CADEC Query Skill
SkillDev toolsQuery the CADEC (CSIRO Adverse Drug Event Corpus). Use whenever the user asks about adverse drug event mentions in consumer health text, entity annotations from patient forum posts, MedDRA/SNOMED-CT normalised ADR spans, or wants to look up drugs, symptoms, or coded entities in the CADEC corpus.
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.
Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
Then ask your AI: use the CADEC Query Skill skill
What this skill tells your AI
The instructions your AI receives, as published by qsong-github/drugclaw in skills/drug_nlp/cadec/SKILL.md and read by ahel’s review.
Search CADEC annotated patient forum posts by any entity. Auto-detects type:
| Input Pattern | Detected As | Match Logic |
|---|---|---|
10019211 (8 digits) | MedDRA code | exact on normalizations.code |
22253000 (6-18 digits) | SNOMED CT code | exact on normalizations.code |
| anything else | free text | substring on entity text, type, or doc_id |
API
| Function | Input | Returns |
|---|---|---|
load_cadec(path) | JSON path | list[dict] (cached) |
search(entity) | single entity string | list[dict] |
search_batch(entities) | list of entity strings | dict[str, list[dict]] |
summarize(hits, entity) | hits + label | compact text |
to_json(hits) | list[dict] | same list (JSON-ready) |
Entity Types in Corpus
| Type | Description |
|---|---|
| ADR | Adverse Drug Reaction |
| Drug | Medication mention |
| Disease | Pre-existing condition |
| Symptom | Patient-reported symptom |
| Finding | Clinical finding |
Usage
See if __name__ == "__main__" block in 34_CADEC.py for runnable examples:
drug name search, ADR text search, MedDRA code lookup, batch search, JSON output.
Data
- Source: CADEC v2, CSIRO (AskaPatient.com forum posts)
- Local file:
cadec_combined.jsonbuilt from BRAT.txt+.annfiles - Annotations: Original spans + MedDRA + SNOMED CT normalisations
- Stats: ~1,250 documents, ~7,600 entity annotations
- Path:
DATA_PATHvariable in34_CADEC.py - Citation: Karimi et al., 2015. J Biomed Inform 55:73–81
Signals
- GitHub stars
- 116
- Forks
- 3
- Last commit
- Aug 2026
Advanced
- Item type
- skill
- Key
cadec-query- Source
- github.com/qsong-github/drugclaw
github.com/qsong-github/drugclaw