpretable model to detect fetal hypoxia from cardiotocography data during labor and delivery

Introduction

Cardiotocography, which consists in monitoring the fetal heart rate as well as uterine activity, is widely used in clinical practice to assess fetal wellbeing during labor and delivery in order to detect fetal hypoxia and intervene before permanent damage to the fetus. We present DeepCTG® 1.0, a model able to predict fetal acidosis from the cardiotocography signals.

Materials and methods

DeepCTG® 1.0 is based on a logistic regression model fed with four features extracted from the last available 30 min segment of cardiotocography signals: the minimum and maximum values of the fetal heart rate baseline, and the area covered by accelerations and decelerations. Those four features have been selected among a larger set of 25 features. The model has been trained and evaluated on three datasets: the open CTU-UHB dataset, the SPaM dataset and a dataset built in hospital Beaujon (Clichy, France). Its performance has been compared with other published models and with nine obstetricians who have annotated the CTU-UHB cases. We have also evaluated the impact of two key factors on the performance of the model: the inclusion of cesareans in the datasets and the length of the cardiotocography segment used to compute the features fed to the model.

Results

The AUC of the model is 0.74 on the CTU-UHB and Beaujon datasets, and between 0.77 and 0.87 on the SPaM dataset. It achieves a much lower false positive rate (12% vs. 25%) than the most frequent annotation among the nine obstetricians for the same sensitivity (45%). The performance of the model is slightly lower on the cesarean cases only (AUC = 0.74 vs. 0.76) and feeding the model with shorter CTG segments leads to a significant decrease in its performance (AUC = 0.68 with 10 min segments).

Discussion

Although being relatively simple, DeepCTG® 1.0 reaches a good performance: it compares very favorably to clinical practice and performs slightly better than other published models based on similar approaches. It has the important characteristic of being interpretable, as the four features it is based on are known and understood by practitioners. The model could be improved further by integrating maternofetal clinical factors, using more advanced machine learning or deep learning approaches and having a more robust evaluation of the model based on a larger dataset with more pathological cases and covering more maternity centers.

Fetal Health Classification from Cardiotocograph for Both Stages of Labor-A Soft-Computing-Based Approach

To date, cardiotocography (CTG) is the only non-invasive and cost-effective tool available for continuous monitoring of the fetal health. In spite of a marked growth in the automation of the CTG analysis, it still remains a challenging signal processing task. Complex and dynamic patterns of fetal heart are poorly interpreted. Particularly, the precise interpretation of the suspected cases is fairly low by both visual and automated methods. Also, the first and second stage of labor produce very different fetal heart rate (FHR) dynamics. Thus, a robust classification model takes both stages into consideration separately. In this work, the authors propose a machine-learning-based model, which was applied separately to both the stages of labor, using standard classifiers such as SVM, random forest (RF), multi-layer perceptron (MLP), and bagging to classify the CTG. The outcome was validated using the model performance measure, combined performance measure, and the ROC-AUC. Though AUC-ROC was sufficiently high for all the classifiers, the other parameters established a better performance by SVM and RF. For suspicious cases the accuracies of SVM and RF were 97.4% and 98%, respectively, whereas sensitivity was 96.4% and specificity was 98% approximately. In the second stage of labor the accuracies were 90.6% and 89.3% for SVM and RF, respectively. Limits of agreement for 95% between the manual annotation and the outcome of SVM and RF were (-0.05 to 0.01) and (-0.03 to 0.02). Henceforth, the proposed classification model is efficient and can be integrated into the automated decision support system.

Detection of Suspicious Cardiotocographic Recordings by Means of a Machine Learning Classifier

Cardiotocography (CTG) is one of the fundamental prenatal diagnostic methods for both antepartum and intrapartum fetal surveillance. Although it has allowed a significant reduction in intrapartum and neonatal mortality and morbidity, its diagnostic accuracy is, however, still far from being fully satisfactory. In particular, the identification of uncertain and suspicious CTG traces remains a challenging task for gynecologists. The introduction of computerized analysis systems has enabled more objective evaluations, possibly leading to more accurate diagnoses. In this work, the problem of classifying suspicious CTG recordings was addressed through a machine learning approach. A machine-based labeling was proposed, and a binary classification was carried out using a support vector machine (SVM) classifier to distinguish between suspicious and normal CTG traces. The best classification metrics showed accuracy, sensitivity, and specificity values of 92%, 92%, and 90%, respectively. The main results were compared both with results obtained by considering a more unbalanced dataset and with relevant literature studies in the field. The use of the SVM proved to be promising in the field of CTG classification. However, appropriate feature selection and dataset balancing are crucial to achieve satisfactory performance of the classifier.

Applications of artificial intelligence in obstetrics

Artificial intelligence, which has been applied as an innovative technology in multiple fields of healthcare, analyzes large amounts of data to assist in disease prediction, prevention, and diagnosis, as well as in patient monitoring. In obstetrics, artificial intelligence has been actively applied and integrated into our daily medical practice. This review provides an overview of artificial intelligence systems currently used for obstetric diagnostic purposes, such as fetal cardiotocography, ultrasonography, and magnetic resonance imaging, and demonstrates how these methods have been developed and clinically applied.

Computerized cardiotocography analysis during labor - A state-of-the-art review

Cardiotocography is defined as the recording of fetal heart rate and uterine contractions and is widely used during labor as a screening tool to determine fetal wellbeing. The visual interpretation of the cardiotocography signals by the practitioners, following common guidelines, is subject to a high interobserver variability, and the efficiency of cardiotocography monitoring is still debated. Since the 1990s, researchers and practitioners work on designing reliable computer-aided systems to assist practitioners in cardiotocography interpretation during labor. Several systems are integrated in the monitoring devices, mostly based on the guidelines, but they have not clearly demonstrated yet their usefulness. In the last decade, the availability of large clinical databases as well as the emergence of machine learning and deep learning methods in healthcare has led to a surge of studies applying those methods to cardiotocography signals analysis. The state-of-the-art systems perform well to detect fetal hypoxia when evaluated on retrospective cohorts, but several challenges remain to be tackled before they can be used in clinical practice. First, the development and sharing of large, open and anonymized multicentric databases of perinatal and cardiotocography data during labor is required to build more accurate systems. Also, the systems must produce interpretable indicators along with the prediction of the risk of fetal hypoxia in order to be appropriated and trusted by practitioners. Finally, common standards should be built and agreed on to evaluate and compare those systems on retrospective cohorts and to validate their use in clinical practice.

Deep learning based fetal distress detection from time frequency representation of cardiotocogram signal using Morse wavelet: research study

Background

Clinically cardiotocography is a technique which is used to monitor and evaluate the level of fetal distress. Even though, CTG is the most widely used device to monitor determine the fetus health, existence of high false positive result from the visual interpretation has a significant contribution to unnecessary surgical delivery or delayed intervention.

Objective

In the current study an innovative computer aided fetal distress diagnosing model is developed by using time frequency representation of FHR signal using generalized Morse wavelet and the concept of transfer learning of pre-trained ResNet 50 deep neural network model.

Method

From the CTG data that is obtained from the only open access CTU-UHB data base only FHR signal is extracted and preprocessed to remove noises and spikes. After preprocessing the time frequency information of FHR signal is extracted by using generalized Morse wavelet and fed to a pre-trained ResNet 50 model which is fine tuned and configured according to the dataset.

Main outcome measures

Sensitivity (Se), specificity (Sp) and accuracy (Acc) of the model adopted from binary confusion matrix is used as outcome measures.

Result

After successfully training the model, a comprehensive experimentation of testing is conducted for FHR data for which a recording is made during early stage of labor and last stage of labor. Thus, a promising classification result which is accuracy of 98.7%, sensitivity of 97.0% and specificity 100% are achieved for FHR signal of 1st stage of labor. For FHR recorded in last stage of labor, accuracy of 96.1%, sensitivity of 94.1% and specificity 97.7% are achieved.

Conclusion

The developed model can be used as a decision-making aid system for obstetrician and gynecologist.

A deep feature fusion network for fetal state assessment

CTG (cardiotocography) has consistently been used to diagnose fetal hypoxia. It is susceptible to identifying the average fetal acid-base balance but lacks specificity in recognizing prenatal acidosis and neurological impairment. CTG plays a vital role in intrapartum fetal state assessment, which can prevent severe organ damage if fetal hypoxia is detected earlier. In this paper, we propose a novel deep feature fusion network (DFFN) for fetal state assessment. First, we extract spatial and temporal information from the fetal heart rate (FHR) signal using a multiscale CNN-BiLSTM network, increasing the features' diversity. Second, the multiscale CNN-BiLSM network and frequently used features are integrated into the deep learning model. The proposed DFFN model combines different features to improve classification accuracy. The multiscale convolutional kernels can identify specific essential information and consider signal's temporal information. The proposed method achieves 61.97%, 73.82%, and 66.93% of sensitivity, specificity, and quality index, respectively, on the public CTU-UHB database. The proposed method achieves the highest QI on the private database, verifying the proposed method's effectiveness and generalization. The proposed DFFN combines the advantages of feature engineering and deep learning models and achieves competitive accuracy in fetal state assessment compared with related works.

Accessing Artificial Intelligence for Fetus Health Status Using Hybrid Deep Learning Algorithm (AlexNet-SVM) on Cardiotocographic Data

Artificial intelligence is serving as an impetus in digital health, clinical support, and health informatics for an informed patient’s outcome. Previous studies only consider classification accuracies of cardiotocographic (CTG) datasets and disregard computational time, which is a relevant parameter in a clinical environment. This paper proposes a modified deep neural algorithm to classify untapped pathological and suspicious CTG recordings with the desired time complexity. In our newly developed classification algorithm, AlexNet architecture is merged with support vector machines (SVMs) at the fully connected layers to reduce time complexity. We used an open-source UCI (Machine Learning Repository) dataset of cardiotocographic (CTG) recordings. We divided 2126 CTG recordings into 3 classes (Normal, Pathological, and Suspected), including 23 attributes that were dynamically programmed and fed to our algorithm. We employed a deep transfer learning (TL) mechanism to transfer prelearned features to our model. To reduce time complexity, we implemented a strategy wherein layers in the convolutional base were partially trained to leave others in the frozen states. We used an ADAM optimizer for the optimization of hyperparameters. The presented algorithm also outperforms the leading architectures (RCNNs, ResNet, DenseNet, and GoogleNet) with respect to real-time accuracies, sensitivities, and specificities of 99.72%, 96.67%, and 99.6%, respectively, making it a viable candidate for clinical settings after real-time validation.

Challenges of Developing Robust AI for Intrapartum Fetal Heart Rate Monitoring

Background: CTG remains the only non-invasive tool available to the maternity team for continuous monitoring of fetal well-being during labour. Despite widespread use and investment in staff training, difficulty with CTG interpretation continues to be identified as a problem in cases of fetal hypoxia, which often results in permanent brain injury. Given the recent advances in AI, it is hoped that its application to CTG will offer a better, less subjective and more reliable method of CTG interpretation. Objectives: This mini-review examines the literature and discusses the impediments to the success of AI application to CTG thus far. Prior randomised control trials (RCTs) of CTG decision support systems are reviewed from technical and clinical perspectives. A selection of novel engineering approaches, not yet validated in RCTs, are also reviewed. The review presents the key challenges that need to be addressed in order to develop a robust AI tool to identify fetal distress in a timely manner so that appropriate intervention can be made. Results: The decision support systems used in three RCTs were reviewed, summarising the algorithms, the outcomes of the trials and the limitations. Preliminary work suggests that the inclusion of clinical data can improve the performance of AI-assisted CTG. Combined with newer approaches to the classification of traces, this offers promise for rewarding future development.