Advanced machine learning based exploration for predicting pandemic fatality: Oman dataset
Jamil Al Shaqsi, Osama Drogham, Sanad Aburass
Abstract
Pandemic-causing pathogens as COVID-19 can lead to a range of symptoms in humans, which may include fever, breathing difficulties, fatigue, cough, and severe respiratory distress. In more serious cases, these pathogens can be fatal. This paper presents the outcomes of a cohort study of 467 confirmed cases of COVID-19 as a specific pandemic-causing pathogen in Oman. Machine Learning-algorithms were employed to extract the hidden patterns and identify the factors of death or survival from the obtained datasets. The 10-fold Cross Validation was applied to ensure the reliability of the results. The experimental results demonstrated that some parameters contribute significantly to the death of the infected patients. It has been revealed that, Sodium, Hemoglobin, Mean Cell Volume, Chloride, and Eosinophil are the most significant factors in predicting the progression of the disease and the final outcome. The findings also suggested that age, gender, chronic kidney disease, and other complete blood count parameters are risk factors for poor prognosis in older patients. The obtained results are promising as they give insight into the main causes of patient status: recovery and death.