Classification of Fetal Cardiac Arrhythmia Using Heart Rate Variability and Machine Learning

Fetal arrhythmias can lead to cardiac failure or death; thus, early detection is crucial but challenged by noise and artifacts. This paper investigates fetal arrhythmia detection using time, frequency, and non-linear Heart Rate Variability (HRV) features extracted from fetal ECG signals in the NIFEEG dataset. Machine learning classifiers including Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Decision Tree, XGBoost, Naive Bayes, and Convolutional Neural Network (CNN) are evaluated. The HRV features provide insights into fetal heart rate patterns. While SVM, KNN, Decision Tree, and XGBoost show promise, CNN demonstrates the highest performance with 98.16% accuracy, 100% sensitivity, 96.15% specificity, and 98.11% F1-score. This highlights CNN's potential for early and reliable fetal arrhythmia detection. Statistical analysis supports the significance of HRV features, paving the way for improved prenatal monitoring. To further improve model generalizability, future work should focus on expanding the dataset size, exploring advanced deep neural network architectures such as LSTMs, and integrating supplementary physiological inputs like uterine contractions. Overall, this study demonstrates the capabilities of HRV-based machine learning approaches, especially CNNs, for robust fetal arrhythmia detection, offering valuable clinical implications for early diagnosis and management.