Segmenting Clinical Sections

What it does

When your agent uses it

• The user has a free-text note
• Discharge summary and wants section-aware processing
• Header detection
• Mapping headers to LOINC document-section codes

Example prompts

• “/segmenting-clinical-sections”

Requirements

• Python 3

Workflow steps

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

1. 1Detect section headers. Use header heuristics: a line that is a known
2. 2Normalize to canonical labels and LOINC codes. Map each detected header to
3. 3Chunk the note into (section, loinc, body) spans between consecutive
4. 4Process per section. Run analyze_text / deidentify on each chunk and
5. 5Reassemble with provenance. Tag each downstream entity with its source

What it can do on your machine

Read from SKILL.md and the folder at commit 9dca507. 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

  Links to these hosts (documentation or services it may open):

  • loinc.org
  • ncbi.nlm.nih.gov
  • hl7.org

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

• Credentials

  Names no API keys, tokens, secrets or passwords.

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

Context cost

Segmenting Clinical Sections loads about 1.8k tokens when it runs. Until then it costs about 187 tokens; SKILL.md has 602 words of instructions outside code blocks.

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

~187

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

~1.8k

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 9dca507, republished under its Apache-2.0 licence (© maziyarpanahi). 602 words, ~1,761 tokens.

name

segmenting-clinical-sections

description

Split a clinical note into canonical sections (Chief Complaint, HPI, PMH, Medications, Allergies, Assessment & Plan, etc.) before running OpenMed NER or de-identification, so section context sharpens downstream precision. Use when the user has a free-text note or discharge summary and wants section-aware processing, header detection, mapping headers to LOINC document-section codes, or per-section NER/de-id. Covers heuristic header detection, normalization to canonical section labels, LOINC/SecTag framing, and why a finding in PMH is historical while the same finding in A&P is active. Hand-off: feed each sectioned chunk into openmed.analyze_text / openmed.deidentify. Pairs before extracting-clinical-entities.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

clinical-nlp

metadata.pairs

before

metadata.version

1.0

import re
import openmed

# Synthetic note.
note = """CHIEF COMPLAINT: chest pain.
HPI: 54M with 2 hours of substernal pressure.
PAST MEDICAL HISTORY: type 2 diabetes, prior MI 2019.
MEDICATIONS: metformin 500 mg BID.
ALLERGIES: penicillin (rash).
ASSESSMENT AND PLAN: acute coronary syndrome; start aspirin, admit."""

# Map common header variants -> canonical section + LOINC document-section code.
SECTION_MAP = {
    "chief complaint": ("Chief Complaint", "10154-3"),
    "hpi": ("History of Present Illness", "10164-2"),
    "history of present illness": ("History of Present Illness", "10164-2"),
    "past medical history": ("Past Medical History", "11348-0"),
    "medications": ("Medications", "10160-0"),
    "allergies": ("Allergies", "48765-2"),
    "assessment and plan": ("Assessment and Plan", "51847-2"),
}

HEADER_RE = re.compile(r"^(?P<h>[A-Z][A-Za-z /&]+):", re.MULTILINE)

# Split note into (canonical_label, loinc, body) chunks at each header.
chunks, matches = [], list(HEADER_RE.finditer(note))
for i, m in enumerate(matches):
    raw = m.group("h").strip().lower()
    label, loinc = SECTION_MAP.get(raw, (m.group("h").strip(), None))
    body_start = m.end()
    body_end = matches[i + 1].start() if i + 1 < len(matches) else len(note)
    chunks.append({"section": label, "loinc": loinc,
                   "text": note[body_start:body_end].strip()})

# Run NER per section — pass the section label downstream as context.
for c in chunks:
    ents = openmed.analyze_text(c["text"], model_name="disease_detection_superclinical",
                                output_format="dict")
    c["entities"] = ents

© 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/segmenting-clinical-sections of maziyarpanahi/openmed.

Open the folder on GitHubat commit 9dca507