tooluniverse-adverse-event-detection
Detect and analyze adverse drug event signals using FDA FAERS data, drug labels, disproportionality analysis (PRR, ROR, IC), and biomedical evidence. Generates quantitative safety signal scores (0-100) with evidence grading. Use for post-market surveillance, pharmacovigilance, drug safety assessment, adverse event investigation, and regulatory decision support.
npx skills add FreedomIntelligence/OpenClaw-Medical-Skills --skill tooluniverse-adverse-event-detection --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Automated pipeline for detecting, quantifying, and contextualizing adverse drug event signals using FAERS disproportionality analysis, FDA label mining, mechanism-based prediction, and literature evidence. Produces a quantitative Safety Signal Score (0-100) for regulatory and clinical decision-making.
How it works
- Phase 0: Input Parsing & Drug Disambiguation
- Resolve drug identity via OpenTargets to obtain CHEMBL ID, mechanism, black box status, DrugBank safety/toxicity data, DrugBank targets, and approved indications.
- Output includes fields such as Generic Name, ChEMBL ID, DrugBank ID, Drug Class, Mechanism, Primary Target, Black Box Warning, Withdrawn.
- Phase 1: FAERS Adverse Event Profiling
- Query FAERS for adverse events, seriousness, outcomes, age distribution, death-related events, and reporter countries for the specified drug.
- Produce a top adverse events list and demographic distributions.
- Phase 2: Disproportionality Analysis (Signal Detection)
- For each significant adverse event, compute PRR, ROR, and IC with 95% CI.
- Determine signal detection using criteria for PRR, ROR, and IC.
- Classify signal strength as Strong, Moderate, Weak, or No signal based on thresholds.
- Stratify key signals by demographics (sex, age, country) when applicable.
- Phase 3: FDA Label Safety Information
- Retrieve boxed warnings, contraindications, warnings and precautions, adverse reactions, drug interactions, and pregnancy/geriatrics/pediatrics/pharmacogenomics info from label tools.
- Note: If a section is not found, the tool returns NOT_FOUND, which is normal for many drugs.
- Phase 4: Contextual and Comparative Analysis (implied by workflow)
- Phase 4 includes mechanism-based adverse event context, OpenTargets safety context, and potential drug class comparisons, as described in the workflow overview.
- Phase 5: Report Synthesis & Recommendations
- Compile a structured report with monitoring recommendations, risk mitigation strategies, and a completeness checklist, aligned with the Safety Signal Score and evidence grading.
When to use it
Use to answer questions about safety signals for a specific drug, to detect adverse events, to compare safety across drugs, and for post-market surveillance and regulatory support. It emphasizes signal quantification with disproportionality metrics and a comparative safety angle across drug classes.
What it can touch
Utilizes tools for OpenTargets drug data, DrugBank data, and FAERS data, plus FDA label extraction tools. Commands and tool names are invoked as shown in the workflow (e.g., OpenTargets_get_drug_chembId_by_generic_name, FAERS_count_reactions_by_drug_event, FDA_get_boxed_warning_info_by_drug_name, etc.).
Caveats
Label sections may return NOT_FOUND if absent for a drug; this is normal. The workflow relies on multiple data sources and statistical criteria; outcomes depend on data availability and tool responses.
# Adverse Drug Event Signal Detection & Analysis Automated pipeline for detecting, quantifying, and contextualizing adverse drug event signals using FAERS disproportionality analysis, FDA label mining, mechanism-based prediction, and literature evidence. Produces a quantitative Safety Signal Score (0-100) for regulatory and clinical decision-making. **KEY PRINCIPLES**: 1. **Signal quantification first** - Every adverse event must have PRR/ROR/IC with confidence intervals 2. **Serious events priority** - Deaths, hospitalizations, life-threatening events always analyzed first 3. **Multi-source triangulation** - FAERS + FDA labels + OpenTargets + DrugBank + literature 4. **Context-aware assessment** - Distinguish drug-specific vs class-wide vs confounding signals 5. **Report-first approach** - Create report file FIRST, update progressively 6. **Evidence grading mandatory** - T1 (regulatory/boxed warning) through T4 (computational) 7. **English-first queries** - Always use English drug names in tool calls, respond in user's language --- ## When to Use Apply when user asks: - "What are the safety signals for [drug]?" - "Detect adverse events for [drug]" - "Is [drug] associated with [adv
- When to Use
- Workflow Overview
- Phase 0: Input Parsing & Drug Disambiguation
- 0.1 Resolve Drug Identity
- 0.2 Output for Report
- Phase 1: FAERS Adverse Event Profiling
- 1.1 Query FAERS for Adverse Events
- 1.2 Get Serious Events Breakdown
- 1.3 MedDRA Hierarchy Rollup
- 1.4 Output for Report
- Phase 2: Disproportionality Analysis (Signal Detection)
- 2.1 Calculate Signal Metrics
- 2.2 Signal Detection Criteria
- 2.3 Signal Strength Classification
What does the tooluniverse-adverse-event-detection skill do?
Detect and analyze adverse drug event signals using FDA FAERS data, drug labels, disproportionality analysis (PRR, ROR, IC), and biomedical evidence. Generates quantitative safety signal scores (0-100) with evidence grading. Use for post-market surveillance, pharmacovigilance, drug safety assessment, adverse event investigation, and regulatory decision support.
How do I install it?
Run `npx skills add FreedomIntelligence/OpenClaw-Medical-Skills --skill tooluniverse-adverse-event-detection --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From FreedomIntelligence/OpenClaw-Medical-Skills, a repository with 2,909 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.