Cargando…

Machine Learning Models for Predicting Mortality in 7472 Very Low Birth Weight Infants Using Data from a Nationwide Neonatal Network

Statistical and analytical methods using artificial intelligence approaches such as machine learning (ML) are increasingly being applied to the field of pediatrics, particularly to neonatology. This study compared the representative ML analysis and the logistic regression (LR), which is a traditiona...

Descripción completa

Detalles Bibliográficos
Autores principales: Do, Hyun Jeong, Moon, Kyoung Min, Jin, Hyun-Seung
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947011/
https://www.ncbi.nlm.nih.gov/pubmed/35328178
http://dx.doi.org/10.3390/diagnostics12030625
_version_ 1784674336945209344
author Do, Hyun Jeong
Moon, Kyoung Min
Jin, Hyun-Seung
author_facet Do, Hyun Jeong
Moon, Kyoung Min
Jin, Hyun-Seung
author_sort Do, Hyun Jeong
collection PubMed
description Statistical and analytical methods using artificial intelligence approaches such as machine learning (ML) are increasingly being applied to the field of pediatrics, particularly to neonatology. This study compared the representative ML analysis and the logistic regression (LR), which is a traditional statistical analysis method, using them to predict mortality of very low birth weight infants (VLBWI). We included 7472 VLBWI data from a nationwide Korean neonatal network. Eleven predictor variables (neonatal factors: male sex, gestational age, 5 min Apgar scores, body temperature, and resuscitation at birth; maternal factors: diabetes mellitus, hypertension, chorioamnionitis, premature rupture of membranes, antenatal steroid, and cesarean delivery) were selected based on clinical impact and statistical analysis. We compared the predicted mortality between ML methods—such as artificial neural network (ANN), random forest (RF), and support vector machine (SVM)—and LR with a randomly selected training set (80%) and a test set (20%). The model performances of area under the receiver operating curve (95% confidence interval) equaled LR 0.841 (0.811–0.872), ANN 0.845 (0.815–0.875), and RF 0.826 (0.795–0.858). The exception was SVM 0.631 (0.578–0.683). No statistically significant differences were observed between the performance of LR, ANN, and RF (i.e., p > 0.05). However, the SVM model was lower (p < 0.01). We suggest that VLBWI mortality prediction using ML methods would yield the same prediction rate as the traditional statistical LR method and may be suitable for predicting mortality. However, low prediction rates are observed in certain ML methods; hence, further research is needed on these limitations and selecting an appropriate method.
format Online
Article
Text
id pubmed-8947011
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-89470112022-03-25 Machine Learning Models for Predicting Mortality in 7472 Very Low Birth Weight Infants Using Data from a Nationwide Neonatal Network Do, Hyun Jeong Moon, Kyoung Min Jin, Hyun-Seung Diagnostics (Basel) Article Statistical and analytical methods using artificial intelligence approaches such as machine learning (ML) are increasingly being applied to the field of pediatrics, particularly to neonatology. This study compared the representative ML analysis and the logistic regression (LR), which is a traditional statistical analysis method, using them to predict mortality of very low birth weight infants (VLBWI). We included 7472 VLBWI data from a nationwide Korean neonatal network. Eleven predictor variables (neonatal factors: male sex, gestational age, 5 min Apgar scores, body temperature, and resuscitation at birth; maternal factors: diabetes mellitus, hypertension, chorioamnionitis, premature rupture of membranes, antenatal steroid, and cesarean delivery) were selected based on clinical impact and statistical analysis. We compared the predicted mortality between ML methods—such as artificial neural network (ANN), random forest (RF), and support vector machine (SVM)—and LR with a randomly selected training set (80%) and a test set (20%). The model performances of area under the receiver operating curve (95% confidence interval) equaled LR 0.841 (0.811–0.872), ANN 0.845 (0.815–0.875), and RF 0.826 (0.795–0.858). The exception was SVM 0.631 (0.578–0.683). No statistically significant differences were observed between the performance of LR, ANN, and RF (i.e., p > 0.05). However, the SVM model was lower (p < 0.01). We suggest that VLBWI mortality prediction using ML methods would yield the same prediction rate as the traditional statistical LR method and may be suitable for predicting mortality. However, low prediction rates are observed in certain ML methods; hence, further research is needed on these limitations and selecting an appropriate method. MDPI 2022-03-03 /pmc/articles/PMC8947011/ /pubmed/35328178 http://dx.doi.org/10.3390/diagnostics12030625 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Do, Hyun Jeong
Moon, Kyoung Min
Jin, Hyun-Seung
Machine Learning Models for Predicting Mortality in 7472 Very Low Birth Weight Infants Using Data from a Nationwide Neonatal Network
title Machine Learning Models for Predicting Mortality in 7472 Very Low Birth Weight Infants Using Data from a Nationwide Neonatal Network
title_full Machine Learning Models for Predicting Mortality in 7472 Very Low Birth Weight Infants Using Data from a Nationwide Neonatal Network
title_fullStr Machine Learning Models for Predicting Mortality in 7472 Very Low Birth Weight Infants Using Data from a Nationwide Neonatal Network
title_full_unstemmed Machine Learning Models for Predicting Mortality in 7472 Very Low Birth Weight Infants Using Data from a Nationwide Neonatal Network
title_short Machine Learning Models for Predicting Mortality in 7472 Very Low Birth Weight Infants Using Data from a Nationwide Neonatal Network
title_sort machine learning models for predicting mortality in 7472 very low birth weight infants using data from a nationwide neonatal network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8947011/
https://www.ncbi.nlm.nih.gov/pubmed/35328178
http://dx.doi.org/10.3390/diagnostics12030625
work_keys_str_mv AT dohyunjeong machinelearningmodelsforpredictingmortalityin7472verylowbirthweightinfantsusingdatafromanationwideneonatalnetwork
AT moonkyoungmin machinelearningmodelsforpredictingmortalityin7472verylowbirthweightinfantsusingdatafromanationwideneonatalnetwork
AT jinhyunseung machinelearningmodelsforpredictingmortalityin7472verylowbirthweightinfantsusingdatafromanationwideneonatalnetwork