Cargando…

Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure

Background: Early identification of critically ill neonates with poor outcomes can optimize therapeutic strategies. We aimed to examine whether machine learning (ML) methods can improve mortality prediction for neonatal intensive care unit (NICU) patients on intubation for respiratory failure. Metho...

Descripción completa

Detalles Bibliográficos
Autores principales: Hsu, Jen-Fu, Yang, Chi, Lin, Chun-Yuan, Chu, Shih-Ming, Huang, Hsuan-Rong, Chiang, Ming-Chou, Wang, Hsiao-Chin, Liao, Wei-Chao, Fu, Rei-Huei, Tsai, Ming-Horng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8533201/
https://www.ncbi.nlm.nih.gov/pubmed/34680497
http://dx.doi.org/10.3390/biomedicines9101377
_version_ 1784587255368646656
author Hsu, Jen-Fu
Yang, Chi
Lin, Chun-Yuan
Chu, Shih-Ming
Huang, Hsuan-Rong
Chiang, Ming-Chou
Wang, Hsiao-Chin
Liao, Wei-Chao
Fu, Rei-Huei
Tsai, Ming-Horng
author_facet Hsu, Jen-Fu
Yang, Chi
Lin, Chun-Yuan
Chu, Shih-Ming
Huang, Hsuan-Rong
Chiang, Ming-Chou
Wang, Hsiao-Chin
Liao, Wei-Chao
Fu, Rei-Huei
Tsai, Ming-Horng
author_sort Hsu, Jen-Fu
collection PubMed
description Background: Early identification of critically ill neonates with poor outcomes can optimize therapeutic strategies. We aimed to examine whether machine learning (ML) methods can improve mortality prediction for neonatal intensive care unit (NICU) patients on intubation for respiratory failure. Methods: A total of 1734 neonates with respiratory failure were randomly divided into training (70%, n = 1214) and test (30%, n = 520) sets. The primary outcome was the probability of NICU mortality. The areas under the receiver operating characteristic curves (AUCs) of several ML algorithms were compared with those of the conventional neonatal illness severity scoring systems including the NTISS and SNAPPE-II. Results: For NICU mortality, the random forest (RF) model showed the highest AUC (0.939 (0.921–0.958)) for the prediction of neonates with respiratory failure, and the bagged classification and regression tree model demonstrated the next best results (0.915 (0.891–0.939)). The AUCs of both models were significantly better than the traditional NTISS (0.836 (0.800–0.871)) and SNAPPE-II scores (0.805 (0.766–0.843)). The superior performances were confirmed by higher accuracy and F1 score and better calibration, and the superior and net benefit was confirmed by decision curve analysis. In addition, Shapley additive explanation (SHAP) values were utilized to explain the RF prediction model. Conclusions: Machine learning algorithms increase the accuracy and predictive ability for mortality of neonates with respiratory failure compared with conventional neonatal illness severity scores. The RF model is suitable for clinical use in the NICU, and clinicians can gain insights and have better communication with families in advance.
format Online
Article
Text
id pubmed-8533201
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-85332012021-10-23 Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure Hsu, Jen-Fu Yang, Chi Lin, Chun-Yuan Chu, Shih-Ming Huang, Hsuan-Rong Chiang, Ming-Chou Wang, Hsiao-Chin Liao, Wei-Chao Fu, Rei-Huei Tsai, Ming-Horng Biomedicines Article Background: Early identification of critically ill neonates with poor outcomes can optimize therapeutic strategies. We aimed to examine whether machine learning (ML) methods can improve mortality prediction for neonatal intensive care unit (NICU) patients on intubation for respiratory failure. Methods: A total of 1734 neonates with respiratory failure were randomly divided into training (70%, n = 1214) and test (30%, n = 520) sets. The primary outcome was the probability of NICU mortality. The areas under the receiver operating characteristic curves (AUCs) of several ML algorithms were compared with those of the conventional neonatal illness severity scoring systems including the NTISS and SNAPPE-II. Results: For NICU mortality, the random forest (RF) model showed the highest AUC (0.939 (0.921–0.958)) for the prediction of neonates with respiratory failure, and the bagged classification and regression tree model demonstrated the next best results (0.915 (0.891–0.939)). The AUCs of both models were significantly better than the traditional NTISS (0.836 (0.800–0.871)) and SNAPPE-II scores (0.805 (0.766–0.843)). The superior performances were confirmed by higher accuracy and F1 score and better calibration, and the superior and net benefit was confirmed by decision curve analysis. In addition, Shapley additive explanation (SHAP) values were utilized to explain the RF prediction model. Conclusions: Machine learning algorithms increase the accuracy and predictive ability for mortality of neonates with respiratory failure compared with conventional neonatal illness severity scores. The RF model is suitable for clinical use in the NICU, and clinicians can gain insights and have better communication with families in advance. MDPI 2021-10-02 /pmc/articles/PMC8533201/ /pubmed/34680497 http://dx.doi.org/10.3390/biomedicines9101377 Text en © 2021 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
Hsu, Jen-Fu
Yang, Chi
Lin, Chun-Yuan
Chu, Shih-Ming
Huang, Hsuan-Rong
Chiang, Ming-Chou
Wang, Hsiao-Chin
Liao, Wei-Chao
Fu, Rei-Huei
Tsai, Ming-Horng
Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure
title Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure
title_full Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure
title_fullStr Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure
title_full_unstemmed Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure
title_short Machine Learning Algorithms to Predict Mortality of Neonates on Mechanical Intubation for Respiratory Failure
title_sort machine learning algorithms to predict mortality of neonates on mechanical intubation for respiratory failure
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8533201/
https://www.ncbi.nlm.nih.gov/pubmed/34680497
http://dx.doi.org/10.3390/biomedicines9101377
work_keys_str_mv AT hsujenfu machinelearningalgorithmstopredictmortalityofneonatesonmechanicalintubationforrespiratoryfailure
AT yangchi machinelearningalgorithmstopredictmortalityofneonatesonmechanicalintubationforrespiratoryfailure
AT linchunyuan machinelearningalgorithmstopredictmortalityofneonatesonmechanicalintubationforrespiratoryfailure
AT chushihming machinelearningalgorithmstopredictmortalityofneonatesonmechanicalintubationforrespiratoryfailure
AT huanghsuanrong machinelearningalgorithmstopredictmortalityofneonatesonmechanicalintubationforrespiratoryfailure
AT chiangmingchou machinelearningalgorithmstopredictmortalityofneonatesonmechanicalintubationforrespiratoryfailure
AT wanghsiaochin machinelearningalgorithmstopredictmortalityofneonatesonmechanicalintubationforrespiratoryfailure
AT liaoweichao machinelearningalgorithmstopredictmortalityofneonatesonmechanicalintubationforrespiratoryfailure
AT fureihuei machinelearningalgorithmstopredictmortalityofneonatesonmechanicalintubationforrespiratoryfailure
AT tsaiminghorng machinelearningalgorithmstopredictmortalityofneonatesonmechanicalintubationforrespiratoryfailure