Investigating the Association of Acute Kidney Injury (AKI) with COVID-19 Mortality Using Data-Mining Scheme
16 Pages Posted: 2 Mar 2023
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: Suggested Citation