BookmarkSubscribeRSS Feed
Banke
Pyrite | Level 9

Hello everyone,

 

Please, I am monitoring patietns for 1 year: 6months before they start taking medications (start_date) and 6 months after (end_date). The first day of medication intake is the index_date. Each patient has unique start, index, and end dates. I am asked toidentify baseline characteristics of my patients 6 months before they start taking medications i.e before the index date.My data consists of multiple observations for each patient. I am trying to reduce these to observations occuring 6 months before the index date.I am confused at what to do. I will really appreciate your help. Thank you

 

My data looks like this

patient  start_date   index_date  end_date

1            04/2015    10/24/2015   04/2016

1            04/2015    10/24/2015   04/2016

1            04/2015    10/24/2015   04/2016

2           01/2015     07/17/2015   01/2016

2           01/2015     07/17/2015   01/2016

4 REPLIES 4
ballardw
Super User

You say "identifying diseases" in the title. Which of these dates relates to disease? Before which "particular date".

 

You must define characteristics in terms of the variables you share with us as we do not know any interpretation without your help.

Banke
Pyrite | Level 9

Sorry for the confusion. The baseline characteristics i want to identify are age, sex, region, diseases they had in that period and medications they took. I am not really worried about the first 3 because they usually stay the same but they are likely to have fewer diseases and take fewer medications before the index date. The disease variables are like 10 e.g. icd1 icd2 icd3 icd4 etc. each icd variable have list of conditions the patients have. I dont know how to link this because the index, start, and end dates are fixed for each patient. But checking now, there is a medical treatment date variable. Is that what i will use to identify if the condition was diagnosed before the index date? There is also fill date for prescription.

 

Thank you

ballardw
Super User

Your example data should include enough information that you can point to variables and values to do the task. Which means how do we know what disease? What "particular date" ?

 

Do you have a SAS data set with the information? If not building one or more sets with the information is a first step.

 

Banke
Pyrite | Level 9
I understand it better now, thank you

SAS Innovate 2025: Register Now

Registration is now open for SAS Innovate 2025 , our biggest and most exciting global event of the year! Join us in Orlando, FL, May 6-9.
Sign up by Dec. 31 to get the 2024 rate of just $495.
Register now!

Mastering the WHERE Clause in PROC SQL

SAS' Charu Shankar shares her PROC SQL expertise by showing you how to master the WHERE clause using real winter weather data.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 4 replies
  • 751 views
  • 1 like
  • 2 in conversation