NER Biomedical PHI Ensemble

NER Biomedical PHI Ensemble

A Streamlit app for named entity recognition in biomedical text that combines three named models through an ensemble config. It suits people who want to try entity tagging in a browser.

Made by ajitrajasekharan on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: NER Biomedical PHI Ensemble is a Streamlit app on Hugging Face Spaces for named entity recognition. Its title points to biomedical text and PHI, short for protected health information. It names three models, ajitrajasekharan/biomedical, flair/pos-english and google-bert/bert-base-cased, and the repository carries an ensemble config.

Who it suits: It suits people who work with biomedical text and want to try entity tagging in a browser, and developers who want to read how several models are combined.

Industry | Who uses it | How they use it | Example
Healthcare research | Text-mining researchers | Try entity tagging on biomedical sentences | Open the Space and enter a sentence
Health data | Data engineers | Read the ensemble config to see how models are combined | Download the Space and open ensemble_config.json
Education | Instructors | Show how several models can share one tagging task | Walk through app.py and common.py

Anyone who needs documented privacy guarantees or measured accuracy can skip it, since the source gives none.

Where to use it:

• A web browser, straight from the Space page on Hugging Face
• Windows, macOS or Linux with Python, as a local copy

Use case | Who | What they get back
Tag entities in biomedical text | Researchers | Entities marked in the text shown in the browser
Study an ensemble setup | Developers | Config files, entity type lists and batch scripts in one repository

How to set it up: Using it online needs nothing. A local copy needs these first.

• Python and pip
• The huggingface_hub package, to fetch the files
• Streamlit, and the packages in requirements.txt

1. Install the Hugging Face Hub package.
2. Download the Space into a folder called NER-Biomedical-PHI-Ensemble.
3. Move into that folder.
4. Install Streamlit, then the packages from requirements.txt.
5. Start the app with Streamlit.

pip install -U huggingface_hub
hf download ajitrajasekharan/NER-Biomedical-PHI-Ensemble --repo-type space --local-dir NER-Biomedical-PHI-Ensemble
cd NER-Biomedical-PHI-Ensemble
pip install streamlit
pip install -r requirements.txt
streamlit run app.py

How to use it: Open the Space page on Hugging Face, enter some biomedical text and read the tagged result. For a local copy, run streamlit run app.py in the folder and open the page it starts.

Example: You paste a sentence from a clinical note into the text box. The app runs its models over it and shows the entities it finds in the sentence.

For newcomers and experts: If you are new, open the Space page and try one short sentence. Named entity recognition means a program marks the names of things in your text, such as a drug or a person.

If you know the field, the repository holds an ensemble config, entity type lists and batch scripts, so the models are combined rather than used alone. How the votes are merged is in the code, and the source does not describe it.

You enter biomedical text in the browser
app.py runs the models listed in the config
The tagged entities show on the page

Good to know:

• The README gives no description, so the exact output is clear only when you try the app
• It names three models and needs Streamlit and the packages in requirements.txt
• License: mit
• Cost to run: none named
• Data it reaches: the three models it names and the files in its own repository

On Hugging Face, 13 November 2026

• Likes: 2
• Built with: streamlit
• License: mit

Links

• Space: https://huggingface.co/spaces/ajitrajasekharan/NER-Biomedical-PHI-Ensemble
• Files: https://huggingface.co/spaces/ajitrajasekharan/NER-Biomedical-PHI-Ensemble/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.