Synthesis
AuraScore 81/100

Post-Market Pharmacovigilance Signal Synthesis Specification

Synthesizes multi-registry adverse event reports and real-world exposure data into an actionable pharmacovigilance safety evaluation specification.

Use this template when investigating potential drug safety signals from post-market spontaneous reporting and observational registries. It yields a standardized evaluation and signal management specification for safety review committees.

Template

Role: Global Pharmacovigilance Director and Medical Safety Officer

Context

  • Investigational / Marketed Drug: {{drug_product_name}}
  • Potential Safety Signals Under Review: {{signal_adverse_events}}
  • Safety Databases & Spontaneous Registries: {{surveillance_databases}}
  • Primary Regulatory Jurisdictions: {{reporting_jurisdictions}}
  • Relevant Patient Exposure Window: {{exposure_window}}
  • Risk Minimization & Mitigation Objective: {{risk_mitigation_target}}

Task

Synthesize disproportionality metrics, mechanistic pharmacology, and longitudinal health records across {{surveillance_databases}} into a rigorous Pharmacovigilance Signal Synthesis Specification to evaluate safety impact and support regulatory reporting.

Method

  1. Aggregate raw case counts and calculate disproportionality scores (e.g., PRR, ROR, EBGM) for {{signal_adverse_events}} from {{surveillance_databases}}.
  2. Stratify reported adverse incidents across patient demographics, co-medications, and {{exposure_window}} duration.
  3. Evaluate biological plausibility by mapping receptor affinities, off-target binding, and class-effect mechanisms for {{drug_product_name}}.
  4. Filter confounders including indication bias, stimulated reporting artifacts, and underlying comorbidity progression.
  5. Benchmark observed-to-expected incidence rates against baseline population epidemiology in {{reporting_jurisdictions}}.
  6. Formulate clear signal verification or refutation thresholds for each monitored adverse event.
  7. Detail specific risk minimization interventions, label update specifications, or targeted REMS protocols to fulfill {{risk_mitigation_target}}.

Constraints

  • MUST compute and display disproportionality signal metrics alongside 95% confidence intervals.
  • MUST NOT categorize a safety signal as refuted without documented confounder analysis and background incidence benchmarking.
  • All signal validation criteria must align with GVP (Good Pharmacovigilance Practices) and FDA post-market surveillance guidelines.
  • Timelines and reporting triggers must explicitly reflect statutory requirements across {{reporting_jurisdictions}}.

Output format

Synthesize the results into the following exact technical sections:

  1. Signal Characterization & Metrics Table (columns: Adverse Event, PRR/ROR Score, 95% CI, Case Count, Fatal Outcomes)
  2. Causality Assessment & Biological Plausibility Synthesis (concise narrative analysis, max 300 words)
  3. Confounder & Bias Stratification (bulleted risk factor evaluation)
  4. Regulatory Impact Matrix (table mapping impact across each region in {{reporting_jurisdictions}})
  5. Risk Minimization Specification & Action Plan (concrete numbered mandates aligned with {{risk_mitigation_target}})

Self-review

  • Did I analyze every specified event listed in {{signal_adverse_events}}?
  • Are regulatory notification triggers aligned with the specific laws of {{reporting_jurisdictions}}?
  • Does the action plan provide measurable steps toward achieving {{risk_mitigation_target}}?
AuraScore breakdown
81/100Provisional
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 engineering12/12 · Strong

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.

research-analysis
research-synthesis
healthcare-life-sciences
pharmacovigilance
regulatory-affairs
drug-safety