Identification of Risk Factors Associated With Mortality Among Patients With COVID-19 Using Random Forest Model: A Historical Cohort Study

Fatemeh  Moghaddam-Tabrizi; Tahereh Omidi; Masoomeh  Mahdi-Akhgar; Robabeh Bahadori; Rohollah Valizadeh; Hamidreza  Farrokh-Eslamlou

doi:10.18502/acta.v59i8.7248

Fatemeh Moghaddam-Tabrizi Reproductive Health Research Center, Clinical Research Institute, Urmia University of Medical Sciences, Urmia, Iran
Tahereh Omidi Department of Biostatistics, Hamadan University of Medical Sciences, Hamadan, Iran
Masoomeh Mahdi-Akhgar Department of Biostatistics, Tarbiat Modares University, Tehran, Iran
Robabeh Bahadori Department of Pediatric, Urmia University of Medical Sciences, Urmia, Iran
Rohollah Valizadeh Department of Epidemiology, School of Public Health, Iran University of Medical Sciences, Tehran, Iran
Hamidreza Farrokh-Eslamlou Department of Public Health, School of Health, Urmia University of Medical Sciences, Urmia, Iran

DOI: https://doi.org/10.18502/acta.v59i8.7248

Keywords: Decision tree; Random forests; Variable importance; Coronavirus disease 2019 (COVID-19); Mortality

Abstract

There is conflicting evidence about factors associated with Clinical course and risk factors for mortality of adult inpatients. We aimed to identify the demographic, clinical, treatment, and laboratory data factors associated with mortality in the Khoy district. We performed a retrospective cohort study including COVID-19 infected patients who were admitted to Qamar-Bani Hashim hospital from 2 November 2020 to 4 December 2020. We used random forest methods to explore the risk factors associated with death. The applied method was evaluated using sensitivity, specificity, accuracy, and the area under the curve. Age, pulmonary symptoms, patients need a ventilator, brain symptoms, nasal airway, job were the most important risk factors for mortality of COVID-19 in the random forest (RF) method. The RF method showed the highest accuracy, 82.9 and 79.3, for training and testing samples, respectively. However, this method resulted in the highest specificity (89.5% for training and 95.7% for testing sample) and the highest sensitivity (91.9% for training and 94.5% for testing sample). The potential risk factors consisting of older age, pulmonary symptoms, the use of a ventilator, brain symptoms, nasal airway, and the job could help clinicians to identify patients with poor prognosis at an early stage.