干旱区生态环境知识资源中心(Arid): A machine learning-based model for 1-year mortality prediction in patients admitted to an Intensive Care Unit with a diagnosis of sepsis

Arid

DOI	10.1016/j.medin.2018.07.016
	A machine learning-based model for 1-year mortality prediction in patients admitted to an Intensive Care Unit with a diagnosis of sepsis
	Garcia-Gallo, J. E.1; Fonseca-Ruiz, N. J.2,3; Celi, L. A.4; Duitama-Munoz, J. F.1
通讯作者	Garcia-Gallo, J. E.
来源期刊	MEDICINA INTENSIVA
ISSN	0210-5691
EISSN	1578-6749
出版年	2020
卷号	44 期号:3 页码:160-170
英文摘要	Introduction: Sepsis is associated to a high mortality rate, and its severity must be evaluated quickly. The severity of illness scores used are intended to be applicable to all patient populations, and generally evaluate in-hospital mortality. However, patients with sepsis continue to be at risk of death after hospital discharge. Objective: To develop a model for predicting 1-year mortality in critical patients diagnosed with sepsis. Patients: The data corresponding to 5650 admissions of patients with sepsis from the Medical Information Mart for Intensive Care (MIMIC-III) database were evaluated, randomly divided as follows: 70% for training and 30% for validation. Design: A retrospective register-based cohort study was carried out. The clinical information of the first 24 h after admission was used to develop a 1-year mortality prediction model based on Stochastic Gradient Boosting (SGB) methodology. Variable selection was addressed using Least Absolute Shrinkage and Selection Operator (LASSO) and SGB variable importance methodologies. The predictive power was evaluated using the area under the ROC curve (AUROC). Results: An AUROC of 0.8039 (95% confidence interval (CI): [0.8033 0.80451) was obtained in the validation subset. The model exceeded the predictive performances obtained with traditional severity of disease scores in the same subset. Conclusion: The use of assembly algorithms, such as SGB, for the generation of a customized model for sepsis yields more accurate 1-year mortality prediction than the traditional scoring systems such as SAPS II, SOFA or OASIS. (C) 2018 Elsevier Espana, S.L.U. y SEMICYUC. All rights reserved.
英文关键词	Prognosis prediction Sepsis Stochastic gradient boosting Intensive care unit Least absolute shrinkage and selection operator
类型	Article
语种	英语
国家	Colombia ; USA
收录类别	SCI-E
WOS记录号	WOS:000521984300005
WOS关键词	INTERNATIONAL CONSENSUS DEFINITIONS ; SEPTIC SHOCK ; CLINICAL-CRITERIA ; SCORE
WOS类目	Critical Care Medicine
WOS研究方向	General & Internal Medicine
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/315158
作者单位	1.Univ Antioquia UdeA, Engn & Software Invest Grp, Medellin, Colombia; 2.Medellin Clin, Crit & Intens Care, Medellin, Colombia; 3.CES Univ, Crit & Intens Care Program, Medellin, Colombia; 4.Harvard MIT Div Hlth Sci & Technol, Lab Computat Physiol, Cambridge, MA USA
推荐引用方式 GB/T 7714	Garcia-Gallo, J. E.,Fonseca-Ruiz, N. J.,Celi, L. A.,et al. A machine learning-based model for 1-year mortality prediction in patients admitted to an Intensive Care Unit with a diagnosis of sepsis[J],2020,44(3):160-170.
APA	Garcia-Gallo, J. E.,Fonseca-Ruiz, N. J.,Celi, L. A.,&Duitama-Munoz, J. F..(2020).A machine learning-based model for 1-year mortality prediction in patients admitted to an Intensive Care Unit with a diagnosis of sepsis.MEDICINA INTENSIVA,44(3),160-170.
MLA	Garcia-Gallo, J. E.,et al."A machine learning-based model for 1-year mortality prediction in patients admitted to an Intensive Care Unit with a diagnosis of sepsis".MEDICINA INTENSIVA 44.3(2020):160-170.