Flyeasy
Mobile app that connects travelers with verified passengers on their exact flight.
Solo founder and developer
- React Native
- Expo
- TypeScript
- Supabase (Postgres)
- AeroDataBox API
- Claude API
Replicated and extended a Nature Medicine RL model for skin-lesion triage, where a missed melanoma costs far more than over-treating.
Classifiers optimized for accuracy treat every error the same, but in skin-cancer triage a missed melanoma costs far more than an unnecessary excision. The paper turns this into a decision problem and uses an expert-designed reward matrix to teach an RL agent the asymmetric cost.
With a team of three, I reproduced the paper's diagnosis results on HAM10000 (~10,000 images, 7 classes), where our plain DQN matched the paper's melanoma recall (0.80 vs 0.795). I replicated the lesion-level management pipeline (dismiss, cryotherapy, excise) and wrote the naive and threshold-based baselines myself, so we could compare all three approaches. I also simulated the environment, tweaked the reward matrix for comparison runs, built the evaluation visualizations and shaped the presentation.
Reward design shapes what the agent learns. In our runs, RL matched a hand-tuned threshold rule on melanoma safety with about 2.5x fewer unnecessary excisions. Our numbers followed the paper's trends but ran 15 to 30 points lower, mostly because we used an internal split instead of the paper's external ISIC 2018 test set.
For the team's extension we used a Dueling DQN, which splits the network into two parts: one estimates how good a case is overall, the other how much better each action is than the alternatives. Separating the two tends to make learning steadier when several actions score similarly, which, together with reward-matrix tuning, likely helped it reach about 0.96 melanoma recall.
More top projects
Mobile app that connects travelers with verified passengers on their exact flight.
Solo founder and developer
A Claude Code agent harness that finds jobs matched to your profile, fills applications for your review, and tracks every response from Gmail.
Designed and built solo