camescopetech/NLP-classification

LLM-based disease classification from symptom text descriptions using prompt engineering on the Symptom2Disease dataset. Compares zero-shot, few-shot (static & TF-IDF dynamic), and Chain-of-Thought strategies across 15 disease classes. Best result: F1-macro 0.55 with dynamic few-shot.

15
/ 100
Experimental
No License No Package No Dependents
Maintenance 13 / 25
Adoption 1 / 25
Maturity 1 / 25
Community 0 / 25

How are scores calculated?

Stars

1

Forks

Language

Jupyter Notebook

License

Last pushed

Mar 24, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/camescopetech/NLP-classification"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.