Please use this identifier to cite or link to this item: http://hdl.handle.net/1822/62777

TitleChild’s target height prediction evolution
Author(s)Cordeiro, João Rala
Postolache, Octavian
Ferreira, João C.
Keywordschild height prediction
growth assessment
child personalized medicine
data mining
XGB-Extreme Gradient Boosting Regression
LGBM-LightGradient Boosting Machine Regression
Issue date12-Dec-2019
PublisherMultidisciplinary Digital Publishing Institute
JournalApplied Sciences
CitationCordeiro, J.R.; Postolache, O.; Ferreira, J.C. Child’s Target Height Prediction Evolution. Appl. Sci. 2019, 9, 5447.
Abstract(s)This study is a contribution for the improvement of healthcare in children and in society generally. This study aims to predict children’s height when they become adults, also known as “target height”, to allow for a better growth assessment and more personalized healthcare. The existing literature describes some existing prediction methods, based on longitudinal population studies and statistical techniques, which with few information resources, are able to produce acceptable results. The challenge of this study is in using a new approach based on machine learning to forecast the target height for children and (eventually) improve the existing height prediction accuracy. The goals of the study were achieved. The extreme gradient boosting regression (XGB) and light gradient boosting machine regression (LightGBM) algorithms achieved considerably better results on the height prediction. The developed model can be usefully applied by pediatricians and other clinical professionals in growth assessment.
TypeArticle
URIhttp://hdl.handle.net/1822/62777
DOI10.3390/app9245447
ISSN2076-3417
Publisher versionhttps://www.mdpi.com/2076-3417/9/24/5447
Peer-Reviewedyes
AccessOpen access
Appears in Collections:CAlg - Artigos em revistas internacionais/Papers in international journals

Files in This Item:
File Description SizeFormat 
applsci-09-05447.pdf3,53 MBAdobe PDFView/Open

This item is licensed under a Creative Commons License Creative Commons

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu ORCID