# Parsing Lab Values

Parse laboratory values and reference ranges from clinical text and flag results as...

- Repository: https://github.com/maziyarpanahi/openmed (5755 stars)
- Category: Engineering
- License: Apache-2.0
- Last updated: 2026-10-31
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add maziyarpanahi/openmed --skill parsing-lab-values -g -a claude-code -y`
Codex: `npx skills add maziyarpanahi/openmed --skill parsing-lab-values -g -a codex -y`
Cursor: `npx skills add maziyarpanahi/openmed --skill parsing-lab-values -g -a cursor -y`
Gemini CLI: `npx skills add maziyarpanahi/openmed --skill parsing-lab-values -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add maziyarpanahi/openmed`

## Description

Parse laboratory values and reference ranges from clinical text and flag results as low, normal, high, or critical with OpenMed. Use when the user needs to interpret lab results, compute abnormal flags, parse reference ranges like \"135-145\" or \"<5\", honor an originating-lab flag (H/L/critical), or turn extracted lab entities into structured high/low/critical signals. Covers openmed.clinical.parse_reference_range, derive_abnormal_flag, ReferenceRange, and AbnormalFlag, with UCUM/LOINC framing. Unit-agnostic, it does not convert units. Pairs after extracting-clinical-entities (lab entities from analyze_text).

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Parsing lab values

Lab results in clinical text arrive as a value, a unit, and a reference range
("Sodium 132 mmol/L (135, 145)"). To act on them you need a structured
**abnormal flag**, is 132 low, normal, high, or critical? OpenMed's
`openmed.clinical` lab helpers parse the reference range deterministically and
derive the flag, honoring any explicit flag the originating lab already supplied.
The helpers are **unit-agnostic by design**: they compare numbers within a stated
range and never convert units, so a mmol/L value is never silently compared
against a mg/dL range.

## When to use

- After `extracting-clinical-entities` surfaces lab/measurement entities and you
  need to classify each as low / normal / high / critical.
- The user asks to parse reference ranges, flag abnormal labs, build a flagged
  labs table, or interpret values like `<5`, `>=10`, `0.5 - 1.2`.
- You have an originating-lab flag (`H`, `L`, `C`, `HH`) and want it honored over
  a derived comparison.

## Quick start

```python
from openmed.clinical import (
    parse_reference_range, derive_abnormal_flag, LAB_FLAG_ADVISORY,
)

# Closed range
rng = parse_reference_range("135-145")
# -> {"low": 135.0, "high": 145.0, "low_inclusive": True, "high_inclusive": True}

derive_abnormal_flag(132, rng)            # "low"
derive_abnormal_flag(140, "135-145")      # "normal"  (raw range string accepted)
derive_abnormal_flag(150, "135 to 145")   # "high"

# One-sided bounds
derive_abnormal_flag(7, parse_reference_range("<5"))    # "high" (above the cap)
derive_abnormal_flag(3, parse_reference_range(">=10"))  # "low"

# Honor the lab's own explicit flag (takes precedence over derived comparison)
derive_abnormal_flag(132, "135-145", explicit_flag="C")   # "critical"
derive_abnormal_flag(132, "135-145", explicit_flag="HH")  # "critical"

The rest: https://github.com/maziyarpanahi/openmed/blob/HEAD/skills/parsing-lab-values/SKILL.md