README.md

metadata

title: AI-Powered Differential Diagnosis (Educational)
emoji: ⚕️
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false
license: mit

AI-Powered Differential Diagnosis (Educational)

This Hugging Face Space allows you to input patient symptoms and receive a ranked list of possible differential diagnoses based on TF-IDF similarity to an existing dataset.

How It Works

• Input at least 3 comma-separated symptoms.
• The app uses TF-IDF vectorization to compare your input against the dataset.
• It provides:
  • A ranked list of possible diagnoses.
  • A chain of reasoning explaining logical steps.
  • Few-shot examples and a tree of hypotheses.

Files Required

• app.py
• requirements.txt
• differential_diagnosis_dataset.csv

Run Locally

pip install -r requirements.txt
python app.py

Then open http://127.0.0.1:7860 in your browser.

Deployment Steps on Hugging Face

1. Go to your Space (e.g. https://huggingface.co/spaces/Konaguy/GradiotestApp)
2. Upload the files listed above using the Files and versions → Add file → Upload files option.
3. Commit your changes.
4. Wait for the build to finish; the Space will automatically start the Gradio app.

Safety Notice

This project is for educational and research purposes only. It is not a medical device and should not be used for real patient diagnosis or treatment. Always consult a licensed medical professional for actual care or emergencies.