General analytics
AuraScore 77/100

Post-Market Drug Safety Signal Disproportionality Report

Evaluate pharmacovigilance adverse event data to detect statistical disproportionate reporting trends.

Use this template when assessing adverse drug reaction reports and post-market safety signals. It guides safety data scientists in delivering a clean disproportionality briefing for pharmacovigilance safety boards.

Template

Role: Lead Pharmacovigilance Data Scientist and Drug Safety Epidemiologist with expertise in post-market surveillance analytics.

Context

  • Investigated Medicinal Product: {{product_name}}
  • Indication Population: {{indication_cohort}}
  • Surveillance Period: {{surveillance_window}}
  • Spontaneous AE Dataset: {{adverse_event_extract}}
  • Disproportionality Calculations: {{disproportionality_scores}}
  • Applicable Framework: {{regulatory_jurisdiction}}

Task

Generate a Pharmacovigilance Signal Detection & Disproportionality Report that assesses spontaneous adverse event reports, evaluates statistical signal thresholds, and categorizes safety concerns for Safety Review Committee evaluation.

Method

  1. Quantify total case volumes and unique spontaneous safety reports from {{adverse_event_extract}} across {{surveillance_window}}.
  2. Review the disproportionality metrics in {{disproportionality_scores}} (e.g., PRR >= 2.0, chi-square >= 4.0, or lower bound IC > 0).
  3. Map identified adverse event signals to their designated MedDRA System Organ Classes (SOC).
  4. Stratify flagged signals by severity, labeling status (labeled vs. unlabeled events), and time-to-onset patterns.
  5. Assess potential confounding factors such as co-medications, baseline comorbidities in {{indication_cohort}}, or reporting channel spikes.
  6. Determine whether each candidate signal warrants routine surveillance, updated product labeling, or an expedited safety review under {{regulatory_jurisdiction}}.

Constraints

  • MUST clearly separate confirmed statistical signals from background noise using provided metrics in {{disproportionality_scores}}.
  • MUST NOT declare definitive medical causation; state findings in terms of statistical association and disproportionality.
  • Maintain terminology consistent with MedDRA and {{regulatory_jurisdiction}} safety guidance.
  • Keep report concise and structured under 750 words.

Output format

Format the report using the following markdown hierarchy:

Safety Signal Assessment Report: {{product_name}}

Surveillance Summary

  • 3 summary points detailing reporting volume, surveillance window, and primary safety themes.

Signal Disproportionality Table

  • Markdown table including Preferred Term (PT), System Organ Class (SOC), Observed Cases, Statistical Score (PRR/IC), and Signal Status (New Signal / Under Monitoring / Non-Significant).

Epidemiological & Clinical Discussion

  • 2-3 focused paragraphs reviewing biological plausibility and confounding risk in {{indication_cohort}}.

Pharmacovigilance Action Plan

  • Bulleted recommendations outlining regulatory reporting requirements and targeted medical review steps.

Self-review

  1. Ensure all MedDRA terms and statistical measures from {{adverse_event_extract}} and {{disproportionality_scores}} match faithfully.
  2. Verify that language adheres to statistical association without asserting unverified causal liability.
  3. Check that regulatory action steps reflect the specified {{regulatory_jurisdiction}} standards.
AuraScore breakdown
77/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering8/12 · Adequate

Hard boundaries — what the model must and must not do.

Output specification6/14 · Thin

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

data-analytics
data-general
healthcare-life-sciences
pharmacovigilance
drug safety
safety signals