Determining the Predictive Performance of Hybrid Classification Algorithms on Covid-۱۹ Patient Death Rate in Nigeria

several epidemiological models are being used around the world to project the number of infected individuals and the mortality rates of the COVID-۱۹ outbreak. Advancing accurate prediction models is of utmost importance to take proper actions. Due to the lack of essential data and uncertainty, the epidemiological models have been challenged regarding the delivery of higher accuracy for long-term prediction. The focus of this study is to determine the predictive performance of different classification algorithms on COVID-۱۹ patient death rate in Nigeria. This research aims at determining the predictive accuracy of the various factors contributing to the increase death rate of covid-۱۹ in Nigeria such as patient’s displayed symptoms, patient’s level of education and patient’s age. The primary data used for this study were collected from Akwa Ibom State Covid-۱۹ surveillance and monitoring unit which aided the classification of the components and factors contributing to the spread of the disease. For analysis, the study adopted the following data mining techniques (classification algorithms): logistic regression, conditional inference tree, adaptive boost, decision tree, random forest, support vector machine and neural network. The R Programming statistical tool was used in this study and from cross examination of the above data mining techniques, conditional inference tree gave the highest prediction accuracy of (۷۳.۲%), sensitivity (۹۸%), F-value (۸۶.۷%) and precision (۷۴%) as compared to other classification algorithms. It was identified that the area under the curve (AUC) for the selected model (conditional inference tree) is (۹۶%) indicating that the model excellently predicted patient death. The findings show that the number of symptoms displayed and the age range of patients are the major causes of death and the increase in the number of cases in the state.

کلیدواژه ها:

Data mining ، Classification techniques ، Prediction ، Covid-۱۹