Ensemble learning for the early prediction of neonatal jaundice with genetic features

Abstract Background Neonatal jaundice may cause severe neurological damage if poorly evaluated and diagnosed when high bilirubin occurs. The study explored how to effectively integrate high-dimensional genetic features into predicting neonatal jaundice. Methods This study recruited 984 neonates from...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Haowen Deng, Youyou Zhou, Lin Wang, Cheng Zhang
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Hyperbilirubinemia Machine learning Genetic variants Transcutaneous bilirubin Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/9d0f4e1f5b704a18a682f988c3196f40
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9d0f4e1f5b704a18a682f988c3196f40
record_format	dspace
spelling	oai:doaj.org-article:9d0f4e1f5b704a18a682f988c3196f402021-12-05T12:19:00ZEnsemble learning for the early prediction of neonatal jaundice with genetic features10.1186/s12911-021-01701-91472-6947https://doaj.org/article/9d0f4e1f5b704a18a682f988c3196f402021-12-01T00:00:00Zhttps://doi.org/10.1186/s12911-021-01701-9https://doaj.org/toc/1472-6947Abstract Background Neonatal jaundice may cause severe neurological damage if poorly evaluated and diagnosed when high bilirubin occurs. The study explored how to effectively integrate high-dimensional genetic features into predicting neonatal jaundice. Methods This study recruited 984 neonates from the Suzhou Municipal Central Hospital in China, and applied an ensemble learning approach to enhance the prediction of high-dimensional genetic features and clinical risk factors (CRF) for physiological neonatal jaundice of full-term newborns within 1-week after birth. Further, sigmoid recalibration was applied for validating the reliability of our methods. Results The maximum accuracy of prediction reached 79.5% Area Under Curve (AUC) by CRF and could be marginally improved by 3.5% by including genetic variant (GV). Feature importance illustrated that 36 GVs contributed 55.5% in predicting neonatal jaundice in terms of gain from splits. Further analysis revealed that the main contribution of GV was to reduce the false-positive rate, i.e., to increase the specificity in the prediction. Conclusions Our study shed light on the theoretical and practical value of GV in the prediction of neonatal jaundice.Haowen DengYouyou ZhouLin WangCheng ZhangBMCarticleHyperbilirubinemiaMachine learningGenetic variantsTranscutaneous bilirubinComputer applications to medicine. Medical informaticsR858-859.7ENBMC Medical Informatics and Decision Making, Vol 21, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Hyperbilirubinemia Machine learning Genetic variants Transcutaneous bilirubin Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Hyperbilirubinemia Machine learning Genetic variants Transcutaneous bilirubin Computer applications to medicine. Medical informatics R858-859.7 Haowen Deng Youyou Zhou Lin Wang Cheng Zhang Ensemble learning for the early prediction of neonatal jaundice with genetic features
description	Abstract Background Neonatal jaundice may cause severe neurological damage if poorly evaluated and diagnosed when high bilirubin occurs. The study explored how to effectively integrate high-dimensional genetic features into predicting neonatal jaundice. Methods This study recruited 984 neonates from the Suzhou Municipal Central Hospital in China, and applied an ensemble learning approach to enhance the prediction of high-dimensional genetic features and clinical risk factors (CRF) for physiological neonatal jaundice of full-term newborns within 1-week after birth. Further, sigmoid recalibration was applied for validating the reliability of our methods. Results The maximum accuracy of prediction reached 79.5% Area Under Curve (AUC) by CRF and could be marginally improved by 3.5% by including genetic variant (GV). Feature importance illustrated that 36 GVs contributed 55.5% in predicting neonatal jaundice in terms of gain from splits. Further analysis revealed that the main contribution of GV was to reduce the false-positive rate, i.e., to increase the specificity in the prediction. Conclusions Our study shed light on the theoretical and practical value of GV in the prediction of neonatal jaundice.
format	article
author	Haowen Deng Youyou Zhou Lin Wang Cheng Zhang
author_facet	Haowen Deng Youyou Zhou Lin Wang Cheng Zhang
author_sort	Haowen Deng
title	Ensemble learning for the early prediction of neonatal jaundice with genetic features
title_short	Ensemble learning for the early prediction of neonatal jaundice with genetic features
title_full	Ensemble learning for the early prediction of neonatal jaundice with genetic features
title_fullStr	Ensemble learning for the early prediction of neonatal jaundice with genetic features
title_full_unstemmed	Ensemble learning for the early prediction of neonatal jaundice with genetic features
title_sort	ensemble learning for the early prediction of neonatal jaundice with genetic features
publisher	BMC
publishDate	2021
url	https://doaj.org/article/9d0f4e1f5b704a18a682f988c3196f40
work_keys_str_mv	AT haowendeng ensemblelearningfortheearlypredictionofneonataljaundicewithgeneticfeatures AT youyouzhou ensemblelearningfortheearlypredictionofneonataljaundicewithgeneticfeatures AT linwang ensemblelearningfortheearlypredictionofneonataljaundicewithgeneticfeatures AT chengzhang ensemblelearningfortheearlypredictionofneonataljaundicewithgeneticfeatures
_version_	1718372090413842432

Ensemble learning for the early prediction of neonatal jaundice with genetic features

Ejemplares similares