Open AccessPrediction of CoVid-19 mortality in Iraq-Kurdistan by using Machine learning
Author(s) -
Ardalan Husin Awlla,
Brzu T. Muhammed,
Sherko H. Murad,
Sabah N. Ahmad
Publication year - 2021
Publication title -
uhd journal of science and technology
Language(s) - English
Resource type - Journals
eISSN - 2521-4217
pISSN - 2521-4209
DOI - 10.21928/uhdjst.v5n1y2021.pp66-70
Subject(s) - naive bayes classifier , covid-19 , support vector machine , decision tree , coronavirus , mortality rate , artificial intelligence , machine learning , computer science , analytics , bayes' theorem , data mining , disease , medicine , bayesian probability , infectious disease (medical specialty)
This research analyzed different aspects of coronavirus disease (COVID-19) for patients who have coronavirus, for find out which aspects have an effect to patient death. First, a literature has been made with the previous research that has been done on the analysis dataset of coronavirus using Machine learning (ML) algorithm. Second, data analytics is applied on a dataset of Sulaymaniyah, Iraq, to find factors that affect the mortality rate of coronavirus patients. Third, classification algorithms are used on a dataset of 1365 samples provided by hospitals in Sulaymaniyah, Iraq to diagnose COVID-19. Using ML algorithm provided us to find mortality rate of this disease, and detect which factor has major effect to patient death. It is shown here that support vector machine (SVM), decision tree (DT), and naive Bayes algorithms can classify COVID-19 patients, and DT is best one among them at an accuracy (96.7 %).