IFMedTech/ner

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Clinical NER, Anatomy Detection, and POS Tagging

This Gradio application provides Named Entity Recognition (NER) for clinical text, anatomy detection, and Part-of-Speech (POS) tagging using state-of-the-art transformer models.

Features

• —Clinical NER: Extract medical entities (diseases, symptoms, treatments, etc.) from clinical text
• —Anatomy Detection: Identify anatomical terms in medical text
• —POS Tagging: Part-of-speech tagging for linguistic analysis
• —Multiple Output Formats: Get results in human-readable format or Prolog facts
• —Combined Analysis: Run all three analyses simultaneously

Models Used

• —Clinical NER: samrawal/bert-base-uncased_clinical-ner
• —Anatomy Detection: OpenMed/OpenMed-NER-AnatomyDetect-BioPatient-108M
• —POS Tagging: spaCy en_core_web_sm

Usage

The app provides four tabs:

1. 1.Clinical NER: Extract clinical entities from medical text
2. 2.Anatomy Detection: Detect anatomical terms
3. 3.POS Tagging: Analyze part-of-speech tags
4. 4.Combined Analysis: Run all analyses at once

Each tab supports:

• —Basic format: Human-readable output with entity highlighting
• —Prolog format: Structured facts for logic programming

Example

Input:

Patient presents with pain in the left ventricle and elevated cardiac enzymes. The heart shows signs of inflammation.

Output includes detected medical conditions, anatomical structures, and linguistic analysis.

Based On

This is a Gradio version of the clinical-ner FastAPI application, converted for easier demonstration and interaction.