| OHDSI Home | Forums | Wiki | Github |
Hi,
We are developing a new algorithm/tool to query OMOP data. The tool may benefit the broader OHDSI community.
Is that possible to host the code under OHDSI github (Observational Health Data Sciences and Informatics · GitHub)?
What is the process to do it?
Thanks!
Yupeng
There’s no formal procedure for this, but I can create a repo for you if you provide the requested repo name and your github user name. I guess there are two requirements for the software
What language does the tool use? R? Python?
I bet on R… It’s my guess
Thank you! @schuemie
Merck and Amazon are working together to develop a tool that can translate user’s question to SQL query and directly retrieve the result from OMOP data.
It has a similar concept with Criteria2Query Criteria2Query, but it is a deep learning model with higher accuracy and flexibility. The workflow does not depend on Atlas.
We also have a set of training data (user-generated questions and corresponding SQL queries) we can include in the github repository. The training data can be used for more general Text-to-SQL purpose.
Can we call it “NL2SQL-OMOP”? (Changing it to NOSTOS, “navigate omop-structured data via text-to-sql" based on suggestion from Chris)
The github users are: miguelrc1, liyupeng111, Weilin37.
cc @gregk
Mostly python
I wonder if ‘NL2SQL-OMOP’ is too generic? Do you think you could come up with a project name for this? Examples are CIRCE, ACHILLES, HADES, CAPER, etc.
How about “navigate omop-structured data via text-to-sql (NOSTOS)”?
That works for me (not that I have any say in this 
) and if there are other implemenattions/efforts to create a simiilar function, the other impl can come up with their own name.