Data mining methods for covid-19 influences detection on technological tools and instrumentations performance

The primary aim of the survey is to examine the published papers to identify the most popular techniques and knowledge gaps for data mining. Since the danger of pandemics heightened public health worries, the researchers used data mining methods to uncover buried information. For systematic searches, websites for Science, Scopus, and PubMed databases were chosen. Then all papers found were evaluated in the process according to the Systematic Review and Meta-Analyses checklist Preferred Reporting Items for the selection of suitable publications. All findings were evaluated and presented on the basis of certain classifications. Of the 335 citations, 50 publications were selected by a scope evaluation as qualifying papers. The findings of the study indicate that the most popular DM was natural language processing (22%), with the most frequent method disclosing illness features (22 percent). Concerning illnesses, COVID-19 was the disease most addressed. The findings indicate that supervised learning methods predominate (90 percent). With respect to the healthcare sector, we discovered that infectious illness (36%) is the most common ailment, followed closely by disciplinary epidemiology. SPSS (22 percent) and R were the most prevalent software in the research (20 percent). The findings showed that some important study was carried out using the capacities of techniques of finding information to comprehend the unknown aspects of pandemic illnesses. However, most research will require therapy and illness control.