Extracting SDOH and Z-Codes

What it does

When your agent uses it

• Turning social risks documented in clinical notes into structured, coded data
• Building health-equity dashboards that need SDOH as discrete fields
• Finding SDOH that is written in the chart but was never given a Z-code

Example prompts

• “Extract SDOH from these de-identified discharge notes and suggest Z-codes with source spans.”
• “List every note in ./notes that mentions housing instability so a coder can check for missing Z-codes.”
• “Find transportation barriers in the dialysis clinic notes and map them to Z-codes.”

Requirements

• The OpenMed Python package
• Clinical notes that have been de-identified first

Workflow steps

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

1. 1De-identify the note with openmed.deidentify (HIPAA Safe Harbor or a
2. 2Extract entities with openmed.analyze_text. Pick a model whose label
3. 3Map spans to Z-codes using a curated lookup keyed by label
4. 4Stage for confirmation. Emit (span, label, suggested_code, confidence)
5. 5Normalize to value sets. Align labels to the Gravity Project SDOH

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:

  • hl7.org

  Also links to:

  • cdc.gov
  • confluence.hl7.org
  • n2c2.dbmi.hms.harvard.edu
  • cms.gov
  • healthit.gov

  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

Extracting SDOH and Z-Codes loads about 1.9k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 165 tokens; SKILL.md has 725 words of instructions outside code blocks.

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

~165

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

~1.9k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.9k

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). 725 words, ~1,860 tokens.

name

extracting-sdoh

description

Extracts social determinants of health (SDOH) — housing instability, food insecurity, unemployment, transportation barriers, social isolation, financial strain — from clinical narrative and maps the spans to ICD-10-CM Z-codes (Z55–Z65). Use after running OpenMed NER when the user wants SDOH surfacing, Z-code suggestion, health-equity analytics, or to recover SDOH that is documented in free text but not coded. Pairs with OpenMed analyze_text output. Standards: ICD-10-CM Z55–Z65, Gravity Project value sets, n2c2 2022 SDOH track. Trigger keywords: SDOH, social determinants, Z-codes, housing, food insecurity, health equity, Gravity Project.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

clinical-nlp

metadata.pairs

after

metadata.version

1.0

import openmed
from sdoh_zcode_map import SDOH_ZCODES  # see references/sdoh_zcode_map.md

note = (
    "62F with CHF. Reports she lost her apartment last month and is "
    "staying in a shelter. Often runs out of food before month-end. "
    "No car; misses appointments because the bus does not run to clinic."
)

# 1) Strip PHI before any downstream processing or storage.
deid = openmed.deidentify(note, method="replace", policy="hipaa_safe_harbor")

# 2) Run clinical NER. Use an SDOH/clinical model from the registry; discover
#    available keys with openmed.get_models_by_category(...).
result = openmed.analyze_text(deid.text, output_format="dict")

# 3) Map each entity span to a candidate Z-code.
for ent in result["entities"]:
    code = SDOH_ZCODES.get(ent["label"].lower())
    if code:
        print(f"{ent['text']!r:40}  {ent['label']:18}  -> {code}")

© 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

SKILL.md and 1 other file (references) in skills/extracting-sdoh of maziyarpanahi/openmed.

• SKILL.md
• references/sdoh_zcode_map.md

Open the folder on GitHubat commit 34d7b8c