Explainable Artificial Intelligence for COVID-19 Diagnosis Through Blood Test Variables

This work proposes an explainable artificial intelligence approach to help diagnose COVID-19 patients based on blood test and pathogen variables. Two glass-box models, logistic regression boosting machine, two black-box random forest support vector were used assess the disease diagnosis. Shapley additive explanations explain predictions for while models feature importance brought insights into most relevant features. All global show eosinophils leukocytes, white cells are among essential features COVID-19. Moreover, best model obtained AUC of 0.87.