Simplified Pediatric Index of Mortality 3 Score by Explainable Machine Learning Algorithm

OBJECTIVES:. Pediatric Index of Mortality 3 is a validated tool including 11 variables for the assessment of mortality risk in PICU patients. With the recent advances in explainable machine learning algorithms, we aimed to assess feasibility of application of these machine learning models to simplif...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Orkun Baloglu, MD, Matthew Nagy, MPH, Chidiebere Ezetendu, MD, Samir Q. Latifi, MBBS, Aziz Nazha, MD
Formato:	article
Lenguaje:	EN
Publicado:	Wolters Kluwer 2021
Materias:	Medical emergencies. Critical care. Intensive care. First aid RC86-88.9
Acceso en línea:	https://doaj.org/article/9da1d1462eb94f98b724c68943283832
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9da1d1462eb94f98b724c68943283832
record_format	dspace
spelling	oai:doaj.org-article:9da1d1462eb94f98b724c689432838322021-11-25T07:56:43ZSimplified Pediatric Index of Mortality 3 Score by Explainable Machine Learning Algorithm2639-802810.1097/CCE.0000000000000561https://doaj.org/article/9da1d1462eb94f98b724c689432838322021-10-01T00:00:00Zhttp://journals.lww.com/10.1097/CCE.0000000000000561https://doaj.org/toc/2639-8028OBJECTIVES:. Pediatric Index of Mortality 3 is a validated tool including 11 variables for the assessment of mortality risk in PICU patients. With the recent advances in explainable machine learning algorithms, we aimed to assess feasibility of application of these machine learning models to simplify the Pediatric Index of Mortality 3 scoring system in order to decrease time and labor required for data collection and entry for Pediatric Index of Mortality 3. DESIGN:. Single-center, retrospective cohort study. Data from the Virtual Pediatric Systems for patients admitted to Cleveland Clinic Children`s PICU between January 2008 and December 2019 was obtained. Light Gradient Boosting Machine Regressor (a gradient boosting decision tree algorithm) was used for building the machine learning models. Variable importance was analyzed by SHapley Additive exPlanations. All of the 11 Pediatric Index of Mortality 3 variables were used as input variables in the machine learning models to predict Pediatric Index of Mortality 3 risk of mortality as the outcome variable. Mean absolute error, root mean squared error, and R-squared were calculated for each of the 11 machine learning models as model performance parameters. SETTING:. Quaternary children’s hospital. PATIENTS:. PICU patients. INTERVENTIONS:. None. MEASUREMENTS AND MAIN RESULTS:. Five-thousand sixty-eight patients were analyzed. The machine learning models were able to maintain similar predictive error until the number of input variables decreased to four. The machine learning model with five input variables (mechanical ventilation in the first hour of PICU admission, very-high-risk diagnosis, surgical recovery from a noncardiac procedure, low-risk diagnosis, and base excess) produced lowest mean root mean squared error of 1.49 (95% CI, 1.05–1.93) and highest R-squared of 0.73 (95% CI, 0.6–0.86) with mean absolute error of 0.43 (95% CI, 0.35–0.5) among all the 11 machine learning models. CONCLUSIONS:. Explainable machine learning methods were feasible in simplifying the Pediatric Index of Mortality 3 scoring system with similar risk of mortality predictions compared to the original Pediatric Index of Mortality 3 model tested in a single-center dataset.Orkun Baloglu, MDMatthew Nagy, MPHChidiebere Ezetendu, MDSamir Q. Latifi, MBBSAziz Nazha, MDWolters KluwerarticleMedical emergencies. Critical care. Intensive care. First aidRC86-88.9ENCritical Care Explorations, Vol 3, Iss 10, p e0561 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medical emergencies. Critical care. Intensive care. First aid RC86-88.9
spellingShingle	Medical emergencies. Critical care. Intensive care. First aid RC86-88.9 Orkun Baloglu, MD Matthew Nagy, MPH Chidiebere Ezetendu, MD Samir Q. Latifi, MBBS Aziz Nazha, MD Simplified Pediatric Index of Mortality 3 Score by Explainable Machine Learning Algorithm
description	OBJECTIVES:. Pediatric Index of Mortality 3 is a validated tool including 11 variables for the assessment of mortality risk in PICU patients. With the recent advances in explainable machine learning algorithms, we aimed to assess feasibility of application of these machine learning models to simplify the Pediatric Index of Mortality 3 scoring system in order to decrease time and labor required for data collection and entry for Pediatric Index of Mortality 3. DESIGN:. Single-center, retrospective cohort study. Data from the Virtual Pediatric Systems for patients admitted to Cleveland Clinic Children`s PICU between January 2008 and December 2019 was obtained. Light Gradient Boosting Machine Regressor (a gradient boosting decision tree algorithm) was used for building the machine learning models. Variable importance was analyzed by SHapley Additive exPlanations. All of the 11 Pediatric Index of Mortality 3 variables were used as input variables in the machine learning models to predict Pediatric Index of Mortality 3 risk of mortality as the outcome variable. Mean absolute error, root mean squared error, and R-squared were calculated for each of the 11 machine learning models as model performance parameters. SETTING:. Quaternary children’s hospital. PATIENTS:. PICU patients. INTERVENTIONS:. None. MEASUREMENTS AND MAIN RESULTS:. Five-thousand sixty-eight patients were analyzed. The machine learning models were able to maintain similar predictive error until the number of input variables decreased to four. The machine learning model with five input variables (mechanical ventilation in the first hour of PICU admission, very-high-risk diagnosis, surgical recovery from a noncardiac procedure, low-risk diagnosis, and base excess) produced lowest mean root mean squared error of 1.49 (95% CI, 1.05–1.93) and highest R-squared of 0.73 (95% CI, 0.6–0.86) with mean absolute error of 0.43 (95% CI, 0.35–0.5) among all the 11 machine learning models. CONCLUSIONS:. Explainable machine learning methods were feasible in simplifying the Pediatric Index of Mortality 3 scoring system with similar risk of mortality predictions compared to the original Pediatric Index of Mortality 3 model tested in a single-center dataset.
format	article
author	Orkun Baloglu, MD Matthew Nagy, MPH Chidiebere Ezetendu, MD Samir Q. Latifi, MBBS Aziz Nazha, MD
author_facet	Orkun Baloglu, MD Matthew Nagy, MPH Chidiebere Ezetendu, MD Samir Q. Latifi, MBBS Aziz Nazha, MD
author_sort	Orkun Baloglu, MD
title	Simplified Pediatric Index of Mortality 3 Score by Explainable Machine Learning Algorithm
title_short	Simplified Pediatric Index of Mortality 3 Score by Explainable Machine Learning Algorithm
title_full	Simplified Pediatric Index of Mortality 3 Score by Explainable Machine Learning Algorithm
title_fullStr	Simplified Pediatric Index of Mortality 3 Score by Explainable Machine Learning Algorithm
title_full_unstemmed	Simplified Pediatric Index of Mortality 3 Score by Explainable Machine Learning Algorithm
title_sort	simplified pediatric index of mortality 3 score by explainable machine learning algorithm
publisher	Wolters Kluwer
publishDate	2021
url	https://doaj.org/article/9da1d1462eb94f98b724c68943283832
work_keys_str_mv	AT orkunbaloglumd simplifiedpediatricindexofmortality3scorebyexplainablemachinelearningalgorithm AT matthewnagymph simplifiedpediatricindexofmortality3scorebyexplainablemachinelearningalgorithm AT chidiebereezetendumd simplifiedpediatricindexofmortality3scorebyexplainablemachinelearningalgorithm AT samirqlatifimbbs simplifiedpediatricindexofmortality3scorebyexplainablemachinelearningalgorithm AT aziznazhamd simplifiedpediatricindexofmortality3scorebyexplainablemachinelearningalgorithm
_version_	1718413637297635328

Simplified Pediatric Index of Mortality 3 Score by Explainable Machine Learning Algorithm

Ejemplares similares