Mobile Health · Hackathon

Draculin

Walk through Draculin: a Flutter + Django health-tracking app with an AI chatbot and computer vision assistance. BitsXLaMarató 2023 finalist.

Frontend Code (GitHub)Backend Code (GitHub)

The 22-second version

A question typed into the chatbot, a quiz verdict, a photo of a pad turned into a blood-volume estimate, and a week of daily totals.

MusicSascha Ende, Happy Beats / Business Moves Vol. 12, CC BY 4.0

Interactive demo of the Draculin health app. Start the backend (cd Draculin-Backend && docker compose up -d) for live chat and news.

About this project

Draculin was developed for the BitsXLaMarató 2023 hackathon, where it reached the finals. The app uses a Google LLM-powered chatbot for health guidance and computer vision to analyze images for menstrual health tracking. The frontend is built with Flutter (supporting iOS, Android, and web), while the backend runs on Django with image inference capabilities.

PreviousBachelor's Thesis — Polyp DetectionBachelor's thesis on detecting polyps in colonoscopy images with deep learning, using CycleGAN and SPADE to generate synthetic training data when real labels were scarce.
  • PyTorch
  • CycleGAN
  • Object Detection
  • UPC
NextBitsXLaMarató — AortaBitsXLaMarató 2022 winner: a tool to segment the aorta in ultrasound videos with Mask R-CNN and reconstruct it in 3D to help detect aneurysms.
  • PyTorch
  • OpenCV
  • 3D
  • CV

More Projects

Algorithm Visualizer
  • Qwik
  • Canvas
  • Algorithms
  • Graphs
  • Sorting
Trip Planner (Expert System)
  • HTMX
  • Alpine.js
  • Litestar
  • Expert System
Travel agency (PDDL)
  • PDDL
  • Planning
  • UPC
JSBach Interpreter
  • ANTLR4
  • Web Audio
  • Language