Cargando…

Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation

BACKGROUND: Patient monitoring is vital in all stages of care. In particular, intensive care unit (ICU) patient monitoring has the potential to reduce complications and morbidity, and to increase the quality of care by enabling hospitals to deliver higher-quality, cost-effective patient care, and im...

Descripción completa

Detalles Bibliográficos
Autores principales: Alghatani, Khalid, Ammar, Nariman, Rezgui, Abdelmounaam, Shaban-Nejad, Arash
Formato: Online Artículo Texto
Lenguaje:English
Publicado: JMIR Publications 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8135024/
https://www.ncbi.nlm.nih.gov/pubmed/33949961
http://dx.doi.org/10.2196/21347
_version_ 1783695290443759616
author Alghatani, Khalid
Ammar, Nariman
Rezgui, Abdelmounaam
Shaban-Nejad, Arash
author_facet Alghatani, Khalid
Ammar, Nariman
Rezgui, Abdelmounaam
Shaban-Nejad, Arash
author_sort Alghatani, Khalid
collection PubMed
description BACKGROUND: Patient monitoring is vital in all stages of care. In particular, intensive care unit (ICU) patient monitoring has the potential to reduce complications and morbidity, and to increase the quality of care by enabling hospitals to deliver higher-quality, cost-effective patient care, and improve the quality of medical services in the ICU. OBJECTIVE: We here report the development and validation of ICU length of stay and mortality prediction models. The models will be used in an intelligent ICU patient monitoring module of an Intelligent Remote Patient Monitoring (IRPM) framework that monitors the health status of patients, and generates timely alerts, maneuver guidance, or reports when adverse medical conditions are predicted. METHODS: We utilized the publicly available Medical Information Mart for Intensive Care (MIMIC) database to extract ICU stay data for adult patients to build two prediction models: one for mortality prediction and another for ICU length of stay. For the mortality model, we applied six commonly used machine learning (ML) binary classification algorithms for predicting the discharge status (survived or not). For the length of stay model, we applied the same six ML algorithms for binary classification using the median patient population ICU stay of 2.64 days. For the regression-based classification, we used two ML algorithms for predicting the number of days. We built two variations of each prediction model: one using 12 baseline demographic and vital sign features, and the other based on our proposed quantiles approach, in which we use 21 extra features engineered from the baseline vital sign features, including their modified means, standard deviations, and quantile percentages. RESULTS: We could perform predictive modeling with minimal features while maintaining reasonable performance using the quantiles approach. The best accuracy achieved in the mortality model was approximately 89% using the random forest algorithm. The highest accuracy achieved in the length of stay model, based on the population median ICU stay (2.64 days), was approximately 65% using the random forest algorithm. CONCLUSIONS: The novelty in our approach is that we built models to predict ICU length of stay and mortality with reasonable accuracy based on a combination of ML and the quantiles approach that utilizes only vital signs available from the patient’s profile without the need to use any external features. This approach is based on feature engineering of the vital signs by including their modified means, standard deviations, and quantile percentages of the original features, which provided a richer dataset to achieve better predictive power in our models.
format Online
Article
Text
id pubmed-8135024
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher JMIR Publications
record_format MEDLINE/PubMed
spelling pubmed-81350242021-05-24 Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation Alghatani, Khalid Ammar, Nariman Rezgui, Abdelmounaam Shaban-Nejad, Arash JMIR Med Inform Original Paper BACKGROUND: Patient monitoring is vital in all stages of care. In particular, intensive care unit (ICU) patient monitoring has the potential to reduce complications and morbidity, and to increase the quality of care by enabling hospitals to deliver higher-quality, cost-effective patient care, and improve the quality of medical services in the ICU. OBJECTIVE: We here report the development and validation of ICU length of stay and mortality prediction models. The models will be used in an intelligent ICU patient monitoring module of an Intelligent Remote Patient Monitoring (IRPM) framework that monitors the health status of patients, and generates timely alerts, maneuver guidance, or reports when adverse medical conditions are predicted. METHODS: We utilized the publicly available Medical Information Mart for Intensive Care (MIMIC) database to extract ICU stay data for adult patients to build two prediction models: one for mortality prediction and another for ICU length of stay. For the mortality model, we applied six commonly used machine learning (ML) binary classification algorithms for predicting the discharge status (survived or not). For the length of stay model, we applied the same six ML algorithms for binary classification using the median patient population ICU stay of 2.64 days. For the regression-based classification, we used two ML algorithms for predicting the number of days. We built two variations of each prediction model: one using 12 baseline demographic and vital sign features, and the other based on our proposed quantiles approach, in which we use 21 extra features engineered from the baseline vital sign features, including their modified means, standard deviations, and quantile percentages. RESULTS: We could perform predictive modeling with minimal features while maintaining reasonable performance using the quantiles approach. The best accuracy achieved in the mortality model was approximately 89% using the random forest algorithm. The highest accuracy achieved in the length of stay model, based on the population median ICU stay (2.64 days), was approximately 65% using the random forest algorithm. CONCLUSIONS: The novelty in our approach is that we built models to predict ICU length of stay and mortality with reasonable accuracy based on a combination of ML and the quantiles approach that utilizes only vital signs available from the patient’s profile without the need to use any external features. This approach is based on feature engineering of the vital signs by including their modified means, standard deviations, and quantile percentages of the original features, which provided a richer dataset to achieve better predictive power in our models. JMIR Publications 2021-05-05 /pmc/articles/PMC8135024/ /pubmed/33949961 http://dx.doi.org/10.2196/21347 Text en ©Khalid Alghatani, Nariman Ammar, Abdelmounaam Rezgui, Arash Shaban-Nejad. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 05.05.2021. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Medical Informatics, is properly cited. The complete bibliographic information, a link to the original publication on https://medinform.jmir.org/, as well as this copyright and license information must be included.
spellingShingle Original Paper
Alghatani, Khalid
Ammar, Nariman
Rezgui, Abdelmounaam
Shaban-Nejad, Arash
Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation
title Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation
title_full Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation
title_fullStr Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation
title_full_unstemmed Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation
title_short Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation
title_sort predicting intensive care unit length of stay and mortality using patient vital signs: machine learning model development and validation
topic Original Paper
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8135024/
https://www.ncbi.nlm.nih.gov/pubmed/33949961
http://dx.doi.org/10.2196/21347
work_keys_str_mv AT alghatanikhalid predictingintensivecareunitlengthofstayandmortalityusingpatientvitalsignsmachinelearningmodeldevelopmentandvalidation
AT ammarnariman predictingintensivecareunitlengthofstayandmortalityusingpatientvitalsignsmachinelearningmodeldevelopmentandvalidation
AT rezguiabdelmounaam predictingintensivecareunitlengthofstayandmortalityusingpatientvitalsignsmachinelearningmodeldevelopmentandvalidation
AT shabannejadarash predictingintensivecareunitlengthofstayandmortalityusingpatientvitalsignsmachinelearningmodeldevelopmentandvalidation