COVID-19 HASTALIK TEŞHİSİNİN ADABOOST VE NAİVE BAYES ALGORİTMALARIYLA TAHMİN EDİLMESİ

Abstract

Coronavirus disease (COVID-19) has infected millions of people all over the world and caused the death of many people. Identifying people with this disease as soon as possible is an important factor to prevent the disease from spreading. For disease detection, PCR (Polymerase Chain Reaction) tests performed. The results of tests always cannot give 100% accurate. In addition, obtaining information about test results sometimes may take a few days. Regarding the persons who applied to health institutions with suspicion of that illness, the diagnosis of COVID-19 disease takes place with the emergence of different disease symptoms. In this study, diagnostic estimates made for patients in the COVID-19 Surveillance dataset implementing Adaboost and Naive Bayes machine learning (ML) algorithm. It is possible to make predictions about new data by gaining experience from pre-existing data by means of using ML algorithms. In dataset determined within international disease codes for COVID-19 disease diagnosis estimates. Symptoms of patients used as attribute data in the dataset and used in binary format to be suitable for machine learning algorithms. According to the results obtained in this study, the classification forecast made with 85% accuracy with the Naive Bayes algorithm and 100% with the Adaboost algorithm.