We stood up the full Parthenon analyses pipeline end-to-end: 11 comparative effectiveness studies across 10 disease areas, 46 generated cohorts, and 26 executed analyses including R-based CohortMethod propensity score matching on populations up to 68,000 patients. Along the way, we found and fixed every null-safety bug that only surfaces when real analysis results hit the frontend.
Today we transformed Abby from a capable AI assistant into an OHDSI domain expert backed by the largest curated outcomes research knowledge base we're aware of in any open-source platform. By the end of the day, Abby's ohdsi_papers ChromaDB collection held 79,070 SapBERT-embedded vectors spanning peer-reviewed research papers, the Book of OHDSI, HADES package documentation, and a decade of practitioner Q&A from the OHDSI forums.
Today we gave Parthenon's AI assistant a research library that most outcomes researchers would envy. Abby — our context-aware, privacy-preserving AI — now has 115,000+ SapBERT-embedded vectors spanning 2,258 peer-reviewed OHDSI papers, the complete Book of OHDSI, documentation from 30 HADES R packages, a decade of community forum Q&A, and 19 medical reference textbooks covering epidemiology, biostatistics, pharmacology, pathology, and clinical medicine.
This post tells the full story: why we built Abby, how the architecture works, what we harvested, what we learned about data quality in knowledge bases, and where we're headed next.
Today was a focused, high-output session centered entirely on one major architectural shift: evolving the GIS Explorer from a hardcoded COVID-19 dashboard into a fully generalized spatial analytics tool capable of visualizing any condition in the OMOP CDM. Eighteen commits across the full stack — Python AI service, Laravel backend, and React frontend — tell the story of a component suite that went from COVID-specific to condition-agnostic in a single day.
A massive day across the Acumenus suite — 60 commits touching six repositories. The throughlines: a platform-wide push to standardize authentication using the MediCosts pattern, TypeScript migrations gaining serious momentum in multiple apps, and meaningful OHDSI clinical data work in Parthenon including surfacing 52.6 million clinical notes through a new Patient Profile tab.
We ran every analysis type in Parthenon — estimation, prediction, SCCS, evidence synthesis, pathways, characterization, and incidence rates — against our full Acumenus CDM with 1 million synthetic patients. Thirteen seeded analyses. Seven different OHDSI methodologies. One session.
This post covers what happened when we moved from the 2,694-patient Eunomia demo dataset to production scale, the bugs that only surface at a million patients, and the hard-won lessons about propensity score modeling on synthetic data.
The OHDSI HADES ecosystem is remarkable. CohortMethod, PatientLevelPrediction, SelfControlledCaseSeries — these R packages encode decades of pharmacoepidemiology methodology into reusable software. In theory, you point them at an OMOP CDM database, call a few functions, and get publication-ready causal inference results.
In practice, getting these packages to run correctly in a modern production environment required solving problems that no documentation warned us about.
This is the story of what we encountered building Parthenon's R runtime — a Plumber API sidecar that executes HADES analyses against a 1-million-patient CDM — and the specific, reproducible bugs we had to fix before a single analysis could complete.