Investigating the Association of Acute Kidney Injury (AKI) with COVID-19 Mortality Using Data-Mining Scheme

16 Pages Posted: 2 Mar 2023

See all articles by Ayoub Tavakolian

Ayoub Tavakolian

Mashhad University of Medical Sciences - Department of Emergency Medicine

Mahdieh Farhanji

Islamic Azad University (IAU) - Department of Nursing

Farhang Shapouran

Sabzevar University of Medical Sciences

Arghavan Zal

Sabzevar University of Medical Sciences

Zahra Taheri

Sabzevar University of Medical Sciences

Tina Ghobadi

Sabzevar University of Medical Sciences

Vida Fazliani Moghaddam

Sabzevar University of Medical Sciences

Neda Mahdavi

Tehran University of Medical Sciences - Department of Epidemiology and Biostatistics

Nasrin Talkhi

Mashhad University of Medical Sciences - Department of Biostatistics

Abstract

COVID-19 has caused significant challenges in kidney research and disease management. Data mining techniques such as logistic regression (LR) and decision tree (DT) were used to model data. All analyses were performed using SPSS 25 and Python 3 programming language.The incidence of AKI was 14.1% and the overall mortality risk was 13% among COVID-19 patients. The mortality was associated with, AKI, age, marital status, smoking status, heart failure, chronic obstructive pulmonary disease, malignancy, and SPO2 level using LR. The accuracy, sensitivity, specificity, and AUC of the DT classifier were 70% (85%), 73% (75%), 78% (79%), and 77% (81%), respectively. Based on the DT model, the most identified important variables were AKI, age, WBC, BMI, and lymphocyte count, respectively. It was concluded that the incidence of AKI was high, and AKI was identified as one of the important factors that played an effective role in mortality due to COVID-19.

Note:
Funding Information: The authors state that this work has not received any funding.

Declaration of Interests: The authors declare that there is no conflict of interest or financial disclosure related to this publication.

Ethics Approval Statement: The study was approved by the Ethics Committee of the Sabzevar University of Medical Sciences with the code of IR.MEDSAB.REC.1400.076 in 2021. Written informed consent was obtained from all subjects (patients) in this study.

Keywords: Acute kidney injury, AKI, COVID-19, Decision tree, Logistic regression, Incidence

Suggested Citation

Tavakolian, Ayoub and Farhanji, Mahdieh and Shapouran, Farhang and Zal, Arghavan and Taheri, Zahra and Ghobadi, Tina and Fazliani Moghaddam, Vida and Mahdavi, Neda and Talkhi, Nasrin, Investigating the Association of Acute Kidney Injury (AKI) with COVID-19 Mortality Using Data-Mining Scheme. Available at SSRN: https://ssrn.com/abstract=4367712 or http://dx.doi.org/10.2139/ssrn.4367712

Ayoub Tavakolian

Mashhad University of Medical Sciences - Department of Emergency Medicine ( email )

Mashed
Iran

Mahdieh Farhanji

Islamic Azad University (IAU) - Department of Nursing ( email )

Farhang Shapouran

Sabzevar University of Medical Sciences ( email )

Asad Abadi
Sabzevar
Iran

Arghavan Zal

Sabzevar University of Medical Sciences ( email )

Asad Abadi
Sabzevar
Iran

Zahra Taheri

Sabzevar University of Medical Sciences ( email )

Asad Abadi
Sabzevar
Iran

Tina Ghobadi

Sabzevar University of Medical Sciences ( email )

Asad Abadi
Sabzevar
Iran

Vida Fazliani Moghaddam

Sabzevar University of Medical Sciences ( email )

Asad Abadi
Sabzevar
Iran

Neda Mahdavi

Tehran University of Medical Sciences - Department of Epidemiology and Biostatistics ( email )

Tehran
Iran

Nasrin Talkhi (Contact Author)

Mashhad University of Medical Sciences - Department of Biostatistics ( email )

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
69
Abstract Views
217
Rank
599,109
PlumX Metrics