https://github.com/xiaowuc2/covid-classifier-a-simpler-supervised-machine-learning-model

An efficient simpler supervised machine learning model to assist in the diagnosis of COVID-19. We've achieved 98.06% accuracy.
https://github.com/xiaowuc2/covid-classifier-a-simpler-supervised-machine-learning-model

classifier covid-19 machine-learning

Last synced: 9 days ago
JSON representation

An efficient simpler supervised machine learning model to assist in the diagnosis of COVID-19. We've achieved 98.06% accuracy.

• Host: GitHub
• URL: https://github.com/xiaowuc2/covid-classifier-a-simpler-supervised-machine-learning-model
• Owner: xiaowuc2
• Created: 2021-10-25T21:17:20.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2022-01-13T17:35:56.000Z (about 3 years ago)
• Last Synced: 2024-11-19T20:52:45.018Z (2 months ago)
• Topics: classifier, covid-19, machine-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 553 KB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        


  

    

  




 COVID-Classifier: a simpler supervised machine learning model / ​Code​ / ​Website​


### Abstract

Coronavirus disease (COVID-19) is an infectious disease causedby the SARS-CoV-2 virus. It is the largest category for anRNA  virus. Authorities in 222 countries and territories have reportedabout 244.2 million Covid-19 cases and 5 million deaths since Chinareported its first cases to the World Health Organization (WHO) in De-cember 2019. Our proposed classifier assists in the early diagnosis of Covid-19. There are many well established model which can give moreaccurate results based on X-ray or CT scans, but they are convoluted andabstruse for normal person. We’ve developed a more simpler model with‘`Yes`’ and ‘`No`’ types on question, where our huge dataset are trained with these features : ‘BreathingProblem’, ‘Fever’, ‘Dry Cough’, ‘Sore throat’, ‘Running Nose’, ‘Asthma’, ‘Chronic  Lung  Disease’, ‘Headache’, ‘Heart  Disease’, ‘Diabetes’, ‘HyperTension’, ‘Fatigue’ and eight more. Based on these data the model willpredict result in a probabilistic view.

### How to use:

 

### Test results:

```

	        Precision	 Sensitivity	 F-score	 Support

COVOD-19	   96%	           100%	           0.98	           25

Normal	           88%	           100%	           0.94	           31

Pneumonia	   100%	           82%	           0.91	           28

```