Any experiences of synthetich openEHR data, e.g. using Synthea?


Are you aware of any experiences of synthetich (fake) openEHR conformant data, generated e.g. using Synthea or similar?

Are there any openEHR based generation-source-code or datasets publicly available?


P.s. I do know that the ORBDA dataset can be used for tests, but since it is based on real patient data it only contains the kind of data that was available in the original source.

I’ve done some work with synthea to get some data based on ad-hoc archetypes (like 6 fields, demographic + diagnosis). If it is of any use I can upload it somewhere.
I believe @bna has done more work with synthea.
If I remember correctly, there was also some heart disease data publicly available in openEHR

1 Like

Yes. We did some work on this last summer it was done by summer students. We’ve not done any follow up on this.
Our approach was to read the generated fhir data and transform it into openehr compositions which where committed to the CDR.

1 Like