Real-World Evidence and Registry Data Analysis Services
Pubrica analyses real-world and registry data for researchers, life-science companies and health technology assessment submissions. We construct study cohorts from routine data, control for confounding with methods suited to the design, and report the analysis to STROBE and RECORD, so that the evidence can be assessed by journals, regulators and payers.
- Target trial emulation used where a causal question is asked of observational data
- Confounding addressed explicitly, with propensity score, weighting or other methods justified
- Sensitivity analyses for unmeasured confounding, missing data and key definitions
- Reporting to STROBE and RECORD, with code lists and definitions supplied
- Fitness of the data assessed before the analysis is designed
Protocol and statistical analysis planIncluded
Analysis code and code listsIncluded
Results tables and figuresIncluded
Study report or manuscript sectionsIncluded
Sensitivity analysis summaryIncluded
Service Scope
What Our Real-World Data Analysis Service Covers
Each project is scoped individually. The components below are combined according to your study and its requirements.
Applications
Typical Applications of Real-World Data
Process
How the Project Works
Methods, deliverables and fees are confirmed in writing before work begins.
Real-world data can support causal conclusions only under assumptions that must be stated and tested. We design the analysis to make those assumptions explicit.
It specifies the randomised trial that would ideally answer the question and then designs the observational analysis to mirror it, which avoids several common biases.
Registries, EHR, claims and linked datasets, subject to the access arrangements and approvals for each source.
Yes. The methods and results are reported to these guidelines, with the code lists and definitions supplied.
Pubrica Academy
Further Reading in Pubrica Academy
Request a Feasibility Review of Your Real-World Data Question
Describe the question and the data source. We assess whether the data can answer it and confirm the design, deliverables and fee.