Tooluniverse Adverse Event Detection

What it does

This skill, Tooluniverse Adverse Event Detection, automatically identifies and analyzes potential adverse drug events from clinical data. It leverages a pipeline incorporating FAERS disproportionality analysis, FDA label mining, mechanism-based prediction, and literature evidence to generate a quantitative Safety Signal Score (0-100). The goal is to improve patient safety monitoring and enable rapid response identification by quantifying signals for regulatory and clinical decision-making.

When to use it

• When investigating reports of unexpected adverse events associated with a drug.
• To prioritize serious adverse events like deaths or hospitalizations for immediate analysis.
• For assessing the potential risk of a new drug based on available data sources.
• To determine if an observed adverse event is specific to a drug, common across a class, or potentially due to confounding factors.

Key capabilities

• Adverse Event Signal Detection: Identifies adverse events reported more than expected using statistical thresholds (PRR >= 2.0, N >= 3, lower CI > 1.0).
• Quantitative Scoring: Generates a Safety Signal Score (0-100) to quantify the severity and likelihood of an adverse event.
• Multi-Source Data Integration: Combines data from FAERS, FDA labels, OpenTargets, DrugBank, and literature sources.
• Mechanism of Action Analysis: Uses tools like OpenTargets_get_drug_mechanisms_of_action_by_chemblId and drugbank_get_targets_by_drug_name_or_drugbank_id to assess biological plausibility.
• Evidence Grading: Assigns evidence grades (T1-T4) to support findings.

Example prompts

• "Analyze the adverse event 'myocardial infarction' associated with drug X."
• "What is the Safety Signal Score for 'liver failure' and drug Y?"
• "Is the adverse event 'rash' biologically plausible given the mechanism of action of drug Z?"

Tips & gotchas

• Always use English drug names when interacting with ToolUniverse tools.
• The skill prioritizes serious adverse events (deaths, hospitalizations) for analysis.
• Results are based on statistical thresholds and data from specific sources; consider these limitations when interpreting findings.