AI-Driven fetal distress monitoring SDN-IoMT networks

Abstract

The healthcare industry is transforming with the integration of the Internet of Medical Things (IoMT) with AI-powered networks for improved clinical connectivity and advanced monitoring capabilities. However, IoMT devices struggle with traditional network infrastructure due to complexity and eterogeneous. Software-defined networking (SDN) is a powerful solution for efficiently managing and controlling IoMT. Additionally, the integration of artificial intelligence such as Deep Learning (DL) algorithms brings intelligence and decision-making capabilities to SDN-IoMT systems. This study focuses on solving the serious problem of information imbalance in cardiotocography (CTG) characteristics with clinical data of pregnant women, especially fetal heart rate (FHR) and deceleration. To improve the performance of prenatal monitoring, this study proposes a framework using Generative Adversarial Networks (GAN), an advanced DL technique, with an auto-encoder model. FHR and deceleration are important markers in CTG monitoring, which are important for assessing fetal health and preventing complications or death. The proposed framework solves the data imbalance problem using reconstruction error and Wasserstein distance-based GANs. The performance of the model is assessed through simulations performed using Mininet, according to criteria such as accuracy, recall, precision and F1 score. The proposed framework outperforms both the basic and advanced DL models and achieves an effective accuracy of 94.2% and an F1 score of 21.1% in very small classes. Validation using the CTU-UHB dataset confirms the significance compared to state-of-the-art solutions for handling unbalanced CTG data. These findings highlight the potential of AI and SDN-based IoMT to improve prenatal outcomes.

Fig 1. The sensing layer gathers data and sends it to the data layer, while the control layer acts as the infrastructure’s central intelligence, overseeing the whole SDN-IoT network.

An example of an SDN-IoMT infrastructure consists of these three layers.

Fig 2. To monitor fetal distress monitoring, many CTG devices are placed in rooms within a distributed SDN-IoT architecture.

After this, the control layer receives the data gathered from these devices for additional processing. We apply a Deep Learning model in this three-layered architecture to identify and categorize anomalies

Fig 3. An actual CTG recording was acquired from a Pakistani hospital located in Islamabad.

Three important data are shown on this CTG: acceleration, baseline variability, and fetal heart rate. All three are within the normal range.

Fig 4. The architecture of the proposed framework.

Fig 5. Creation of a model for tracking fetal health monitoring utilizing an imbalanced CTG dataset, Generative Adversarial Network, and Autoencoder for anomaly detection and classification.

Fig 6. The pre-processing of CTG raw signals [26].

Fig 7. The CNN classifier architecture used in our suggested framework to categorize CTG imbalance data into three groups: abnormal, non-abnormal, and reassuring.

Fig 8. Using the Accuracy metric, three model types—naive deep learning models, advanced deep learning models, and the proposed framework—are compared for the binary classification of normal and abnormal classes in an unbalanced CTG test dataset.

Fig 9. Using the Recall, Precision, and F1-score metrics, three model types are compared: naïve deep learning models, advanced deep learning models, and the proposed framework for binary classification of normal class in an imbalanced CTG test dataset.

Fig 10. Using the Recall, Precision, and F1-score metrics, three model types are compared: naïve deep learning models, advanced deep learning models, and the proposed framework for binary classification of abnormal class in an imbalanced CTG test dataset.

Fig 11. The proposed framework’s confusion matrix on the unbalanced CTG dataset.

Fig 12. ROC analysis of the proposed framework on the imabalnace CTG dataset.

Fig 13. Three types of models are compared using the Accuracy metric for multiclassification in an imbalanced CTG test dataset: basic deep learning models, advanced deep learning models, and the proposed framework.

Fig 14. Using the Recall, Precision, and F1-score metrics, three model types are compared: naïve deep learning models, advanced deep learning models, and the proposed framework for multiclassification of Suspicious minor class in an imbalanced CTG test dataset.

Fig 15. Using the Recall, Precision, and F1-score metrics, three model types—naive deep learning models, advanced deep learning models, and the proposed framework—are compared for multiclassification of the Pathological minor class in an imbalanced CTG test dataset.

The Proposed Framework is indicated here by P.F.

Fig 16. Speed efficiency of the proposed technique in comparison with the baseline deep learning models.