3  Synthetic Data

3.1 Data preparation process

The synthetic data is part of the docker container and already prepared in the right directories.

3.2 Table example

The tables have these columns:

Patient data (saved as cases.csv)

patient_num	start_date	ICD10	domain
num	date (y-m-d h:m:s)	char	char

Demographic data (saved as dems_cases.csv)

patient_num	age	sex_cd	race_cd	ethnicity_cd	CHARLSON_INDEX
num	num	char (F/M)	char	char	num

3.3 Directory guide

The directory tree in the docker container looks as follows:

• /home/rstudio(working directory)
  • data
    • synthetic_data
      • cases.csv
      • dems_cases.csv
  • output
  • scripts