💡 Inspiration

Our inspiration was to create a health platform where people can also earn rewards for their health-related activities to keep motivating them. Users can mint their data to earn tokens and spend them to get rewards. Users can log in with their FitBit user account to get their data listed for keeping track and also as proof of their proper health data.

💻 What it does

HealthCrypto is a decentralized platform that allows users to earn tokens for their health-related activities. Users can also mint their data to earn an exclusive non-fungible token. If they so choose, this digital token and the encrypted data it represents can be held or "burned" for future discounts on healthcare services or insurance premiums. Users need to log in with their FitBit account, acting as a "proof of health" creating an exclusive token/point system that we can either use to ensure adherence of patients to earn heart points to be used for various purposes.

⚙️How we built it

  • ML: Python, Skikit-Learn, TensorFlow
  • Frontend: HTML, CSS, JS
  • Backend: Django
  • Database: CockroachDB
  • Authentication: Auth0
  • IPFS: NFT Storage

☁️ Best use of Linode Cloud

  • We utilized Linode for its hosting and storage. Linode is one of the top IaaS providers and is incredibly easy to use and the free Linode credit from MLH for us to learn and build on Linode was the cherry on the cake!
  • Linode is fast, flexible, and reliable, and we truly enjoyed using it.

💾 Use of CockroachDB

  • We have used CockroachDB as a primary database because it is an easy-to-use, open-source and indestructible SQL database.

🔑 Best Use of Auth0

  • We have used Auth0 for secure user authentication

🧠 Challenges we ran into

  • Reducing the size of the trained model was challenging for us. Bigger size meant that users have to wait a long time for obtaining prediction results and we would not be able to upload it on GitHub as well. We researched the ways we can use to reduce the model's size and found Quantization Aware Training to be useful and effective and we are glad it worked.
  • As we were working with the blockchain tech for the first time it was a bit difficult in the beginning but soon we were able to get it working.

🏅 Accomplishments that we're proud of

  • Completing all these features in just two days is another.
  • We are proud of our ability to use the latest technology and the best way to do it.

📖 What we learned

  • Using Quantization Aware Training to reduce the size of the model
  • Integrate ML models directly without creating an API with Django
  • Using NFT to store data
  • Collaboration.

🚀 What's next for HealthCrypto

  • Add more features and improve the UI.
  • Adding a secure web app to store data.

Built With

Share this project: