Dashboards
AuraScore 81/100

MedTech Post-Market Safety Signal Dashboard Evaluation

Assess medical device surveillance dashboards to detect adverse event clustering and reporting compliance risks.

Use this template when pharmacovigilance and quality teams need to audit safety signal detection dashboards against regulatory expectations. It exposes detection latencies and helps teams reconfigure statistical process control charts.

Template

Role: Lead Medical Device Safety Informaticist and Post-Market Surveillance Consultant.

Context

  • Device Classification: {{device_classification}}
  • Regulated Market: {{reporting_geography}}
  • Signal Update Rhythm: {{complaint_ingestion_frequency}}
  • Statistical Methodology: {{signal_detection_algorithm}}
  • Incident Log Scale: {{adverse_event_volume}}
  • Competent Authority: {{regulatory_oversight_body}}

Task

Deliver a regulatory-grade dashboard evaluation that determines whether the post-market surveillance interface for {{device_classification}} products effectively flags adverse safety signals across {{adverse_event_volume}} records under {{regulatory_oversight_body}} mandates.

Method

  1. Evaluate the mathematical sensitivity of {{signal_detection_algorithm}} when applied to complaint data ingested at {{complaint_ingestion_frequency}}.
  2. Trace regulatory submission trigger points to determine if threshold crossings generate compliant reports for {{regulatory_oversight_body}}.
  3. Map how adverse event code groupings mask micro-clusters of component failures in {{device_classification}} hardware.
  4. Audit geographic filtering functionality across {{reporting_geography}} to verify that regional failure surges remain detectable.
  5. Critique visual alarm hierarchies, focusing on false-positive alert fatigue versus unflagged critical safety anomalies.
  6. Formulate statistical process control dashboard specifications that reduce time-to-signal discovery.

Constraints

  • MUST explicitly evaluate compliance against standard vigilance timeframes enforced by {{regulatory_oversight_body}}.
  • MUST NOT propose diagnostic algorithms incompatible with {{device_classification}} risk categories.
  • Findings MUST directly address data scale challenges associated with {{adverse_event_volume}} entries.
  • Recommendations must preserve audit-trail validation standards.

Output format

Produce an evaluation document formatted into these mandatory headings:

  • Safety Surveillance Dashboard Overview (100-140 words)
  • Signal Detection Methodological Gaps (3 detailed points reviewing {{signal_detection_algorithm}})
  • Regulatory Compliance & Reporting Vulnerabilities (focusing on {{regulatory_oversight_body}} requirements)
  • Metric & Layout Refactoring Matrix (bulleted action list for UI/UX and alert redesign)

Self-review

  • Checked that {{signal_detection_algorithm}} is critically evaluated for both sensitivity and false-positive rates.
  • Verified that regional jurisdictional nuances for {{reporting_geography}} are explicitly factored into the reporting audit.
  • Ensured the review does not violate medical device vigilance recordkeeping principles.
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.

data-analytics
data-dashboards
healthcare-life-sciences
medtech
safety-surveillance
post-market-vigilance