extracting-clinical-entities

Extract biomedical entities from clinical text using OpenMed token-classification models.

5.0k|615|Updated Oct 4, 2025

Search Tags:#confidence scoring #de-identification #named entity recognition #clinical nlp #openmed #biomedical entities #medical text

Ready to run

npx skills add https://github.com/maziyarpanahi/openmed --skill extracting-clinical-entities

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: extracting-clinical-entities
Source: https://github.com/maziyarpanahi/openmed/tree/main/skills/extracting-clinical-entities
Command: npx skills add https://github.com/maziyarpanahi/openmed --skill extracting-clinical-entities

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill turns unstructured medical and biomedical text into structured named entities with labels, character offsets, and confidence scores, reducing manual chart review while keeping analysis on-device.

Core Features & Use Cases

Biomedical NER: Extract diseases, medications, anatomy, genes, proteins, and other clinical entities from notes.
Flexible outputs: Return results as objects, JSON, highlighted HTML, or CSV, with options for confidence filtering, entity grouping, and sentence detection.
Batch and CLI workflows: Save entity spans to JSONL, analyze files from the command line, and reuse loaded models for larger document collections.
Privacy-first pipelines: Run entity extraction after de-identifying clinical text so sensitive patient data remains on hardware under your control.

Quick Start

Ask the skill to extract diseases and medications from a clinical note using OpenMed's analyze_text function and return the results as JSON with confidence scores and character offsets.

Frequently Asked Questions about extracting-clinical-entities

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract biomedical entities from clinical text with confidence scores?▼

Use OpenMed with a compatible token-classification model to extract biomedical entities from clinical text. The process returns structured named entities complete with labels, character span offsets, and confidence scores for precise analysis.

Can I run named entity recognition on de-identified medical text locally?▼

Yes, you can run named entity recognition on de-identified medical text locally. Run entity extraction after de-identifying clinical documents so sensitive patient data remains secure on hardware under your direct control.

What output formats are supported when extracting medical entities from research corpora?▼

Supported output formats for extracted medical entities include dict, JSON, HTML, and CSV. You can apply confidence filtering, enable sentence detection, group entities, and save spans to JSONL for batch CLI workflows.

Does OpenMed support batch processing and JSONL persistence for clinical NLP datasets?▼

OpenMed supports batch processing and JSONL persistence for clinical NLP datasets. You can analyze files from the command line, save extracted entity spans to JSONL, and reuse loaded models for larger document collections.

What clinical entity types can be extracted from medical notes using token classification?▼

Clinical entity types extracted from medical notes using token classification include diseases, medications, anatomy, genes, and proteins. It applies named entity recognition to clinical notes, de-identified documents, and research corpora.