Skip to content

Resources

Related tools, training and reference works from the same authors, for teams building patient-directed registries for ALS, other rare diseases and real world evidence.

CDAtransformer

BoyceLab/CDAtransformer is an earlier tool by the same author that parses an individual C-CDA file and shows its structured content (problems, medications, observations, labs, encounters, narratives) for direct inspection.

CDAtransformer or Registry Forge. The two tools solve different problems and work well together:

Use case Use CDAtransformer Use Registry Forge
"I have one C-CDA file and want to see what's in it" ✓
Exploring an unfamiliar EHR vendor's C-CDA flavor before scaling up ✓
Sanity-checking a single record against the chart ✓
Teaching / learning what C-CDA structure looks like ✓
"I have thousands of files across C-CDA + FHIR + RTF + PDF and want a research-ready data set" ✓
Producing a versioned OMOP CDM v5.4 ETL output ✓
Producing GA4GH Phenopackets for matchmaker submission ✓
Cohort EDA, device extraction, drug repurposing add-ons ✓
Quality control framework, vocabulary-versioned outputs ✓

A common sequence: use CDAtransformer when a new EHR vendor's files start arriving, to learn the shape of its C-CDA documents one at a time, then use Registry Forge to process the full set.

Reference works and training

ALS TDI Real World Evidence Resources

ALS TDI Real World Evidence Resources is the site ALS TDI curates for real world evidence (RWE) methodology, examples, and training relevant to ALS research. Includes worked examples, methodology notes, and pointers to the broader RWE community. A good starting point for anyone beginning RWE work in ALS or related neurodegenerative disease.

Book: Guide to Real-World Data for Clinical Research

By Danielle Boyce (ALS TDI) and Pavel Goriacko (Montefiore). A practical introduction to using real world data for clinical research covering data sources, study design, common pitfalls and worked examples. Recommended for clinicians, registry staff, and trainees who are new to real world evidence and want a single-volume orientation before going deeper into OMOP or Sentinel-style tooling.

Visit rwd.guide

Online course: Introduction to OMOP: Your Frequently Asked Questions Answered

Taught by Danielle Boyce (ALS TDI) and Pavel Goriacko (Montefiore) through the Tufts Clinical and Translational Science Institute. A structured introduction to the OMOP Common Data Model that answers the questions people most often have when they first meet OHDSI tools: what OMOP is and is not, when to use it, how vocabulary mapping works, what ATLAS does and how to read a CDM table. It pairs with the OMOP module.

Enroll in the course

Where this fits

Registry Forge covers the engineering side of registry data: parsing, normalizing and harmonizing raw EHR exports into structured outputs for research. The resources on this page focus on the methodology side: what real world data are suited to, how to design a study with them, what OMOP offers, and how to think about data quality. The pipeline produces the structured data; the methodology resources help decide what to do with them.

For the authoritative references on the standards Registry Forge consumes and produces (OMOP CDM v5.4 spec, GA4GH Phenopackets schema, HPO, Mondo, etc.), see the External references and standards page.