H Al-Najjar1, N Al-Rousan. 1. Department of Computer Engineering, Faculty of Engineering and Architecture, Istanbul Gelisim University, Istanbul, Turkey. nadia.rousan@yahoo.com.
Abstract
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.
OBJECTIVE:CoronavirusCOVID-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-19patients 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.
Authors: Ania Syrowatka; Masha Kuznetsova; Ava Alsubai; Adam L Beckman; Paul A Bain; Kelly Jean Thomas Craig; Jianying Hu; Gretchen Purcell Jackson; Kyu Rhee; David W Bates Journal: NPJ Digit Med Date: 2021-06-10
Authors: Narges Razavian; Vincent J Major; Mukund Sudarshan; Jesse Burk-Rafel; Peter Stella; Hardev Randhawa; Seda Bilaloglu; Ji Chen; Vuthy Nguy; Walter Wang; Hao Zhang; Ilan Reinstein; David Kudlowitz; Cameron Zenger; Meng Cao; Ruina Zhang; Siddhant Dogra; Keerthi B Harish; Brian Bosworth; Fritz Francois; Leora I Horwitz; Rajesh Ranganath; Jonathan Austrian; Yindalon Aphinyanaphongs Journal: NPJ Digit Med Date: 2020-10-06