This new dataset could be great for demoing the Tuva Project. We should investigate whether this is the case, by loading it into Snowflake and assessing if it has the necessary data elements for the claims tables in the Input Layer. If it does, we should map it to the input layer and run the tuva project and run the various SQL queries to see how reasonable / interesting the results are. If the results seem super reasonable / interesting, we should use this as our demo data (it's 10k patients).
Docs: if this turns out to be good data, add to the current Synthetic Data page and maybe write a blog post (see CMS link for an example).
This new dataset could be great for demoing the Tuva Project. We should investigate whether this is the case, by loading it into Snowflake and assessing if it has the necessary data elements for the claims tables in the Input Layer. If it does, we should map it to the input layer and run the tuva project and run the various SQL queries to see how reasonable / interesting the results are. If the results seem super reasonable / interesting, we should use this as our demo data (it's 10k patients).
Docs: if this turns out to be good data, add to the current Synthetic Data page and maybe write a blog post (see CMS link for an example).