Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems

Due to the continuous monitoring process of critical patients, Intensive Care Units (ICU) generate large amounts of data, which are difficult for healthcare personnel to analyze manually, especially in overloaded situations such as those present during the COVID-19 pandemic. Therefore, the automatic...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	José A. González-Nóvoa, Laura Busto, Juan J. Rodríguez-Andina, José Fariña, Marta Segura, Vanesa Gómez, Dolores Vila, César Veiga
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	alarms explainable machine learning Intensive Care Unit machine learning MIMIC patient monitoring Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/e6b12e8e171a4d8c80d062b3f7b2529b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e6b12e8e171a4d8c80d062b3f7b2529b
record_format	dspace
spelling	oai:doaj.org-article:e6b12e8e171a4d8c80d062b3f7b2529b2021-11-11T19:07:42ZUsing Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems10.3390/s212171251424-8220https://doaj.org/article/e6b12e8e171a4d8c80d062b3f7b2529b2021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7125https://doaj.org/toc/1424-8220Due to the continuous monitoring process of critical patients, Intensive Care Units (ICU) generate large amounts of data, which are difficult for healthcare personnel to analyze manually, especially in overloaded situations such as those present during the COVID-19 pandemic. Therefore, the automatic analysis of these data has many practical applications in patient monitoring, including the optimization of alarm systems for alerting healthcare personnel. In this paper, explainable machine learning techniques are used for this purpose, with a methodology based on age-stratification, boosting classifiers, and Shapley Additive Explanations (SHAP) proposed. The methodology is evaluated using MIMIC-III, an ICU patient research database. The results show that the proposed model can predict mortality within the ICU with AUROC values of 0.961, 0.936, 0.898, and 0.883 for age groups 18–45, 45–65, 65–85 and 85+, respectively. By using SHAP, the features with the highest impact in predicting mortality for different age groups and the threshold from which the value of a clinical feature has a negative impact on the patient’s health can be identified. This allows ICU alarms to be improved by identifying the most important variables to be sensed and the threshold values at which the health personnel must be warned.José A. González-NóvoaLaura BustoJuan J. Rodríguez-AndinaJosé FariñaMarta SeguraVanesa GómezDolores VilaCésar VeigaMDPI AGarticlealarmsexplainable machine learningIntensive Care Unitmachine learningMIMICpatient monitoringChemical technologyTP1-1185ENSensors, Vol 21, Iss 7125, p 7125 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	alarms explainable machine learning Intensive Care Unit machine learning MIMIC patient monitoring Chemical technology TP1-1185
spellingShingle	alarms explainable machine learning Intensive Care Unit machine learning MIMIC patient monitoring Chemical technology TP1-1185 José A. González-Nóvoa Laura Busto Juan J. Rodríguez-Andina José Fariña Marta Segura Vanesa Gómez Dolores Vila César Veiga Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems
description	Due to the continuous monitoring process of critical patients, Intensive Care Units (ICU) generate large amounts of data, which are difficult for healthcare personnel to analyze manually, especially in overloaded situations such as those present during the COVID-19 pandemic. Therefore, the automatic analysis of these data has many practical applications in patient monitoring, including the optimization of alarm systems for alerting healthcare personnel. In this paper, explainable machine learning techniques are used for this purpose, with a methodology based on age-stratification, boosting classifiers, and Shapley Additive Explanations (SHAP) proposed. The methodology is evaluated using MIMIC-III, an ICU patient research database. The results show that the proposed model can predict mortality within the ICU with AUROC values of 0.961, 0.936, 0.898, and 0.883 for age groups 18–45, 45–65, 65–85 and 85+, respectively. By using SHAP, the features with the highest impact in predicting mortality for different age groups and the threshold from which the value of a clinical feature has a negative impact on the patient’s health can be identified. This allows ICU alarms to be improved by identifying the most important variables to be sensed and the threshold values at which the health personnel must be warned.
format	article
author	José A. González-Nóvoa Laura Busto Juan J. Rodríguez-Andina José Fariña Marta Segura Vanesa Gómez Dolores Vila César Veiga
author_facet	José A. González-Nóvoa Laura Busto Juan J. Rodríguez-Andina José Fariña Marta Segura Vanesa Gómez Dolores Vila César Veiga
author_sort	José A. González-Nóvoa
title	Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems
title_short	Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems
title_full	Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems
title_fullStr	Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems
title_full_unstemmed	Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems
title_sort	using explainable machine learning to improve intensive care unit alarm systems
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/e6b12e8e171a4d8c80d062b3f7b2529b
work_keys_str_mv	AT joseagonzaleznovoa usingexplainablemachinelearningtoimproveintensivecareunitalarmsystems AT laurabusto usingexplainablemachinelearningtoimproveintensivecareunitalarmsystems AT juanjrodriguezandina usingexplainablemachinelearningtoimproveintensivecareunitalarmsystems AT josefarina usingexplainablemachinelearningtoimproveintensivecareunitalarmsystems AT martasegura usingexplainablemachinelearningtoimproveintensivecareunitalarmsystems AT vanesagomez usingexplainablemachinelearningtoimproveintensivecareunitalarmsystems AT doloresvila usingexplainablemachinelearningtoimproveintensivecareunitalarmsystems AT cesarveiga usingexplainablemachinelearningtoimproveintensivecareunitalarmsystems
_version_	1718431617503985664

Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems

Ejemplares similares