One Sunday morning when I was normally browsing the web, I came across this paper titled An interpretable mortality prediction model for COVID-19 patients published in nature.com which gave me the inspiration to build this tool.
Link to the paper: https://www.nature.com/articles/s42256-020-0180-7
What it does
It displays the probability of COVID-19 infection with respect to the results of the Blood Test. Following are the parameters:-
- Lactic dehydrogenase (LDH),
- Lymphocyte, and
- High-sensitivity C-reactive protein (hs-CRP)
How I built it
- Django [Back-end framework]
- Scikit-learn (to train the model)
Challenges I ran into
Gathering the data to compile the COVID Blood Test dataset.
What I learned
I learned the concept of how Tailwind CSS is based upon class-based CSS styling, and how blood test parameters can also be taken into account for finding whether a person is infected with COVID-19 or not.
What's next for CBT Analysis - COVID Blood Test Analysis
To gather more real-world data and improve the dataset.