Self-diagnosis of SARS-CoV-2 using ELECTRE and PROMETHEE methods

Abstract

The Sars-CoV-2 pandemic resulted in limited space for the public to interact and carry out their daily routines. The limited space available forces everyone to be more creative in meeting their daily needs. With currently developing technology, new information ecosystems have been developed to address problems especially in critical fields such as health, the economy and education. Artificial intelligence is now very commonly implemented in various fields, Decision Support Systems (DSS) are AI which are often found in most systems that are widely used. Many studies have been conducted using DSS. However, only a few are focused on overcoming the support system for the pandemic that has occurred since late 2019. Most of these DSS methods use outranking methods for multi-criteria parameters owned by users who require wise decisions to be decided. The outranking method has been developed in this article with the aim of obtaining a self-diagnosis system for patients with covid types of Alpha (B.1.17), Beta (B.1.351), Gamma (P.1), Delta (B.1.617.2), and Omicron (B.1.1 529) this detection system was developed using Electre and Promethee methods. Both methods utilize outranking to obtain detection results based on multi-criteria decisions of the symptoms experienced by the patient. From the system that has been developed, it is obtained data that is quite promising for the implementation of this outranking system, namely for both systems to obtain an accuracy of approximately 90% and more. This data indicates that the role of artificial intelligence, especially the decision system, is a method that is reliable enough to be implemented in MCDM (Multi-Criteria Decision Making).