Cargando…

Machine Learning Approaches to Predict In-Hospital Mortality among Neonates with Clinically Suspected Sepsis in the Neonatal Intensive Care Unit

Background: preterm and critically ill neonates often experience clinically suspected sepsis during their prolonged hospitalization in the neonatal intensive care unit (NICU), which can be the initial sign of final adverse outcomes. Therefore, we aimed to utilize machine learning approaches to predi...

Descripción completa

Detalles Bibliográficos
Autores principales: Hsu, Jen-Fu, Chang, Ying-Feng, Cheng, Hui-Jun, Yang, Chi, Lin, Chun-Yuan, Chu, Shih-Ming, Huang, Hsuan-Rong, Chiang, Ming-Chou, Wang, Hsiao-Chin, Tsai, Ming-Horng
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8400295/
https://www.ncbi.nlm.nih.gov/pubmed/34442338
http://dx.doi.org/10.3390/jpm11080695
_version_ 1783745281749155840
author Hsu, Jen-Fu
Chang, Ying-Feng
Cheng, Hui-Jun
Yang, Chi
Lin, Chun-Yuan
Chu, Shih-Ming
Huang, Hsuan-Rong
Chiang, Ming-Chou
Wang, Hsiao-Chin
Tsai, Ming-Horng
author_facet Hsu, Jen-Fu
Chang, Ying-Feng
Cheng, Hui-Jun
Yang, Chi
Lin, Chun-Yuan
Chu, Shih-Ming
Huang, Hsuan-Rong
Chiang, Ming-Chou
Wang, Hsiao-Chin
Tsai, Ming-Horng
author_sort Hsu, Jen-Fu
collection PubMed
description Background: preterm and critically ill neonates often experience clinically suspected sepsis during their prolonged hospitalization in the neonatal intensive care unit (NICU), which can be the initial sign of final adverse outcomes. Therefore, we aimed to utilize machine learning approaches to predict neonatal in-hospital mortality through data-driven learning. Methods: a total of 1095 neonates who experienced clinically suspected sepsis in a tertiary-level NICU in Taiwan between August 2017 and July 2020 were enrolled. Clinically suspected sepsis was defined based on clinical features and laboratory criteria and the administration of empiric antibiotics by clinicians. The variables used for analysis included patient demographics, clinical features, laboratory data, and medications. The machine learning methods used included deep neural network (DNN), k-nearest neighbors, support vector machine, random forest, and extreme gradient boost. The performance of these models was evaluated using the area under the receiver operating characteristic curve (AUC). Results: the final in-hospital mortality of this cohort was 8.2% (90 neonates died). A total of 765 (69.8%) and 330 (30.2%) patients were randomly assigned to the training and test sets, respectively. Regarding the efficacy of the single model that most accurately predicted the outcome, DNN exhibited the greatest AUC (0.923, 95% confidence interval [CI] 0.953–0.893) and the best accuracy (95.64%, 95% CI 96.76–94.52%), Cohen’s kappa coefficient value (0.74, 95% CI 0.79–0.69) and Matthews correlation coefficient value (0.75, 95% CI 0.80–0.70). The top three most influential variables in the DNN importance matrix plot were the requirement of ventilator support at the onset of suspected sepsis, the feeding conditions, and intravascular volume expansion. The model performance was indistinguishable between the training and test sets. Conclusions: the DNN model was successfully established to predict in-hospital mortality in neonates with clinically suspected sepsis, and the machine learning algorithm is applicable for clinicians to gain insights and have better communication with families in advance.
format Online
Article
Text
id pubmed-8400295
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-84002952021-08-29 Machine Learning Approaches to Predict In-Hospital Mortality among Neonates with Clinically Suspected Sepsis in the Neonatal Intensive Care Unit Hsu, Jen-Fu Chang, Ying-Feng Cheng, Hui-Jun Yang, Chi Lin, Chun-Yuan Chu, Shih-Ming Huang, Hsuan-Rong Chiang, Ming-Chou Wang, Hsiao-Chin Tsai, Ming-Horng J Pers Med Article Background: preterm and critically ill neonates often experience clinically suspected sepsis during their prolonged hospitalization in the neonatal intensive care unit (NICU), which can be the initial sign of final adverse outcomes. Therefore, we aimed to utilize machine learning approaches to predict neonatal in-hospital mortality through data-driven learning. Methods: a total of 1095 neonates who experienced clinically suspected sepsis in a tertiary-level NICU in Taiwan between August 2017 and July 2020 were enrolled. Clinically suspected sepsis was defined based on clinical features and laboratory criteria and the administration of empiric antibiotics by clinicians. The variables used for analysis included patient demographics, clinical features, laboratory data, and medications. The machine learning methods used included deep neural network (DNN), k-nearest neighbors, support vector machine, random forest, and extreme gradient boost. The performance of these models was evaluated using the area under the receiver operating characteristic curve (AUC). Results: the final in-hospital mortality of this cohort was 8.2% (90 neonates died). A total of 765 (69.8%) and 330 (30.2%) patients were randomly assigned to the training and test sets, respectively. Regarding the efficacy of the single model that most accurately predicted the outcome, DNN exhibited the greatest AUC (0.923, 95% confidence interval [CI] 0.953–0.893) and the best accuracy (95.64%, 95% CI 96.76–94.52%), Cohen’s kappa coefficient value (0.74, 95% CI 0.79–0.69) and Matthews correlation coefficient value (0.75, 95% CI 0.80–0.70). The top three most influential variables in the DNN importance matrix plot were the requirement of ventilator support at the onset of suspected sepsis, the feeding conditions, and intravascular volume expansion. The model performance was indistinguishable between the training and test sets. Conclusions: the DNN model was successfully established to predict in-hospital mortality in neonates with clinically suspected sepsis, and the machine learning algorithm is applicable for clinicians to gain insights and have better communication with families in advance. MDPI 2021-07-22 /pmc/articles/PMC8400295/ /pubmed/34442338 http://dx.doi.org/10.3390/jpm11080695 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
Chang, Ying-Feng
Cheng, Hui-Jun
Yang, Chi
Lin, Chun-Yuan
Chu, Shih-Ming
Huang, Hsuan-Rong
Chiang, Ming-Chou
Wang, Hsiao-Chin
Tsai, Ming-Horng
Machine Learning Approaches to Predict In-Hospital Mortality among Neonates with Clinically Suspected Sepsis in the Neonatal Intensive Care Unit
title Machine Learning Approaches to Predict In-Hospital Mortality among Neonates with Clinically Suspected Sepsis in the Neonatal Intensive Care Unit
title_full Machine Learning Approaches to Predict In-Hospital Mortality among Neonates with Clinically Suspected Sepsis in the Neonatal Intensive Care Unit
title_fullStr Machine Learning Approaches to Predict In-Hospital Mortality among Neonates with Clinically Suspected Sepsis in the Neonatal Intensive Care Unit
title_full_unstemmed Machine Learning Approaches to Predict In-Hospital Mortality among Neonates with Clinically Suspected Sepsis in the Neonatal Intensive Care Unit
title_short Machine Learning Approaches to Predict In-Hospital Mortality among Neonates with Clinically Suspected Sepsis in the Neonatal Intensive Care Unit
title_sort machine learning approaches to predict in-hospital mortality among neonates with clinically suspected sepsis in the neonatal intensive care unit
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8400295/
https://www.ncbi.nlm.nih.gov/pubmed/34442338
http://dx.doi.org/10.3390/jpm11080695
work_keys_str_mv AT hsujenfu machinelearningapproachestopredictinhospitalmortalityamongneonateswithclinicallysuspectedsepsisintheneonatalintensivecareunit
AT changyingfeng machinelearningapproachestopredictinhospitalmortalityamongneonateswithclinicallysuspectedsepsisintheneonatalintensivecareunit
AT chenghuijun machinelearningapproachestopredictinhospitalmortalityamongneonateswithclinicallysuspectedsepsisintheneonatalintensivecareunit
AT yangchi machinelearningapproachestopredictinhospitalmortalityamongneonateswithclinicallysuspectedsepsisintheneonatalintensivecareunit
AT linchunyuan machinelearningapproachestopredictinhospitalmortalityamongneonateswithclinicallysuspectedsepsisintheneonatalintensivecareunit
AT chushihming machinelearningapproachestopredictinhospitalmortalityamongneonateswithclinicallysuspectedsepsisintheneonatalintensivecareunit
AT huanghsuanrong machinelearningapproachestopredictinhospitalmortalityamongneonateswithclinicallysuspectedsepsisintheneonatalintensivecareunit
AT chiangmingchou machinelearningapproachestopredictinhospitalmortalityamongneonateswithclinicallysuspectedsepsisintheneonatalintensivecareunit
AT wanghsiaochin machinelearningapproachestopredictinhospitalmortalityamongneonateswithclinicallysuspectedsepsisintheneonatalintensivecareunit
AT tsaiminghorng machinelearningapproachestopredictinhospitalmortalityamongneonateswithclinicallysuspectedsepsisintheneonatalintensivecareunit