Inspiration

Diagnostic errors are one of the leading types of preventable medical errors stemming from miscommunication between providers and patients. BloodBud attempts to address that knowledge gap by explaining a confusing document in layman's terms.

What it does

BloodBud extracts the relevant information and feeds it to Google Gemini. Gemini produces a summary of the blood report, including information like the meaning of the numbers, whether or not they fall within normal ranges, implications, and terminology that will facilitate further discussions with your provider.

How we built it

BloodBud was built using Flask, HTML, CSS, and JavaScript on the front-end, with Python and Google Gemini working together in the back-end.

Challenges we ran into

Connecting the front- and back-ends posed a challenge for us as we were unsure how to fully ingest a PDF file uploaded in the front-end. We initially wanted to incorporate MongoDB to create a database of past blood reports, but the process was

Accomplishments that we're proud of

We're proud of how we were able to pull it all together.

What we learned

We learned a lot about front-end development and how all the frameworks work together in concert to create interactive web applications. It was also the first time using an AI's API for all of us, so that was a fun experience.

What's next for BloodBud

We would like BloodBud to be compatible with different formats of blood reports, since there is no clear standard. Additionally, we would like to build a database that holds previous blood reports to give a comprehensive overview of a patient's blood history.

Share this project:

Updates