A new DoE-MTOPSIS based prediction model suggestion to capture potential SARS-CoV-2 reactivated patients

Abstract

Difficulties to use convenient data during the Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) pandemic outbreak and complexities of the problem attitude crucial challenges in infectious disease modelling studies. Motivated by the on-going reach to predict a potential reactivated SARS-CoV-2 (COVID-19), we suggest a prediction model that beyond the clinical characteristics based evaluation approaches. In particular, we developed a possibly available and more efficient prediction model to predict a potential reactivated SARS-CoV-2 (COVID-19) patient. Our paper aims to explore the applicability of a modified Technique for Order Preference by Similarity to Ideal Solutions (MTOPSIS) integrated Design of Experiment (DoE) method to predict a potential reactivated COVID-19 patient in real-time clinical or laboratory applications. The presented novel model may be of interest to the readers studying similar research areas. We illustrate MTOPSIS integrated DoE method by applying it to the COVID-19 pandemic real clinical cases from Wuhan/China-based data. Despite the small sample size, our study provides an encouraging preliminary model framework. Finally, a step by step algorithm is suggested in the study for future research perspectives.