Machine learning decision tree algorithm role for predicting mortality in critically ill adult COVID-19 patients admitted to the ICU

被引：48

作者：

Elhazmi, Alyaa ^{[1
,3
]}

Al-Omari, Awad ^{[2
,3
]}

Sallam, Hend ^{[4
]}

Mufti, Hani N. ^{[5
,6
,7
,8
]}

Rabie, Ahmed A. ^{[9
]}

Alshahrani, Mohammed ^{[10
]}

Mady, Ahmed ^{[9
,11
]}

Alghamdi, Adnan ^{[12
]}

Altalaq, Ali ^{[12
]}

Azzam, Mohamed H. ^{[13
]}

Sindi, Anees ^{[14
]}

Kharaba, Ayman ^{[15
]}

Al-Aseri, Zohair A. ^{[16
,17
,18
]}

Almekhlafi, Ghaleb A. ^{[12
]}

Tashkandi, Wail ^{[19
,20
]}

Alajmi, Saud A. ^{[12
]}

Faqihi, Fahad ^{[9
]}

Alharthy, Abdulrahman ^{[9
]}

Al-Tawfiq, Jaffar A. ^{[21
,22
,23
]}

Melibari, Rami Ghazi ^{[24
]}

Al-Hazzani, Waleed ^{[25
,26
]}

Arabi, Yaseen M. ^{[27
]}

机构：

[1] Dr Sulaiman Al Habib Med Grp, Dept Crit Care, Riyadh, Saudi Arabia

[2] Dr Sulaiman Alhabib Med Grp, Res Ctr, Riyadh, Saudi Arabia

[3] Alfaisal Univ, Coll Med, Riyadh, Saudi Arabia

[4] King Faisal Specialist Hosp & Res Ctr, Dept Adult Crit Care Med, Riyadh, Saudi Arabia

[5] MNGHA WR, Dept Cardiac Sci, Sect Cardiac Surg, King Faisal Cardiac Ctr,King Abdulaziz Med City, Jeddah, Saudi Arabia

[6] King Saud Bin Abdulaziz Univ Hlth Sci, Coll Med, Jeddah, Saudi Arabia

[7] King Abdullah Int Med Res Ctr, Jeddah, Saudi Arabia

[8] King Saud Med City, Saudi Arabia Intens Care Dept, Riyadh, Saudi Arabia

[9] King Saud Med City, Crit Care Dept, Riyadh, Saudi Arabia

[10] Imam Abdul Rahman Ben Faisal Univ, King Fahad Hosp Univ, Emergency & Crit Care Dept, Dammam, Saudi Arabia

[11] Tanta Univ Hosp, Dept Anesthesiol & Intens Care, Tanta, Egypt

[12] Minist Def, Mil Med Serv, Prince Sultan Mil Med City, Riyadh, Saudi Arabia

[13] Intens Care Dept, King Abdullah Med Complex, Jeddah, Saudi Arabia

[14] King Abdulaziz Univ, Fac Med, Dept Anesthesia & Crit Care, Jeddah, Saudi Arabia

[15] King Fahad Hosp, Dept Crit Care, Al Medina Al Monawarah, Saudi Arabia

[16] King Saud Univ, Coll Med, Dept Emergency Med, Riyadh, Saudi Arabia

[17] King Saud Univ, Coll Med, Dept Crit Care, Riyadh, Saudi Arabia

[18] Dar Al Uloom Univ, Coll Med, Riyadh, Saudi Arabia

[19] Fakeeh Care Grp, Dept Crit Care, Jeddah, Saudi Arabia

[20] King Abdulaziz Univ, Dept Surg, Jeddah, Saudi Arabia

[21] Johns Hopkins Aramco Healthcare, Infect Dis Unit, Specialty Internal Med, Dhahran, Saudi Arabia

[22] Johns Hopkins Univ, Sch Med, Dept Med, Infect Dis Div, Baltimore, MD 21205 USA

[23] Indiana Univ Sch Med, Infect Dis Div, Dept Med, Indianapolis, IN 46202 USA

[24] King Abdullah Med City, Dept Crit Care, Makah, Saudi Arabia

[25] McMaster Univ, Dept Med, Hamilton, ON, Canada

[26] McMaster Univ, Dept Hlth Res Methods Evidence & Impact, Hamilton, ON, Canada

[27] King Saud Bin Abdulaziz Univ Hlth Sci, Coll Med, King Abdullah Int Med Res Ctr, Intens Care Dept,Minist Natl Guard Hlth Affairs, Riyadh, Saudi Arabia

来源：

JOURNAL OF INFECTION AND PUBLIC HEALTH | 2022年 / 15卷 / 07期

关键词：

COVID-19; SARS-Cov2; Decision tree; ICU; Predictors; APACHE-II; VALIDATION; SEVERITY; SCORE;

D O I：

10.1016/j.jiph.2022.06.008

中图分类号：

R1 [预防医学、卫生学];

学科分类号：

1004 ; 120402 ;

摘要：

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.(c) 2022 The Author(s). Published by Elsevier Ltd on behalf of King Saud Bin Abdulaziz University for Health Sciences. CC_BY_NC_ND_4.0

引用

页码：826 / 834

页数：9

共 47 条

[1] Characteristics, risk factors and outcomes among the first consecutive 1096 patients diagnosed with COVID-19 in Kuwait [J].

Almazeedi, Sulaiman ;

Al-Youha, Sarah ;

Jamal, Mohammad H. ;

Al-Haddad, Mohannad ;

Al-Muhaini, Ali ;

Al-Ghimlas, Fahad ;

Al-Sabah, Salman .

ECLINICALMEDICINE, 2020, 24

[2]

[Anonymous], 2009, The elements of statistical learning: data mining, inference, and prediction

[3] How the COVID-19 pandemic will change the future of critical care [J].

Arabi, Yaseen M. ;

Azoulay, Elie ;

Al-Dorzi, Hasan M. ;

Phua, Jason ;

Salluh, Jorge ;

Binnie, Alexandra ;

Hodgson, Carol ;

Angus, Derek C. ;

Cecconi, Maurizio ;

Du, Bin ;

Fowler, Rob ;

Gomersall, Charles D. ;

Horby, Peter ;

Juffermans, Nicole P. ;

Kesecioglu, Jozef ;

Kleinpell, Ruth M. ;

Machado, Flavia R. ;

Martin, Greg S. ;

Meyfroidt, Geert ;

Rhodes, Andrew ;

Rowan, Kathryn ;

Timsit, Jean-Francois ;

Vincent, Jean-Louis ;

Citerio, Giuseppe .

INTENSIVE CARE MEDICINE, 2021, 47 (03) :282-291

[4] Mortality in patients admitted to intensive care with COVID-19: an updated systematic review and meta-analysis of observational studies [J].

Armstrong, R. A. ;

Kane, A. D. ;

Kursumovic, E. ;

Oglesby, F. C. ;

Cook, T. M. .

ANAESTHESIA, 2021, 76 (04) :537-548

[5]

Bishop C.M., 2006, PATTERN RECOGNITION, DOI [DOI 10.18637/JSS.V017.B05, 10.1117/1.2819119]

[6] Validation of severity scoring systems SAPS II and APACHE II in a single-center population [J].

Capuzzo, M ;

Valpondi, V ;

Sgarbi, A ;

Bortolazzi, S ;

Pavoni, V ;

Gilli, G ;

Candini, G ;

Gritti, G ;

Alvisi, R .

INTENSIVE CARE MEDICINE, 2000, 26 (12) :1779-1785

[7] Comparison of the APACHE III, APACHE II and Glasgow Coma Scale in acute head injury for prediction of mortality and functional outcome [J].

Cho, DY ;

Wang, YC .

INTENSIVE CARE MEDICINE, 1997, 23 (01) :77-84

[8]

Cucinotta Domenico, 2020, Acta Biomed, V91, P157, DOI 10.23750/abm.v91i1.9397

[9] A meta-analysis of potential biomarkers associated with severity of coronavirus disease 2019 (COVID-19) [J].

Danwang, Celestin ;

Endomba, Francky Teddy ;

Nkeck, Jan Rene ;

Wouna, Dominic Leandry Angong ;

Robert, Annie ;

Noubiap, Jean Jacques .

BIOMARKER RESEARCH, 2020, 8 (01)

[10] ICU beds: less is more? No [J].

de Lange, Dylan W. ;

Soares, Marcio ;

Pilcher, David .

INTENSIVE CARE MEDICINE, 2020, 46 (08) :1597-1599

← 1 2 3 4 5 →