Extracting Lab Tables

What it does

When your agent uses it

• The user has a CBC
• Other lab report as a scanned image / PDF / spreadsheet and needs the test name
• Reference range
• Abnormal flag as clean rows

Example prompts

• “Use the extracting-lab-tables skill to detect and extracts tabular laboratory panels from PDFs, scans, and images into structured rows ready for…”
• “/extracting-lab-tables”

Requirements

• Python 3

Workflow steps

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

1. 1Detect the source type. CSV/TSV → read_table. Image/scan → ocr().
2. 2OCR with positions. ocr() returns OcrWords carrying bbox and page.
3. 3Reconstruct the grid. Cluster words by their bbox y into rows, by x
4. 4Identify the lab columns. Map headers to roles: test name, value,
5. 5De-identify embedded PHI. Patient name/MRN often sit in the table header or
6. 6Emit structured rows {test, value, unit, ref_range, flag} per result and

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

  Shell commands in SKILL.md call:

  • pip

  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):

  • hl7.org
  • github.com
  • loinc.org
  • ucum.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

Extracting Lab Tables loads about 2.1k tokens when it runs. Until then it costs about 220 tokens; SKILL.md has 803 words of instructions outside code blocks.

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

~220

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

~2.1k

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). 803 words, ~2,099 tokens.

name

extracting-lab-tables

description

Detects and extracts tabular laboratory panels from PDFs, scans, and images into structured rows ready for OpenMed and FHIR. Use when the user has a CBC, CMP, lipid panel, or other lab report as a scanned image / PDF / spreadsheet and needs the test name, value, unit, reference range, and abnormal flag as clean rows. Trigger keywords: lab table extraction, lab panel, OCR labs, table detection, layout analysis, header detection, reference range column, abnormal flag column, LOINC, UCUM, CBC, CMP, structured labs. Pairs before OpenMed: OCR/parse the table on-device (openmed.multimodal.ocr.ocr, read_table), de-identify embedded PHI with openmed.deidentify, then hand structured rows to LOINC/UCUM mapping and openmed.clinical lab flagging. Image/CSV/TSV intake is supported; PDF/DOCX raise UnsupportedDocumentError — render those to images or text first.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

imaging-ocr

metadata.pairs

before

metadata.version

1.0

from openmed.multimodal.ocr import ocr
from openmed.multimodal import read_table, classify_columns, redact_table

# A) Scanned / image lab report -> words with pixel boxes.
result = ocr("cbc_report.png")               # OcrResult
for w in result.words[:5]:
    print(repr(w.text), w.bbox, round(w.confidence, 2), "p", w.page)

doc = result.to_document()                   # ExtractedDocument; bbox preserved

# B) Delimited lab export (CSV/TSV) -> classified, PHI-redacted rows.
csv_text = (
    "PatientName,Test,Value,Unit,RefRange,Flag\n"
    "Jane Roe,Hemoglobin,9.1,g/dL,12.0-15.5,L\n"
    "Jane Roe,Glucose,148,mg/dL,70-99,H\n"
)
view = read_table(csv_text)                  # TableView
view = classify_columns(view)                # tag PHI vs data columns
redacted = redact_table(view)                # RedactedTable: PatientName redacted

for row in redacted.rows:
    print(row)                               # name column masked; lab data intact
for col in redacted.manifest:                # PHI-safe per-column audit manifest
    print(col["column_name"], col["assigned_class"], col["action"])

© 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/extracting-lab-tables of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c