Download PDFOpen PDF in browser

Artificial Intelligence Approach to Predict the COVID-19 Patient's Recovery

EasyChair Preprint no. 3223

9 pagesDate: April 22, 2020


Coronaviruse is the new pandemic hitting all over the world. Patients all over the world are facing different symptoms. Most of the patients with severe symptoms die specially the elderly. In this paper, we test three machine learning techniques to predict the patient’s recovery.  Support vector machine was tested on the given data with mean absolute error   of 0.2155. The Epidemiological data set was prepared by researchers from many health reports of real time cases to represent the different attributes that contribute as the main factors for recovery prediction. A deep analysis with other machine learning algorithms including artificial neural networks and regression model were test and compared with the SVM results.  We conclude that most of the patients who couldn't recover had fever, cough, general fatigue and most probably malaise. Besides, most of the patients who died live in Wuhan in china or visited Wuhan, France, Italy or Iran.

Keyphrases: Artificial Intelligence, Corona Virus, COVID-19, Regression, Support Vector Machine

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Aboul Ella Hassanien and Aya Salam and Ashraf Darwish},
  title = {Artificial Intelligence Approach to Predict the COVID-19 Patient's Recovery},
  howpublished = {EasyChair Preprint no. 3223},

  year = {EasyChair, 2020}}
Download PDFOpen PDF in browser