Prioritizing severity level of COVID-19 using correlation coefficient and intuitionistic fuzzy logic

Abstract

During the peak of COVID-19 pandemic crisis in 2020 and 2021, with limited medical resources and surge in Covid cases in every hospital and clinic, identifying the most vulnerable patient requiring immediate critical treatment was a great challenge for the medical practitioners. And if such a patient suffers from multiple ailments, his/her condition may deteriorate rapidly if proper treatment is delayed any further. In this paper, we used a novel method which supports medical care units in identifying the patients who need urgent medical treatment. We used Gerstenkorn and Manko correlation coefficient and the intuitionistic fuzzy sets to classify such patients, who should be given the highest priority to start the treatment first. The role of this correlation measurement is very vital in any decision-making process. An intuitionistic fuzzy set (IFS) handles uncertainty, vagueness, ambiguity etc. present in the data and helps in making decision process more realistic. Combining the correlation coefficient with the Intuitionistic fuzzy set makes the decision making process more easy, accurate and reliable. We used COVID-19 dataset which maintains early-stage symptoms of COVID-19 patients, and is publicly available. We applied correlation coefficient and IFS to predict the severity level of the COVID-19 cases by establishing the relationship between the patient and the ailments a COVID-19 patient is suffering from.

On utilizing modified TOPSIS with R-norm q-rung picture fuzzy information measure green supplier selection

“…An intuitionistic fuzzy c-means clustering technique has been given by Kaur [ 16 ] which incorporates the component of hesitancy and fuzzy entropy for the analysis of noise sensitivity. Also, Tarannum and Jabin [ 17 ] presented the decision-making model for the severity of COVID-19 with the incorporation of correlation coefficients under an intuitionistic fuzzy environment.…”