Linking Umls Concepts

What it does

When your agent uses it

• The user wants to normalize concepts across vocabularies to a single CUI
• Resolve synonyms via the UMLS
• Filter by semantic type
• Cross-walk between SNOMED CT

Example prompts

• “Use the linking-umls-concepts skill to link entities extracted by OpenMed to UMLS Metathesaurus CUIs using the USER'S OWN UTS API key, with nothing…”
• “/linking-umls-concepts”

Requirements

• Python 3
• A credential in API_KEY
• A credential in UTS_API_KEY

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Extract spans with OpenMed (Disease, Pharmaceutical, Chemical, Anatomy).
2. 2Search each span via /search/{version} for candidate CUIs.
3. 3Filter by semantic type (TUI) so a drug span resolves to a substance
4. 4Rank candidates (exact preferred-name match > synonym match) and combine
5. 5Cross-walk the chosen CUI to whatever target you actually store —
6. 6Emit the CUI plus the target code(s) and OpenMed source offsets.

What it can do on your machine

Read from SKILL.md and the folder at commit 34d7b8c. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are python).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • uts-ws.nlm.nih.gov

  Also links to:

  • nlm.nih.gov
  • uts.nlm.nih.gov
  • documentation.uts.nlm.nih.gov
  • lhncbc.nlm.nih.gov
  • github.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • API_KEY
  • UTS_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Linking Umls Concepts loads about 2k tokens when it runs. Until then it costs about 198 tokens; SKILL.md has 619 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~198

When it runs · the whole SKILL.md, loaded when a task matches

~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from maziyarpanahi/openmed at commit 34d7b8c, republished under its Apache-2.0 licence (© maziyarpanahi). 619 words, ~2,039 tokens.

name

linking-umls-concepts

description

Links entities extracted by OpenMed to UMLS Metathesaurus CUIs using the USER'S OWN UTS API key, with nothing from the Metathesaurus bundled or cached. Use when the user wants to normalize concepts across vocabularies to a single CUI, resolve synonyms via the UMLS, filter by semantic type, or cross-walk between SNOMED CT, ICD-10, RxNorm and MeSH through their shared CUI. Trigger keywords: UMLS, CUI, Metathesaurus, UTS API key, semantic type, TUI, MetaMap, QuickUMLS, concept normalization, cross-vocabulary. Pairs after OpenMed NER: consume Disease/Pharmaceutical/Chemical/Anatomy entities from openmed.analyze_text and resolve each span to a CUI out-of-process. UMLS is license-restricted — the Metathesaurus is NEVER bundled; every call uses the user's UTS account.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

terminology-coding

metadata.pairs

after

metadata.version

1.0

import os, requests

UTS = "https://uts-ws.nlm.nih.gov/rest"
API_KEY = os.environ["UTS_API_KEY"]          # USER's own key — never hardcoded
VERSION = "current"                           # or a fixed release like 2024AB

def search(term: str, sabs: str | None = None, count: int = 10) -> list[dict]:
    """Search the Metathesaurus for a term; optionally restrict source vocabs."""
    params = {"string": term, "apiKey": API_KEY, "pageSize": count}
    if sabs:                                   # e.g. "SNOMEDCT_US,RXNORM,ICD10CM"
        params["sabs"] = sabs
    r = requests.get(f"{UTS}/search/{VERSION}", params=params, timeout=15)
    r.raise_for_status()
    return r.json().get("result", {}).get("results", [])

def concept(cui: str) -> dict:
    """Pull a concept's preferred name and semantic types."""
    r = requests.get(f"{UTS}/content/{VERSION}/CUI/{cui}",
                     params={"apiKey": API_KEY}, timeout=15)
    r.raise_for_status()
    return r.json().get("result", {})

def crosswalk(cui: str, target_sab: str) -> list[dict]:
    """Atoms of a CUI in a target vocabulary (the cross-walk)."""
    r = requests.get(f"{UTS}/content/{VERSION}/CUI/{cui}/atoms",
                     params={"apiKey": API_KEY, "sabs": target_sab,
                             "pageSize": 50}, timeout=20)
    r.raise_for_status()
    return r.json().get("result", [])

hits = search("type 2 diabetes")              # -> [{ui: 'C0011860', name: ...}, ...]
sct = crosswalk("C0011860", "SNOMEDCT_US")    # CUI -> SNOMED CT codes

import openmed

note = "History of myocardial infarction; started on lisinopril."
result = openmed.analyze_text(
    note,
    model_name="disease_detection_superclinical",   # Disease category
    output_format="dict",
)

# OpenMed label -> acceptable UMLS semantic-type groups (TUI prefixes)
KEEP_STY = {
    "DISEASE":  {"Disease or Syndrome", "Sign or Symptom", "Neoplastic Process"},
    "DRUG":     {"Pharmacologic Substance", "Clinical Drug"},
    "CHEM":     {"Pharmacologic Substance", "Organic Chemical"},
}

for ent in result["entities"]:
    for hit in search(ent["text"], count=5):
        cui = hit["ui"]
        stys = {s["name"] for s in concept(cui).get("semanticTypes", [])}
        if not KEEP_STY.get(ent["label"]) or stys & KEEP_STY[ent["label"]]:
            print(ent["text"], ent["start"], ent["end"], "->", cui, hit["name"])
            break

© maziyarpanahi, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/linking-umls-concepts of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c