Name: mimic
Author: mkurman

About

Imported from mkurman/zorai (skills/scientific-skills/mimic/SKILL.md). Install upstream with npx skills add mkurman/zorai --skill mimic. Copyright stays with the author.

Overview

MIMIC (Medical Information Mart for Intensive Care) provides ICU data: vitals, labs, medications, notes, diagnoses. Tools for querying MIMIC-III/IV, building ML features, and reproducing clinical benchmarks.

Access

Apply for access at https://physionet.org/content/mimiciv/ -- requires CITI data use training.

Installation

uv pip install psycopg2 pandas

Python Analysis

import pandas as pd
from sqlalchemy import create_engine

engine = create_engine("postgresql://user:pass@localhost:5432/mimiciv")

# First 24h vitals
query = """
SELECT subject_id, charttime, valuenum
FROM mimiciv_icu.chartevents
WHERE itemid = 220045
AND valuenum IS NOT NULL
LIMIT 100
"""
hr = pd.read_sql(query, engine)

Workflow

Apply for MIMIC access (physionet.org)
Load MIMIC-IV into PostgreSQL
Query ICU stays, diagnoses, labs, medications, notes
Extract features (vitals over time, labs at admission, comorbidity scores)
Build ML benchmarks (in-hospital mortality, LOS prediction, sepsis detection)

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

yaml

targets:
  - https://api.opensmartroute.ai/api/v1/registry/mkurman-zorai-mimic/manifest   # or paste the manifest below

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

mkurman-zorai-mimic.ocm.jsonjson

{
  "ocm": "1",
  "id": "mkurman-zorai-mimic",
  "kind": "skill",
  "name": "mimic",
  "description": "MIMIC (Medical Information Mart for Intensive Care) database toolkit. Curated ICU data: vitals, labs, medications, notes, diagnoses. Tools for querying MIMIC-III/IV, building ML features, and reproducing benchmarks.",
  "publisher": "mkurman",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "mimic",
      "icu",
      "ehr",
      "clinical-database",
      "research",
      "healthcare",
      "zorai",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "MIMIC (Medical Information Mart for Intensive Care) database toolkit. Curated ICU data: vitals, labs, medications, notes, diagnoses. Tools for querying MIMIC-III/IV, building ML features, and reproducing benchmarks."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/mkurman/zorai",
      "path": "skills/scientific-skills/mimic/SKILL.md",
      "ref": "5b6c05fb8b695e7b0ff23bb839fca8f2a933ab82",
      "url": "https://github.com/mkurman/zorai/blob/5b6c05fb8b695e7b0ff23bb839fca8f2a933ab82/skills/scientific-skills/mimic/SKILL.md",
      "key": "mkurman/zorai/skills/scientific-skills/mimic/SKILL.md"
    }
  },
  "instructions": "## Overview\n\nMIMIC (Medical Information Mart for Intensive Care) provides ICU data: vitals, labs, medications, notes, diagnoses. Tools for querying MIMIC-III/IV, building ML features, and reproducing clinical benchmarks.\n\n## Access\n\nApply for access at https://physionet.org/content/mimiciv/ -- requires CITI data use training.\n\n## Installation\n\n```bash\nuv pip install psycopg2 pandas\n```\n\n## Python Analysis\n\n```python\nimport pandas as pd\nfrom sqlalchemy import create_engine\n\nengine = create_engine(\"postgresql://user:pass@localhost:5432/mimiciv\")\n\n# First 24h vitals\nquery = \"\"\"\nSELECT subject_id,",
  "cost": {
    "context_tokens": 262
  }
}

Fetch it by URL: GET /api/v1/registry/mkurman-zorai-mimic/manifest?version=1.0.0

Reviews

Star ratings from people who tried it. One review per account; edit yours any time.

No reviews yet. Install it, try it, and be the first to rate it.