Computer aided prediction of sepsis-related mortality risk in neonatal intensive care units

Nowadays, sepsis is considered a global burden disease with anannual incidence of three million neonatal cases. Nevertheless, there are no homogeneous criteria for neonatal sepsis. Furthermore, adult sepsis scores don’t work properly in neonatal Intensive Care Units (ICUs) settings due to the specif...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Muñoz Lezcano, Sergio, López, Fernando, Corbi, Alberto
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2022
Materias:
CAD
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/151667
https://publicaciones.sadio.org.ar/index.php/JAIIO/article/download/373/311
Aporte de:
id I19-R120-10915-151667
record_format dspace
spelling I19-R120-10915-1516672023-04-18T20:03:58Z http://sedici.unlp.edu.ar/handle/10915/151667 https://publicaciones.sadio.org.ar/index.php/JAIIO/article/download/373/311 issn:2451-7496 Computer aided prediction of sepsis-related mortality risk in neonatal intensive care units Muñoz Lezcano, Sergio López, Fernando Corbi, Alberto 2022-10 2022 2023-04-18T17:00:42Z en Ciencias Informáticas Sepsis CAD NICU MIMIC-III Artificial Intelligence Nowadays, sepsis is considered a global burden disease with anannual incidence of three million neonatal cases. Nevertheless, there are no homogeneous criteria for neonatal sepsis. Furthermore, adult sepsis scores don’t work properly in neonatal Intensive Care Units (ICUs) settings due to the specific characteristics of the neonates' immune systems. This work describes and surveys a machine-learning computer-aided diagnosis approach for predicting sepsis mortality in neonatal ICUs. The survey is based on a retrospective cohort study in which each patient has an initial sepsis-related diagnosis in the first 24h after ICU admission. Our experiments are based on four different machine-learning techniques: decision trees, random forests, support vector machines and artificial neural networks. The predictive power was assessed using accuracy, sensitivity, and specificity. The importance of the variables was obtained automatically through data science techniques using R. The approach with the best performance was the random forest, which achieves an accuracy of 97% in the prediction of mortality. Sociedad Argentina de Informática e Investigación Operativa Objeto de conferencia Objeto de conferencia http://creativecommons.org/licenses/by-nc-sa/4.0/ Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) application/pdf 64-73
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Sepsis
CAD
NICU
MIMIC-III
Artificial Intelligence
spellingShingle Ciencias Informáticas
Sepsis
CAD
NICU
MIMIC-III
Artificial Intelligence
Muñoz Lezcano, Sergio
López, Fernando
Corbi, Alberto
Computer aided prediction of sepsis-related mortality risk in neonatal intensive care units
topic_facet Ciencias Informáticas
Sepsis
CAD
NICU
MIMIC-III
Artificial Intelligence
description Nowadays, sepsis is considered a global burden disease with anannual incidence of three million neonatal cases. Nevertheless, there are no homogeneous criteria for neonatal sepsis. Furthermore, adult sepsis scores don’t work properly in neonatal Intensive Care Units (ICUs) settings due to the specific characteristics of the neonates' immune systems. This work describes and surveys a machine-learning computer-aided diagnosis approach for predicting sepsis mortality in neonatal ICUs. The survey is based on a retrospective cohort study in which each patient has an initial sepsis-related diagnosis in the first 24h after ICU admission. Our experiments are based on four different machine-learning techniques: decision trees, random forests, support vector machines and artificial neural networks. The predictive power was assessed using accuracy, sensitivity, and specificity. The importance of the variables was obtained automatically through data science techniques using R. The approach with the best performance was the random forest, which achieves an accuracy of 97% in the prediction of mortality.
format Objeto de conferencia
Objeto de conferencia
author Muñoz Lezcano, Sergio
López, Fernando
Corbi, Alberto
author_facet Muñoz Lezcano, Sergio
López, Fernando
Corbi, Alberto
author_sort Muñoz Lezcano, Sergio
title Computer aided prediction of sepsis-related mortality risk in neonatal intensive care units
title_short Computer aided prediction of sepsis-related mortality risk in neonatal intensive care units
title_full Computer aided prediction of sepsis-related mortality risk in neonatal intensive care units
title_fullStr Computer aided prediction of sepsis-related mortality risk in neonatal intensive care units
title_full_unstemmed Computer aided prediction of sepsis-related mortality risk in neonatal intensive care units
title_sort computer aided prediction of sepsis-related mortality risk in neonatal intensive care units
publishDate 2022
url http://sedici.unlp.edu.ar/handle/10915/151667
https://publicaciones.sadio.org.ar/index.php/JAIIO/article/download/373/311
work_keys_str_mv AT munozlezcanosergio computeraidedpredictionofsepsisrelatedmortalityriskinneonatalintensivecareunits
AT lopezfernando computeraidedpredictionofsepsisrelatedmortalityriskinneonatalintensivecareunits
AT corbialberto computeraidedpredictionofsepsisrelatedmortalityriskinneonatalintensivecareunits
_version_ 1765659998324523008