Skip to content

This project focuses on studying the long-term symptoms following COVID-19 recovery. It includes an analysis of how smoking, stress, and anxiety affect COVID-19 outcomes and utilizes the Random Forest Classifier to predict post-COVID conditions, highlighting fatigue as a significant lingering symptom.

Notifications You must be signed in to change notification settings

Guri10/Post-covid-syndrome

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 

Repository files navigation

COVID-19 symptoms can sometimes persist for months. The virus can damage the lungs, heart and brain, which increases the risk of long-term health problems. Most people who had coronavirus disease 2019 (COVID-19) recovered completely within a few weeks. But some people — even those who had mild versions of the disease — continue to experience symptoms after their initial recovery. The objective of this study is to assess the prevalence of health status and physical and mental health symptoms among individuals Post COVID

From the results we got, we could analyse that smoking has a major role in the covid condition of patients getting severe. This was based on few models that we trained. The second major reason we could find was the stress and anxiety in the people due to the surrounding and other personal reasons. A lot of them also mentioned that this can be the only reason for patients not recovering faster. On the contrary of what we expected medications didn’t play a major role in worsening covid patients health. Still the side effects of Remdesivir cannot be ignored. Many of the doctors used remdesivir which resulted in near about 2% of the patients facing side effects. A large fraction of patients used normal medicines to recover but haven’t got any side effects of medicines. Like chest pain we can predict other post conditions as joint pain, brittle teeth, body sallowness, etc. If you are recovered from covid, there is a major chance that you will feel fatigue for some time in future. In the prediction algorithms, Decision Tree Classifier, even though giving good accuracy score, is performing the worst because it is unable to find feature importance for most of the columns in the dataset. Thus, we can conclude that Random Forest Classifier is ideal classifier for predicting post-covid health of patients. It gave good accuracy scores consistently and logical feature importance for most of the cases taken into consideration.

About

This project focuses on studying the long-term symptoms following COVID-19 recovery. It includes an analysis of how smoking, stress, and anxiety affect COVID-19 outcomes and utilizes the Random Forest Classifier to predict post-COVID conditions, highlighting fatigue as a significant lingering symptom.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages