Open-Source Analytics

Turn scientific best practices into reusable tools

OHDSI software turns shared data standards and methodological practices into a transparent, reproducible workflow. Researchers can design a study in ATLAS, coordinate its execution with Strategus, run analyses through HADES, and use diagnostic and results tools to evaluate and communicate the findings. Because the software is open source, study logic can be inspected, reused, and improved by the community.

  • Design with ATLAS. A browser-based environment for defining cohorts and analysis specifications.
  • Execute with HADES. R packages for characterization, causal-effect estimation, patient-level prediction, and supporting analytical functions.
  • Coordinate with Strategus. A standardized way to configure and execute analytical modules across studies and databases.
A common study package is executed behind each data partner’s firewall; approved aggregate results—not patient-level records—move onward for diagnostics, synthesis, and interpretation.
  • Diagnose with purpose-built tools. Data Quality Dashboard, CohortDiagnostics, PheValuator, and related packages help evaluate whether data, phenotypes, and study designs are suitable for the intended question.

You do not need to learn every OHDSI tool or repository. Begin with the task you need to complete: design a study, coordinate execution, run an analysis, or evaluate results. The documentation and tutorials will guide you to the relevant tools, while the forums and workgroups provide help when implementation questions arise.

Useful Publications

  1. Schuemie M, Reps J, Black A, et al. Health-Analytics Data to Evidence Suite (HADES): Open-Source Software for Observational Research. Stud Health Technol Inform. 2024;310:966–970. https://doi.org/10.3233/SHTI231108 7
  2. Reps JM, Schuemie MJ, Suchard MA, et al. Design and implementation of a standardized framework to generate and evaluate patient-level prediction models. JAMIA. 2018. https://doi.org/10.1093/jamia/ocy032 14
  3. Blacketer C, Defalco FJ, Ryan PB, Rijnbeek PR. Increasing trust in real-world evidence through evaluation of observational data quality. JAMIA. 2021. https://doi.org/10.1093/jamia/ocab132 10
  •