Smart COVID-19 Prediction System Using Neural Network

The pandemic of coronavirus COVID-19 has created a great danger and concern for humanity. Many researchers have done different types work in this area to provide medical services. In paper, we proposed smart Covid-19 diagnosis system by using Feed Forward Backpropagation Neural Network (FFBNN) Probabilistic (PNN). Based on personal information from patients such as (age, gender, contact with sick person) five symptoms (headache, fever, cough, sore throat, shortness breath) purpose used 510 samples that are collected sources, then compared previous studies. Results showed FFBNN achieved highest accuracy (98.0%), sensitivity (100%), specificity (94.4%), precision (97.1%), recall (100%) F1-score (98.52%). But PNN accuracy, sensitivity, specificity, precision, recall, 90.2%, 92.7%, 87.2%, 89.47%, 92.7% 91.07% respectively. most relevant features positive were breath, cough correlation coefficient 0.591, 0.495 0.488.