Back to Search Start Over

Distributed Big Data Analytics Method for the Early Prediction of the Neonatal 5-Minute Apgar Score before or during Birth and Ranking the Risk Factors from a National Dataset.

Authors :
Khatibi, Toktam
Farahani, Ali
Sepehri, Mohammad Mehdi
Heidarzadeh, Mohammad
Source :
AI. Jun2022, Vol. 3 Issue 2, p371-389. 19p.
Publication Year :
2022

Abstract

One-minute and five-minute Apgar scores are good measures to assess the health status of newborns. A five-minute Apgar score can predict the risk of some disorders such as asphyxia, encephalopathy, cerebral palsy and ADHD. The early prediction of Apgar score before or during birth and ranking the risk factors can be helpful to manage and reduce the probability of birth producing low Apgar scores. Therefore, the main aim of this study is the early prediction of the neonate 5-min Apgar score before or during birth and ranking the risk factors for a big national dataset using big data analytics methods. In this study, a big dataset including 60 features describing birth cases registered in Iranian maternal and neonatal (IMAN) registry from 1 April 2016 to 1 January 2017 is collected. A distributed big data analytics method for the early prediction of neonate Apgar score and a distributed big data feature ranking method for ranking the predictors of neonate Apgar score are proposed in this study. The main aim of this study is to provide the ability to predict birth cases with low Apgar scores by analyzing the features that describe prenatal properties before or during birth. The top 14 features were identified in this study and used for training the classifiers. Our proposed stack ensemble outperforms the compared classifiers with an accuracy of 99.37 ± 1.06, precision of 99.37 ± 1.06, recall of 99.50 ± 0.61 and F-score of 99.41 ± 0.70 (for confidence interval of 95%) to predict low, moderate and high 5-min Apgar scores. Among the top predictors, fetal height around the baby's head and fetal weight denote fetal growth status. Fetal growth restrictions can lead to low or moderate 5-min Apgar score. Moreover, hospital type and medical science university are healthcare system-related factors that can be managed via improving the quality of healthcare services all over the country. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
26732688
Volume :
3
Issue :
2
Database :
Academic Search Index
Journal :
AI
Publication Type :
Academic Journal
Accession number :
157639204
Full Text :
https://doi.org/10.3390/ai3020023