Covid Tools - A Webapp to fight Covid-19 Misinformation & Provide Right Information.
** This web app has 4 utilities:** you can checkout live at https://addasait-gu1de7yfkag-apigcp.nimbella.io
- Fact check: searches & finds the false information with appropriate reference why the info can be false/misleading. As we are on verge of US presidential election,this can be also used to check facts related to politics as well.
- Safety check: enter your pincode & check distance to nearby contamination zones .
- Help/Info: Interactive map showing nearby Testing Labs, Sample collection centers, Quarantine centers & Treatment centers.
- Urgency of Admission/Vaccination: Given Age & symptoms - categories the case as Low/High. High shows the emergency & they should be given preference for hospital admissions. Similar to this, we can use slightly different data & features to model the Urgency of Vaccination, which can be useful when vaccination arrives.
what inspired me?
For fact-check api:
- Misinformation pertaining to COVID-19 is Rising along with confirmed cases.
- While some misinformation is related to vaccine or symptoms, there is also other irrelevant info spread by people in social media channels like FB, Instagram & Youtube to increase their following.
- The idea is to combat all of these by validating the information to maintain peace of mind. It uses Google's Fact check API in backend (still in Alpha)
With cases increasing day by day, High population countries like India are facing shortages in available emergency beds. And with private hospitals coming into play, they started money bidding on the available beds - Who can pay more money gets the admission first regardless of emergency. I feel lack of money/not being rich should not be discriminator in for availing treatment.
In order to resolve this, I built prototype of an automated system with help of ML Algorithm which rather classifies the urgency of admission based on their age, symptoms & gives them the preference.
Caution: ML Algorithms are only as good as data. This is just a working prototype with a small sample of aggregated data, so don't except top-notch results.
Covid Safety check & Help pages:
- Lack of right information which is easily available for public. Having/knowing Information gives us courage
these currently work only on Indian Pincodes. They use MaymyIndia API's.
Safety Check: Taking the pincode of your current location, it shows approx distance/nearby covid-contaminated zones.
Help: This can show you Near by
- Testing Labs.
- Sample Collection Centers.
- Quarantine Centers.
- District hospitals.
- Treatment Centers.
how I built my project ?
backend: I used serverless platform called nimbella (based on OpenWhisk) to create serverless backend functions for fact-check & urgency of admission modelling using scikit-learn.
what I learned ?
Mostly I am backend guy, dealing with api's. Although I know little frontend it's been more than a year I worked on it. this made recollect my my basic html, css , js & jquery skills. Also, This is first time I am using a serverless platform to deploy my webapp.
- getting used to serverless web application & think in that way is confusing at a start but slowing when started reading & implementing things started to make sense. Now I feel easier as well, as this takes care of lot pain points in deployments.
Whats next ?
planning to learn react.js & port the frontend to react for better usability & interactivity.