Intelligent classification of antepartum cardiotocography model based on deep forest

Multicentric intelligent cardiotocography signal interpretation using deep semi-supervised domain adaptation via minimax entropy and domain invariance

BACKGROUND AND OBJECTIVE

Obstetricians use Cardiotocography (CTG), which is the continuous recording of fetal heart rate and uterine contraction, to assess fetal health status. Deep learning models for intelligent fetal monitoring trained on extensively labeled and identically distributed CTG records have achieved excellent performance. However, creation of these training sets requires excessive time and specialist labor for the collection and annotation of CTG signals. Previous research has demonstrated that multicenter studies can improve model performance. However, models trained on cross-domain data may not generalize well to target domains due to variance in distribution among datasets. Hence, this paper conducted a multicenter study with Deep Semi-Supervised Domain Adaptation (DSSDA) for intelligent interpretation of antenatal CTG signals. This approach helps to align cross-domain distribution and transfer knowledge from a label-rich source domain to a label-scarce target domain.

METHODS

We proposed a DSSDA framework that integrated Minimax Entropy and Domain Invariance (DSSDA-MMEDI) to reduce inter-domain gaps and thus achieve domain invariance. The networks were developed using GoogLeNet to extract features from CTG signals, with fully connected, softmax layers for classification. We designed a Dynamic Gradient-driven strategy based on Mutual Information (DGMI) to unify the losses from Minimax Entropy (MME), Domain Invariance (DI), and supervised cross-entropy during iterative learning.

RESULTS

We validated our DSSDA model on two datasets collected from collaborating healthcare institutions and mobile terminals as the source and target domains, which contained 16,355 and 3,351 CTG signals, respectively. Compared to the results achieved with deep learning networks without DSSDA, DSSDA-MMEDI significantly improved sensitivity and F1-score by over 6%. DSSDA-MMEDI also outperformed other state-of-the-art DSSDA approaches for CTG signal interpretation. Ablation studies were performed to determine the unique contribution of each component in our DSSDA mechanism.

CONCLUSIONS

The proposed DSSDA-MMEDI is feasible and effective for alignment of cross-domain data and automated interpretation of multicentric antenatal CTG signals with minimal annotation cost.

Intelligent antepartum fetal monitoring via deep learning and fusion of cardiotocographic signals and clinical data

Purpose

Cardiotocography (CTG), which measures uterine contraction (UC) and fetal heart rate (FHR), is a crucial tool for assessing fetal health during pregnancy. However, traditional computerized cardiotocography (cCTG) approaches have non-negligible calibration errors in feature extraction and heavily rely on the expertise and prior experience to define diagnostic features from CTG or FHR signals. Although previous works have studied deep learning methods for extracting CTG or FHR features, these methods still neglect the clinical information of pregnant women.

Methods

In this paper, we proposed a multimodal deep learning architecture (MMDLA) for intelligent antepartum fetal monitoring that is capable of performing automatic CTG feature extraction, fusion with clinical data and classification. The multimodal feature fusion was achieved by concatenating high-level CTG features, which were extracted from preprocessed CTG signals via a convolution neural network (CNN) with six convolution layers and five fully connected layers, and the clinical data of pregnant women. Eventually, light gradient boosting machine (LGBM) was implemented as fetal status assessment classifier. The effectiveness of MMDLA was evaluated using a dataset of 16,355 cases, each of which includes FHR signal, UC signal and pertinent clinical data like maternal age and gestational age.

Results

With an accuracy of 90.77% and an area under the curve (AUC) value of 0.9201, the multimodal features performed admirably. The data imbalance issue was also effectively resolved by the LGBM classifier, with a normal-F1 value of 0.9376 and an abnormal-F1 value of 0.8223.

Conclusion

In summary, the proposed MMDLA is conducive to the realization of intelligent antepartum fetal monitoring.

Optimizing fetal health prediction: Ensemble modeling with fusion of feature selection and extraction techniques for cardiotocography data

Cardiotocography (CTG) captured the fetal heart rate and the timing of uterine contractions. Throughout pregnancy, CTG intelligent categorization is crucial for monitoring fetal health and preserving proper fetal growth and development. Since CTG provides information on the fetal heartbeat and uterus contractions, which helps determine if the fetus is pathologic or not, obstetricians frequently use it to evaluate a child's physical health during pregnancy. In the past, obstetricians have artificially analyzed CTG data, which is time-consuming and inaccurate. So, developing a fetal health categorization model is crucial as it may help to speed up the diagnosis and treatment and conserve medical resources. The CTG dataset is used in this study. To diagnose the illness, 7 machine learning models are employed, as well as ensemble strategies including voting and stacking classifiers. In order to choose and extract the most significant and critical attributes from the dataset, Feature Selection (FS) techniques like ANOVA and Chi-square, as well as Feature Extraction (FE) strategies like Principal Component Analysis (PCA) and Independent Component Analysis (ICA), are being used. We used the Synthetic Minority Oversampling Technique (SMOTE) approach to balance the dataset because it is unbalanced. In order to forecast the illness, the top 5 models are selected, and these 5 models are used in ensemble methods such as voting and stacking classifiers. The utilization of Stacking Classifiers (SC), which involve Adaboost and Random Forest (RF) as meta-classifiers for disease detection. The performance of the proposed SC with meta-classifier as RF model, which incorporates Chi-square with PCA, outperformed all other state-of-the-art models, achieving scores of 98.79%,98.88%,98.69%,96.32%, and 98.77% for accuracy, precision, recall, specificity, and f1-score respectively.

A hybrid stacked ensemble and Kernel SHAP-based model for intelligent cardiotocography classification and interpretability

BACKGROUND

Intelligent cardiotocography (CTG) classification can assist obstetricians in evaluating fetal health. However, high classification performance is often achieved by complex machine learning (ML)-based models, which causes interpretability concerns. The trade-off between accuracy and interpretability makes it challenging for most existing ML-based CTG classification models to popularize in prenatal clinical applications.

METHODS

Aiming to improve CTG classification performance and prediction interpretability, a hybrid model was proposed using a stacked ensemble strategy with mixed features and Kernel SHapley Additive exPlanations (SHAP) framework. Firstly, the stacked ensemble classifier was established by employing support vector machines (SVM), extreme gradient boosting (XGB), and random forests (RF) as base learners, and backpropagation (BP) as a meta learner whose input was mixed with the CTG features and the probability value of each category output by base learners. Then, the public and private CTG datasets were used to verify the discriminative performance. Furthermore, Kernel SHAP was applied to estimate the contribution values of features and their relationships to the fetal states.

RESULTS

For intelligent CTG classification using 10-fold cross-validation, the accuracy and average F1 score were 0.9539 and 0.9249 in the public dataset, respectively; and those were 0.9201 and 0.8926 in the private dataset, respectively. For interpretability, the explanation results indicated that accelerations (AC) and the percentage of time with abnormal short-term variability (ASTV) were the key determinants. Specifically, the probability of abnormality increased and that of the normal state decreased as the value of ASTV grew. In addition, the likelihood of the normal status rose with the increase of AC.

CONCLUSIONS

The proposed model has high classification performance and reasonable interpretability for intelligent fetal monitoring.

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.

Multimodal learning for fetal distress diagnosis using a multimodal medical information fusion framework

Cardiotocography (CTG) monitoring is an important medical diagnostic tool for fetal well-being evaluation in late pregnancy. In this regard, intelligent CTG classification based on Fetal Heart Rate (FHR) signals is a challenging research area that can assist obstetricians in making clinical decisions, thereby improving the efficiency and accuracy of pregnancy management. Most existing methods focus on one specific modality, that is, they only detect one type of modality and inevitably have limitations such as incomplete or redundant source domain feature extraction, and poor repeatability. This study focuses on modeling multimodal learning for Fetal Distress Diagnosis (FDD); however, exists three major challenges: unaligned multimodalities; failure to learn and fuse the causality and inclusion between multimodal biomedical data; modality sensitivity, that is, difficulty in implementing a task in the absence of modalities. To address these three issues, we propose a Multimodal Medical Information Fusion framework named MMIF, where the Category Constrained-Parallel ViT model (CCPViT) was first proposed to explore multimodal learning tasks and address the misalignment between multimodalities. Based on CCPViT, a cross-attention-based image-text joint component is introduced to establish a Multimodal Representation Alignment Network model (MRAN), explore the deep-level interactive representation between cross-modal data, and assist multimodal learning. Furthermore, we designed a simple-structured FDD test model based on the highly modal alignment MMIF, realizing task delegation from multimodal model training (image and text) to unimodal pathological diagnosis (image). Extensive experiments, including model parameter sensitivity analysis, cross-modal alignment assessment, and pathological diagnostic accuracy evaluation, were conducted to show our models’ superior performance and effectiveness.

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.

Classification of Cardiotocography Based on the Apriori Algorithm and Multi-Model Ensemble Classifier

Cardiotocography (CTG) recorded fetal heart rate and its temporal relationship with uterine contractions. CTG intelligent classification plays an important role in evaluating fetal health and protecting fetal normal growth and development throughout pregnancy. At the feature selection level, this study uses the Apriori algorithm to search frequent item sets for feature extraction. At the level of the classification model, the combination model of AdaBoost and random forest with the highest classification accuracy is finally selected by comparing various models. The suspicious class data in the CTG data set affect the overall classification accuracy. The number of suspicious class data is predicted by the multi-model ensemble method. Finally, the data set is fused from three classifications to two classifications. The classification accuracy is 0.976, and the AUC is 0.98, which significantly improves the classification effect. In conclusion, the method used in this study has high accuracy in model classification, which is helpful to improve the accuracy of fetal abnormality detection.