Predictors of Mortality Using Machine Learning Decision Tree Algorithm in Critically Ill Adult Patients with COVID-19 Admitted to the ICU.

Background:The Coronavirus Disease-19 (COVID-19) caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) is a major cause of intensive care unit (ICU) admissions globally. Robust data of epidemiology, characteristics, and disease outcomes from different regions and populations showed considerable variations. However, limited number of reports addressed predictors of mortality utilizing machine learning methods. Herein, we aimed to describe the association and relationship of a predefined set of variables found to be predictive of 28–day ICU outcome among adults COVID-19 patients admitted to the ICU using a machine learning decision tree (DT) algorithm.Methods:This was a prospective/retrospective, multicenter cohort study from 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 primary outcome was 28-day ICU mortality. Secondary outcomes were 90-day mortality and ICU length of stay. The predictors of mortality were identified using two predictive models, the conventional logistic regression and DT analysis.Results:A total of 1468 critically ill COVID-19 patients were included. The mean age was 55.9 (SD±15.1) years, with 74% of the patients were males. The 28-day ICU mortality was 540 (36.8%), while 90-day mortality was 600 (40.9%). The multivariable logistic regression model demonstrated that the PaO2/FiO2 ratio on ICU admission and the need for intubation or vasopressors could strongly predict 28-day ICU mortality. The DT algorithm identified five variables [need for intubation, need for vasopressors, age, gender, and PaO2/FiO2 ratio] provided in an algorithmic fashion to predict 28-day ICU outcome. Conclusion:Five clinical predictors of 28-day ICU outcome were identified using DT algorithmic analysis of COVID-19 patients admitted to ICU. The findings of this DT analysis may be used in ICU for early identification of critically ill COVID-19 patients who are at high risk of 28-day mortality.

[1]  Xiaocheng Wu,et al.  Clinical characteristics and a decision tree model to predict death outcome in severe COVID-19 patients , 2021, BMC Infectious Diseases.

[2]  M. Antonelli,et al.  Time course of risk factors associated with mortality of 1260 critically ill patients with COVID-19 admitted to 24 Italian intensive care units , 2021, Intensive Care Medicine.

[3]  O. Gevaert,et al.  AI-based analysis of CT images for rapid triage of COVID-19 patients , 2021, npj Digital Medicine.

[4]  Dandan Li,et al.  A Systematic Review and Meta-Analysis of Risk Factors Associated with Severity and Death in COVID-19 Patients , 2021, The Canadian journal of infectious diseases & medical microbiology = Journal canadien des maladies infectieuses et de la microbiologie medicale.

[5]  P. Horby,et al.  How the COVID-19 pandemic will change the future of critical care , 2021, Intensive Care Medicine.

[6]  T. Cook,et al.  Mortality in patients admitted to intensive care with COVID‐19: an updated systematic review and meta‐analysis of observational studies , 2021, Anaesthesia.

[7]  M. Curley,et al.  Phenotypes and personalized medicine in the acute respiratory distress syndrome , 2020, Intensive Care Medicine.

[8]  Aurélie Godard,et al.  Critical care for COVID-19 during a humanitarian crisis—lessons learnt from Yemen , 2020, Critical Care.

[9]  A. Robert,et al.  A meta-analysis of potential biomarkers associated with severity of coronavirus disease 2019 (COVID-19) , 2020, Biomarker research.

[10]  A. J. Agulló,et al.  Clinical features, ventilatory management, and outcome of ARDS caused by COVID-19 are similar to other causes of ARDS , 2020, Intensive Care Medicine.

[11]  Jun Yan,et al.  Development and external evaluation of predictions models for mortality of COVID-19 patients using machine learning method , 2020, Neural Computing and Applications.

[12]  K. Bhaskaran,et al.  Factors associated with COVID-19-related death using OpenSAFELY , 2020, Nature.

[13]  S. Al-Youha,et al.  Characteristics, risk factors and outcomes among the first consecutive 1096 patients diagnosed with COVID-19 in Kuwait , 2020, EClinicalMedicine.

[14]  K. Ferdinand,et al.  Association of cardiac biomarkers and comorbidities with increased mortality, severity, and cardiac injury in COVID‐19 patients: A meta‐regression and decision tree analysis , 2020, Journal of medical virology.

[15]  M. Debray,et al.  Admission chest CT score predicts 5-day outcome in patients with COVID-19 , 2020, Intensive Care Medicine.

[16]  D. D. de Lange,et al.  ICU beds: less is more? No , 2020, Intensive Care Medicine.

[17]  V. Siguret,et al.  Understanding pathophysiology of hemostasis disorders in critically ill patients with COVID-19 , 2020, Intensive Care Medicine.

[18]  Mickaël Ohana,et al.  High risk of thrombosis in patients with severe SARS-CoV-2 infection: a multicenter prospective cohort study , 2020, Intensive Care Medicine.

[19]  M. Moghadami,et al.  Epidemiological and clinical features of 2019 novel coronavirus diseases (COVID-19) in the South of Iran , 2020, BMC Infectious Diseases.

[20]  J. Vincent,et al.  Ethical aspects of the COVID-19 crisis: How to deal with an overwhelming shortage of acute beds , 2020, European heart journal. Acute cardiovascular care.

[21]  D. Cucinotta,et al.  WHO Declares COVID-19 a Pandemic , 2020, Acta bio-medica : Atenei Parmensis.

[22]  Qiurong Ruan,et al.  Clinical predictors of mortality due to COVID-19 based on an analysis of data of 150 patients from Wuhan, China , 2020, Intensive Care Medicine.

[23]  L. Mombaerts,et al.  A machine learning-based model for survival prediction in patients with severe COVID-19 infection , 2020, medRxiv.

[24]  G. Gao,et al.  A Novel Coronavirus from Patients with Pneumonia in China, 2019 , 2020, The New England journal of medicine.

[25]  Dimitar Vassilev,et al.  Application of Machine Learning Models for Survival Prognosis in Breast Cancer Studies , 2019, Inf..

[26]  S. Deppen,et al.  Developing prediction models for clinical use using logistic regression: an overview. , 2019, Journal of thoracic disease.

[27]  Kevin Read,et al.  A new hat for librarians: providing REDCap support to establish the library as a central data hub , 2018, Journal of the Medical Library Association : JMLA.

[28]  Abbas Toloie Eshlaghy,et al.  Using Three Machine Learning Techniques for Predicting Breast Cancer Recurrence , 2013 .

[29]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[30]  K. Polderman,et al.  Inter-observer variability in APACHE II scoring: effect of strict guidelines and training , 2001, Intensive Care Medicine.

[31]  M. Capuzzo,et al.  Validation of severity scoring systems SAPS II and APACHE II in a single-center population , 2000, Intensive Care Medicine.

[32]  D. Cho,et al.  Comparison of the APACHE III, APACHE II and Glasgow Coma Scale in acute head injury for prediction of mortality and functional outcome , 1997, Intensive Care Medicine.

[33]  J. Vincent,et al.  The SOFA (Sepsis-related Organ Failure Assessment) score to describe organ dysfunction/failure , 1996, Intensive Care Medicine.

[34]  John Rand,et al.  Using neural networks to diagnose cancer , 1991, Journal of Medical Systems.

[35]  L. D. Shabas.  Training algorithms for the decision tree method of pattern recognition , 1976, Cybernetics.

[36]  Xi Chen,et al.  A deep learning-based multi-model ensemble method for cancer prediction , 2018, Comput. Methods Programs Biomed..

[37]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[38]  A. Mancini,et al.  Validation of a severity of illness score (APACHE II) in a surgical intensive care unit , 2004, Intensive Care Medicine.

[39]  R. Simes,et al.  Treatment selection for cancer patients: application of statistical decision theory to the treatment of advanced ovarian cancer. , 1985, Journal of chronic diseases.