BinaryBros · PeaceOfCode 2026

Skin triage,
instantly.

A rural health worker photographs a skin lesion. Tvak classifies the severity and likely condition in seconds — helping decide when to refer, without a specialist on-site.

Analyze a lesion → How it works
80.7%
Severity accuracy
86.5%
Disease accuracy
29k
Training images
14
Skin conditions
What Tvak does
Severity first, always.

The most important question for a health worker isn't what the condition is called — it's how urgent it is. Tvak is built around that. Severity classification is the primary output. Disease name is secondary.

Healthy
No referral needed. Advise routine monitoring.
Mild
Treat locally. Refer if no improvement in 2 weeks.
Serious
Urgent referral. Refer to district hospital promptly.
Other
Further assessment needed. Refer if changes observed.
Known limitations

Severity classification is reliable (86.5% test accuracy). Disease name prediction is less reliable on real-world smartphone photos — the model was trained on clinical images and may misidentify specific conditions while still correctly classifying severity. Always treat the severity level as the primary signal.