How do I install the Openmed skill?

Run npx skillmds@latest add mkurman/openmed in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Openmed safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Openmed?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Openmed free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Openmed?

mkurman (@mkurman) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Openmed by mkurman — Agent Skill

Name: Openmed
Author: mkurman

Openmed

Production-ready medical NLP toolkit (maziyarpanahi/openmed). Entity extraction, assertion detection, PII de-identification, batch processing, REST API, and multilingual support. Covers installation, all model families, configuration, and deployment.

mkurman 80c733a 9 files · 16.4 KB Updated Sep 17, 2026

File contents

OpenMed

OpenMed transforms clinical text into structured insights. It bundles curated biomedical NER models, HIPAA-compliant de-identification, batch processing, a Dockerized REST API, and Apple Silicon acceleration — all behind a single analyze_text() call.

When to Use

Scenario	Start with
Extract diseases, drugs, anatomy from clinical notes	`references/entity-extraction`
Remove PHI/PII before sharing or storing data	`references/pii-deidentification`
Run NER on hundreds of clinical documents	`references/batch-processing`
Serve OpenMed behind a REST API	`references/rest-service`
Set up on Apple Silicon, Docker, or Swift	`references/installation`
Configure profiles, pick the right model	`references/configuration`
PII in French, German, Spanish, Portuguese, etc.	`references/multilingual-pii`
Privacy Filter (OpenAI / Nemotron) families	`references/privacy-filter`

Quick Start

git clone https://github.com/maziyarpanahi/openmed.git
cd openmed
uv pip install -e ".[hf]"

from openmed import analyze_text

result = analyze_text(
    "Patient started imatinib for chronic myeloid leukemia.",
    model_name="disease_detection_superclinical",
)
for entity in result.entities:
    print(f"{entity.label:<12} {entity.text:<35} {entity.confidence:.2f}")
# DISEASE      chronic myeloid leukemia          0.98
# DRUG         imatinib                           0.95

Model Registry (12+ Models)

Model	Entity Types
`disease_detection_superclinical`	DISEASE, CONDITION, DIAGNOSIS
`pharma_detection_superclinical`	DRUG, MEDICATION, TREATMENT
`pii_detection_superclinical`	NAME, DATE, SSN, PHONE, EMAIL, ADDRESS
`anatomy_detection_electramed`	ANATOMY, ORGAN, BODY_PART
`gene_detection_genecorpus`	GENE, PROTEIN

Browse the full catalog: openmed.life/docs/model-registry

Key Concepts

analyze_text() — single-call inference with configurable model, aggregation, format, and confidence threshold
BatchProcessor — multi-text and multi-file workflows with progress tracking
extract_pii() / deidentify() — HIPAA-compliant PII detection and redaction
Configuration Profiles — dev, prod, test, fast presets via YAML or env vars
REST API — FastAPI endpoints: /health, /analyze, /pii/extract, /pii/deidentify

References

OpenMed docs
OpenMed arXiv paper
OpenMed GitHub
references/installation.md — cross-platform install, Docker, Swift
references/entity-extraction.md — disease, drug, anatomy, gene models
references/pii-deidentification.md — HIPAA compliance, smart merging, anonymization
references/batch-processing.md — BatchProcessor API
references/rest-service.md — FastAPI endpoints, Docker
references/configuration.md — profiles, model registry, profiling
references/multilingual-pii.md — 9-language PII support
references/privacy-filter.md — OpenAI Privacy Filter, Nemotron, MLX

---name: openmeddescription: Production-ready medical NLP toolkit (maziyarpanahi/openmed). Entity extraction, assertion detection, PII de-identification, batch processing, REST API, and multilingual support. Covers installation, all model families, configuration, and deployment.---# OpenMed**OpenMed** transforms clinical text into structured insights. It bundles curated biomedical NER models, HIPAA-compliant de-identification, batch processing, a Dockerized REST API, and Apple Silicon acceleration — all behind a single `analyze_text()` call.## When to Use| Scenario | Start with ||---|---|| Extract diseases, drugs, anatomy from clinical notes | `references/entity-extraction` || Remove PHI/PII before sharing or storing data | `references/pii-deidentification` || Run NER on hundreds of clinical documents | `references/batch-processing` || Serve OpenMed behind a REST API | `references/rest-service` || Set up on Apple Silicon, Docker, or Swift | `references/installation` || Configure profiles, pick the right model | `references/configuration` || PII in French, German, Spanish, Portuguese, etc. | `references/multilingual-pii` || Privacy Filter (OpenAI / Nemotron) families | `references/privacy-filter` |## Quick Start```bashgit clone https://github.com/maziyarpanahi/openmed.gitcd openmeduv pip install -e ".[hf]"``````pythonfrom openmed import analyze_textresult = analyze_text( "Patient started imatinib for chronic myeloid leukemia.", model_name="disease_detection_superclinical",)for entity in result.entities: print(f"{entity.label:<12} {entity.text:<35} {entity.confidence:.2f}")# DISEASE chronic myeloid leukemia 0.98# DRUG imatinib 0.95```## Model Registry (12+ Models)| Model | Entity Types ||---|---|| `disease_detection_superclinical` | DISEASE, CONDITION, DIAGNOSIS || `pharma_detection_superclinical` | DRUG, MEDICATION, TREATMENT || `pii_detection_superclinical` | NAME, DATE, SSN, PHONE, EMAIL, ADDRESS || `anatomy_detection_electramed` | ANATOMY, ORGAN, BODY_PART || `gene_detection_genecorpus` | GENE, PROTEIN |Browse the full catalog: `openmed.life/docs/model-registry`## Key Concepts- **analyze_text()** — single-call inference with configurable model, aggregation, format, and confidence threshold- **BatchProcessor** — multi-text and multi-file workflows with progress tracking- **extract_pii()** / **deidentify()** — HIPAA-compliant PII detection and redaction- **Configuration Profiles** — `dev`, `prod`, `test`, `fast` presets via YAML or env vars- **REST API** — FastAPI endpoints: `/health`, `/analyze`, `/pii/extract`, `/pii/deidentify`## References- [OpenMed docs](https://openmed.life/docs/)- [OpenMed arXiv paper](https://arxiv.org/abs/2508.01630)- [OpenMed GitHub](https://github.com/maziyarpanahi/openmed)- `references/installation.md` — cross-platform install, Docker, Swift- `references/entity-extraction.md` — disease, drug, anatomy, gene models- `references/pii-deidentification.md` — HIPAA compliance, smart merging, anonymization- `references/batch-processing.md` — BatchProcessor API- `references/rest-service.md` — FastAPI endpoints, Docker- `references/configuration.md` — profiles, model registry, profiling- `references/multilingual-pii.md` — 9-language PII support- `references/privacy-filter.md` — OpenAI Privacy Filter, Nemotron, MLX

Frequently asked questions