A Novel Active Learning Technique for Fetal Health Classification Based on XGBoost Classifier

Ensuring safe pregnancy and reducing maternal and infant mortality rates require early prediction of fetal health. The application of machine learning algorithms in monitoring fetal health helps to improve the chances of timely intervention and better outcomes in the event of any possible health issues in fetuses. Existing studies offered to help this issue, typically by training models using a significant portion of the dataset, ranging mainly above 70%. The only existing active learning method in this field employs around 41% training samples to achieve 98% accuracy. This work presents a novel active learning technique to identify the most informative data samples to train a model, leading to high accuracy with a limited number of training samples. It employs a novel query function built upon uncertainty and diversity criteria which are derived based on properties of XGBoost classifier and distance from each other. For deriving uncertainty criterion the soft probabilities obtained for the unlabeled samples are used, while the distance among the uncertain samples in feature space is utilized for deriving diversity criterion. The proposed approach shows superior performance compared to all state-of-the-art methods. Through analysis and experimentation, the proposed solution achieves an accuracy greater than 99% using less than 20% of the dataset for training. This shows its efficacy and potential in the monitoring of fetal health. The code and dataset are available on the GitHub repository https://github.com/niyg7/fetal-health-dataset.