Reporting Adverse Events

What it does

When your agent uses it

• The user needs to build an individual case safety report (ICSR)
• Populate a FAERS submission
• Map a narrative to E2B(R
• Classify seriousness (death

Example prompts

• “Use the reporting-adverse-events skill to structure adverse-event mentions that OpenMed extracts into FAERS / ICH E2B(R3) reportable fields —…”
• “/reporting-adverse-events”

Requirements

• Python 3

Workflow steps

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

1. 1De-identify first. Run openmed.deidentify(narrative, policy=...) and
2. 2Extract drugs and reactions with the two analyze_text calls above.
3. 3Characterize each drug as suspect (1), concomitant (2), or
4. 4Code reactions to MedDRA. Map each verbatim reaction term to a MedDRA
5. 5Determine seriousness. Scan the narrative for the six criteria; set
6. 6Assign reaction outcome from the value set above.
7. 7Hand the structured draft to a qualified safety reviewer for causality

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

  Links to these hosts (documentation or services it may open):

  • fda.gov
  • ich.org
  • meddra.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

Reporting Adverse Events loads about 2.2k tokens when it runs. Until then it costs about 213 tokens; SKILL.md has 757 words of instructions outside code blocks.

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

~213

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

~2.2k

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). 757 words, ~2,219 tokens.

name

reporting-adverse-events

description

Structures adverse-event mentions that OpenMed extracts into FAERS / ICH E2B(R3) reportable fields — suspect drug, reaction (MedDRA PT), seriousness criteria, and outcome. Use when the user needs to build an individual case safety report (ICSR), populate a FAERS submission, map a narrative to E2B(R3) data elements, classify seriousness (death, life-threatening, hospitalization, disability, congenital anomaly), or assign reaction outcomes. Trigger keywords: adverse event, ADR, ICSR, FAERS, E2B, E2B(R3), suspect drug, seriousness, MedDRA, reaction outcome, pharmacovigilance case. Pairs after OpenMed NER: consume Pharmaceutical/Chemical and Disease entities from openmed.analyze_text. MedDRA is licensed and user-supplied — never bundled. De-identify the narrative with openmed.deidentify before any external submission.

license

Apache-2.0

metadata.project

OpenMed

metadata.category

safety-pharmacovigilance

metadata.pairs

after

metadata.version

1.0

import openmed

narrative = (
    "68-year-old patient on warfarin 5 mg daily developed a gastrointestinal "
    "hemorrhage and was hospitalized. Warfarin was discontinued; the patient "
    "recovered."
)

# 1) Extract drug spans (Pharmaceutical category) on-device.
drugs = openmed.analyze_text(
    narrative,
    model_name="pharma_detection_superclinical",
    output_format="dict",
)["entities"]

# 2) Extract condition / reaction spans (Disease category).
conditions = openmed.analyze_text(
    narrative,
    model_name="disease_detection_superclinical",
    output_format="dict",
)["entities"]

# 3) Assemble an E2B(R3)-shaped ICSR skeleton (reaction PTs filled later via MedDRA).
icsr = {
    "patient": {"age": None, "sex": None},          # from de-identified demographics
    "drugs": [
        {
            "name": e["text"],
            "drugcharacterization": 1,              # 1=suspect 2=concomitant 3=interacting
            "action": None,                          # e.g. drug withdrawn / dose reduced
        }
        for e in drugs
    ],
    "reactions": [
        {
            "verbatim": e["text"],                   # narrative term, pre-MedDRA
            "meddra_pt": None,                       # coded with user's MedDRA dict
            "outcome": None,                         # E2B reaction outcome code
        }
        for e in conditions
    ],
    "seriousness": {
        "serious": None, "death": False, "lifeThreatening": False,
        "hospitalization": True, "disability": False, "congenitalAnomaly": False,
        "otherMedicallyImportant": False,
    },
}

© 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/reporting-adverse-events of maziyarpanahi/openmed.

Open the folder on GitHubat commit 34d7b8c