COVID Symptom Study model to improve Symptom Checker accuracy

[brunobowden]

Consider using the COVID Symptom Study model to improve the accuracy of the symptom checker tool.

Research Paper: https://www.nature.com/articles/s41591-020-0916-2 GitHub: https://github.com/zoe/covid-tracker-react-native

The authors may have a system with improved accuracy but this is the linear model published in the research paper:

Predictionmodel=−1.32−(0.01×age) +(0.44×sex)+(1.75×lossofsmellandtaste) +(0.31×severeorsignificantpersistentcough) +(0.49×severefatigue)+(0.39×skippedmeals)

All symptoms are coded as 1 if the person self-reports the symptom and 0 if not. The sex feature is also binary, with 1 indicative of male participants and 0 representing females. The obtained value is then transformed into predicted probability using exp(x)/(1 + exp(x)) transformation followed by assigning cases of predicted COVID-19 for probabilities >0.5 and controls for probabilities <0.5.

• [x] Searched the existing issues to ensure you are not creating a duplicate.
• [x] Followed the Contributor Guidelines.
• [x] Issue has descriptive title focused on the feature or problem from the user's perspective

[mohak852]

@advayDev1 I wanna work in this issue can you assign this to me

[advayDev1]

Hi @mohak852 thanks for your interest - we are currently waiting while we decide and document what our next feature set is.

As you can see, this issue has a needs:triage label, so until we've decided whether or not this feature will make it into the product, we won't be performing engineering on it.

[mohak852]

ok thanks @advayDev1 for your responce.