Dataset Overview

The HealthVerity Stratified Dataset is a large, longitudinal closed medical and pharmacy claims dataset designed for rapid, evidence-ready real-world analyses. This dataset is fully integrated and available within the Medeloop Analytics platform.

• Population size: ~3.9 million de-identified patients
• Timeframe: January 2020 – March 2025
• Geography: United States

Core Data Sources

• Medical claims
  • Diagnoses (ICD-10)
  • Procedures (CPT/HCPCS)
  • Site of care (inpatient, outpatient, ER)
  • Provider and facility identifiers (aggregated use)
• Pharmacy claims
  • Dispensed medications (NDC)
  • Fill dates, days’ supply
  • Therapeutic class comparisons
• Mortality data
  • Linked death indicators and dates (where available)

What the Dataset Supports Well ✅

• Patient cohort identification and feasibility
• Prevalence and incidence analyses
• Treatment patterns and switching
• Adherence and persistence (PDC, MPR)
• Comparative effectiveness and safety
• Time-to-event and survival analyses
• Utilization metrics (e.g., hospitalizations, ER visits)

Partial / Emerging Support ⚙️

• Cost of care (manual, beta workflows)
• Resource utilization summaries