OHDSI Home | Forums | Wiki | Github

Maintainer for ETL-Synthea

(Michael Shamberger) #1


Could I become a maintainer for ETL-Synthea? There are 5 outstanding pull requests so it is in need of some effort.

I have been around omop silently for about 4 years receiving Masters degree from Georgia Tech and took a class from Jimeng Sun on Big Data in Healthcare analytics.

I recently contributed the first country module to synthea-international for the country of Finland and am planning the entire Europe now from open data feeds.

With a little more work I think we can generate massive data sets in OMOP format (beyond the 5% synpuf) and also could produce some automation to produce module specifc small datasets for researchers. For example, if someone wants 100 patients only with cancer in omop format they could download it without having to run the translators.

(Vojtech Huser) #2

I would contact the J&J team about this.

One nice addition to the OMOP Synthea space would be a guide on how to get your synthetic data. (without piecing it from 2 repos).

I have to first study the Synthea product and then do the ETL. It is 4+ hours of work and having a guide shrinking it to 1 hour would be great. Or even better, a SqlLite file with 100 person Synthea OMOP data. (like Eunomia)