Create synthetic datasets

[rileeki]

Data submission guidelines for CA hospitals:

https://hcai.ca.gov/wp-content/uploads/2022/12/IP-format-and-file-specs-jan-2023.pdf https://hcai.ca.gov/wp-content/uploads/2022/12/ED-AS-format-and-file-specs-jan-2023.pdf

Hospitals are required to submit their patient discharge data to the state as .txt files with a specific fixed-width layout.

I'd like to create synthetic data that we can use to demonstrate projects before having access to real, sensitive data.

[rileeki]

This is probably a whole project of its own... We'd want them to roll up to match the real, publicly available summary statistics. It could actually be kind of like our synthetic case pools for the surgery scheduling project.

[rileeki]

Summary files:

Inpatient

• https://data.chhs.ca.gov/dataset/hospital-inpatient-characteristics-by-facility-pivot-profile
• "Data" tab in .xlsx files 2012-2021

ED

• https://data.chhs.ca.gov/dataset/hospital-emergency-department-characteristics-by-facility-pivot-profile
• "Data" tab in .xlsx files 2005-2021

MS-DRGs

• https://data.chhs.ca.gov/dataset/top-25-ms-drgs-individual-hospital-pivot-profile
• "All Data" tab in .xlsx files 2012-2021

Homeless IP & ED

• https://data.chhs.ca.gov/dataset/hospital-encounters-for-homeless-patients
• .csv file 2019-2020

[rileeki]

also note: The 2021 IP data, at least, is set up with an existing Data API that might be worth exploring instead of downloading the Excel files and creating our own database. https://docs.ckan.org/en/latest/maintaining/datastore.html