학술논문
Machine learning decision tree algorithm role for predicting mortality in critically ill adult COVID-19 patients admitted to the ICU.
Document Type
Academic Journal
Author
Elhazmi A; Department of Critical Care, Dr. Sulaiman Al-Habib Medical Group, Riyadh, Saudi Arabia; College of Medicine, Alfaisal University, Riyadh, Saudi Arabia. Electronic address: a.m.haz@live.com.; Al-Omari A; Research Center, Dr. Sulaiman Alhabib Medical Group, Riyadh, Saudi Arabia; College of Medicine, Alfaisal University, Riyadh, Saudi Arabia.; Sallam H; Department of Adult Critical Care Medicine, King Faisal Specialist Hospital & Research Centre, Saudi Arabia.; Mufti HN; Section of Cardiac Surgery, Department of Cardiac Sciences, King Faisal Cardiac Center, King Abdulaziz Medical City, MNGHA-WR, Jeddah, Saudi Arabia; College of Medicine, King Saud Bin Abdulaziz University for Health Sciences, Jeddah, Saudi Arabia. King Abdullah International Medical Research Center, Jeddah, Saudi Arabia Intensive Care Department, King Saud Medical City, Riyadh, Saudi Arabia.; Rabie AA; Critical Care Department, King Saud Medical City, Riyadh, Saudi Arabia. Electronic address: drarabie@ksmc.med.sa.; Alshahrani M; Emergency and Critical Care Department, King Fahad Hospital of The University, Imam Abdul Rahman ben Faisal University, Dammam, Saudi Arabia.; Mady A; Critical Care Department, King Saud Medical City, Riyadh, Saudi Arabia; Department of Anesthesiology and Intensive Care, Tanta University Hospitals, Tanta, Egypt.; Alghamdi A; Prince Sultan Military Medical City, Military Medical Services, Ministry of Defence, Riyadh, Saudi Arabia.; Altalaq A; Prince Sultan Military Medical City, Military Medical Services, Ministry of Defence, Riyadh, Saudi Arabia.; Azzam MH; Intensive Care Department, King Abdullah Medical Complex, Jeddah, Saudi Arabia.; Sindi A; Department of Anesthesia and Critical Care, Faculty of Medicine, King Abdulaziz University, Jeddah, Saudi Arabia.; Kharaba A; Department of Critical Care, King Fahad Hospital, Al Medina Al Monawarah, Saudi Arabia.; Al-Aseri ZA; Departments Of Emergency Medicine and Critical Care, College of Medicine, King Saud University, Riyadh, Saudi Arabia; College Of Medicine, Dar Al Uloom University, Riyadh, Saudi Arabia.; Almekhlafi GA; Prince Sultan Military Medical City, Military Medical Services, Ministry of Defence, Riyadh, Saudi Arabia.; Tashkandi W; Department of Critical Care, Fakeeh Care Group, Jeddah, Saudi Arabia; Department of Surgery, King Abdulaziz University, Jeddah, Saudi Arabia.; Alajmi SA; Prince Sultan Military Medical City, Military Medical Services, Ministry of Defence, Riyadh, Saudi Arabia.; Faqihi F; Critical Care Department, King Saud Medical City, Riyadh, Saudi Arabia.; Alharthy A; Critical Care Department, King Saud Medical City, Riyadh, Saudi Arabia.; Al-Tawfiq JA; Infectious Disease Unit, Specialty Internal Medicine, Johns Hopkins Aramco Healthcare, Dhahran, Saudi Arabia. Infectious Disease Division, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USA; Infectious Disease Division, Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, USA.; Melibari RG; Department of Critical Care, King Abdullah Medical City, Makah, Saudi Arabia.; Al-Hazzani W; Department of Medicine, McMaster University, Hamilton, Canada; Department of Health Research Methods, Evidence, and Impact, McMaster University, Hamilton, Canada.; Arabi YM; College of Medicine, King Saud bin Abdulaziz University for Health Sciences, King Abdullah International Medical Research Center, Intensive Care Department, Ministry of National Guard Health Affairs, Riyadh, Saudi Arabia.
Source
Publisher: Elsevier Country of Publication: England NLM ID: 101487384 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1876-035X (Electronic) Linking ISSN: 18760341 NLM ISO Abbreviation: J Infect Public Health Subsets: MEDLINE
Subject
Language
English
Abstract
Background: Coronavirus disease-19 (COVID-19) is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and is currently a major cause of intensive care unit (ICU) admissions globally. The role of machine learning in the ICU is evolving but currently limited to diagnostic and prognostic values. A decision tree (DT) algorithm is a simple and intuitive machine learning method that provides sequential nonlinear analysis of variables. It is simple and might be a valuable tool for bedside physicians during COVID-19 to predict ICU outcomes and help in critical decision-making like end-of-life decisions and bed allocation in the event of limited ICU bed capacities. Herein, we utilized a machine learning DT algorithm to describe the association of a predefined set of variables and 28-day ICU outcome in adult COVID-19 patients admitted to the ICU. We highlight the value of utilizing a machine learning DT algorithm in the ICU at the time of a COVID-19 pandemic.
Methods: This was a prospective and multicenter cohort study involving 14 hospitals in Saudi Arabia. We included critically ill COVID-19 patients admitted to the ICU between March 1, 2020, and October 31, 2020. The predictors of 28-day ICU mortality were identified using two predictive models: conventional logistic regression and DT analyses.
Results: There were 1468 critically ill COVID-19 patients included in the study. The 28-day ICU mortality was 540 (36.8 %), and the 90-day mortality was 600 (40.9 %). The DT algorithm identified five variables that were integrated into the algorithm to predict 28-day ICU outcomes: need for intubation, need for vasopressors, age, gender, and PaO2/FiO2 ratio.
Conclusion: DT is a simple tool that might be utilized in the ICU to identify critically ill COVID-19 patients who are at high risk of 28-day ICU mortality. However, further studies and external validation are still required.
Competing Interests: Declaration of Competing Interest None of the authors have a conflict of interest related to this work.
(Copyright © 2022 The Authors. Published by Elsevier Ltd.. All rights reserved.)
Methods: This was a prospective and multicenter cohort study involving 14 hospitals in Saudi Arabia. We included critically ill COVID-19 patients admitted to the ICU between March 1, 2020, and October 31, 2020. The predictors of 28-day ICU mortality were identified using two predictive models: conventional logistic regression and DT analyses.
Results: There were 1468 critically ill COVID-19 patients included in the study. The 28-day ICU mortality was 540 (36.8 %), and the 90-day mortality was 600 (40.9 %). The DT algorithm identified five variables that were integrated into the algorithm to predict 28-day ICU outcomes: need for intubation, need for vasopressors, age, gender, and PaO2/FiO2 ratio.
Conclusion: DT is a simple tool that might be utilized in the ICU to identify critically ill COVID-19 patients who are at high risk of 28-day ICU mortality. However, further studies and external validation are still required.
Competing Interests: Declaration of Competing Interest None of the authors have a conflict of interest related to this work.
(Copyright © 2022 The Authors. Published by Elsevier Ltd.. All rights reserved.)