Surface Web Merits for SARS-CoV-2 Pandemic in Iraq

Background: Data on SARS-CoV-2 from developing countries is not entirely accurate, demanding incorporating digital epidemiology data the pandemic.
 Objectives: To reconcile non-Bayesian models and artificial intelligence connected with classical (non-digital) epidemiological pandemic in Iraq.
 Results: Baghdad Sulaymaniyah represented statistical outliers connection daily cases recoveries, deaths, respectively. Multivariate tests neural networks detected a predictor effect of web searches concerning two search terms, "كورونا" "Coronavirus" (Pillai's Trace value=1, F=1106915.624, Hypothesis df=3, Error df=12, p-value<0.001, Partial Eta Squared=1). Using hierarchical clustering, we identified distinctive aggregates involving Iraqi capital, Kurdistan region, south Iraq. Three terms were most prevalent among users, including "كورونا", "كوفيد-19", "Coronavirus". Significant bivariate correlations all positive except for those term "لقاح كورونا". Al-Muthanna governorate residents least interested vaccines.Methods: Our study design longitudinal, period 24 February 2020 to 25 September 2020. We retrieved Ministry Health cases, deaths SARS-CoV-2, incorporated collateral Google Trends using five "Coronavirus", "COVID-19", The كورونا" represent Arabic translations "COVID-19 Vaccine". implemented multivariate machine learning scrutinize spatio-temporal trends Iraq interpret causality influencing Iraqis seek knowledge, via web, SARS-CoV-2.
 Conclusion: analyses triumphant syncretizing models, forms opine that current exquisite precious decision-makers at Health.