Apgar score is a test applied 1 minute after birth to check the infant health and can be performed as much as needed. The goal of this paper is to apply a deep learning (DL) method called convolutional neural network (CNN) to predict infants with potentially low Apgar score. Our CNN is a multi-input model that accepts denoised cardiotocography (CTG) images and gestational age. In the first half of the paper, we use basic machine learning (ML) techniques to explore what features and target labels are most effective. In the latter half, we verify to what extent the prediction accuracies can be improved by using our CNN model. Using 5-folds cross validation (CV), the CNN model performance scored an Area Under Curve (AUC) of 0.958 when classifying infants with Apgar score 5 minutes < 7 and AUC of 0.955 if Apgar score 1 or 5 minutes < 6 without using feature extraction algorithms. We conclude that the built model can be utilized as a prognosis tool to predict fetuses with a low Apgar score. Still, we think that a one model isn't enough as obstetricians could benefit more from multiple models that help predict different risks to fetuses.
Cardiotocography (CTG) has been widely used to promote newborn prognosis and has saved a vast number of pregnancies worldwide. The efficacy of this method which depends on real-time diagnosis has not changed for half a century. However, the establishment the computational diagnosis method of CTG with Artificial intelligence (AI) had been required to prevent misinterpretation and lessness of medical resource. Experimental and retrospective studies to estimate the efficiency of AI diagnosis and how it contributes to human diagnosis have thus far only been implemented using small cohorts. The usage of previously developed machine learning (ML) and deep learning (DL) methods has generated areas under the curve (AUC) of 0.730 and 0.949, respectively. In this study, diagnoses based on human judgement were collected from obstetricians and midwives. Neither ML nor DL could reach the high performance of humans. However, an aggregation analysis model mimicking the corroboration of newborn asphyxia predictions by human judgment and DL showed higher specificity and accuracy, though the AUC of receiver operating characteristics analyses were still lower than those with humans alone. While further data accumulation and analyses are necessary to increase the accuracy of these methods, they bear the promise of constituting a helpful tool for the safe management of delivery.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.