A classifier prediction model to predict the status of Coronavirus CoVID-19 patients in South Korea
Yükleniyor...
Dosyalar
Tarih
2020
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
VERDUCI PUBLISHER, VIA GREGORIO VII, ROME, 186-00165, ITALY
Erişim Hakkı
info:eu-repo/semantics/openAccess
Attribution-NonCommercial-NoDerivs 3.0 United States
Attribution-NonCommercial-NoDerivs 3.0 United States
Özet
OBJECTIVE: Coronavirus COVID-19 further transmitted to several countries globally. The status of the infected cases can be determined basing on the treatment process along with several other factors. This research aims to build a classifier prediction model to predict the status of recovered and death coronavirus CovID-19 patients in South Korea. MATERIALS AND METHODS: Artificial neural network principle is used to classify the collected data between February 20, 2020 and March 9, 2020. The proposed classifier used different seven variables, namely, country, infection reason, sex, group, confirmation date, birth year, and region. The most effective variables on recovered and fatal cases are analyzed based on the neural network model. RESULTS: The results found that the proposed predictive classifier efficiently predicted recovered and death cases. Besides, it is found that discovering the infection reason would increase the probability to recover the patient. This indicates that the virus might be controllable based on infection reasons. In addition, the earlier discovery of the disease affords better control and a higher probability of being recovered. CONCLUSIONS: Our recommendation is to use this model to predict the status of the patients globally.
Açıklama
Document Information
Language:English
Accession Number: WOS:000525326200064
PubMed ID: 32271458
Anahtar Kelimeler
Epidemiology, Engineering and technology, Infection, South Korea
Kaynak
EUROPEAN REVIEW FOR MEDICAL AND PHARMACOLOGICAL SCIENCES
WoS Q Değeri
Q2
Scopus Q Değeri
Q2
Cilt
24
Sayı
6
