search

ruoqi-liu / DeepIPW

Code for paper "A deep learning framework for drug repurposing via emulating clinical trials on real world patient data" (Accepted to Nature Machine Intelligence).
MIT License
92 stars 20 forks source link

Question about synthetic data #2

Open jdjmoon opened 2 years ago

jdjmoon commented 2 years ago

Hi Ruoqi, I found the paper to be interested, and thank you for making the codes available. Before I planned on applying the model to our real data problem, I was running your code with the simulation data you have provided. While I have followed the direction provided (including using same version of the libraries), I have been getting several errors while running the Bash/python command: "bash run_lstm.sh" (I have also tried to change the pkl files in the FILES, but did not had any luck). I was wondering if you happened to get any errors when you run it? Another question I had was if I understood your code and paper properly, it's okay to add and modify demographic information (and changing the pre_demo.py) would make the code to work properly. Is this correct, or would the model only work in this particular frame for real data?

Thanks very much to your response or help!

haolx commented 1 year ago

One basic question please, why insurance enrollment start and end dates are needed? Is that because in the RCT step you consider all the patients that had a valid insurance only / balanced-out the insurance-covered/non-covered factor? Thank you!

ruoqi-liu commented 1 year ago

One basic question please, why insurance enrollment start and end dates are needed? Is that because in the RCT step you consider all the patients that had a valid insurance only / balanced-out the insurance-covered/non-covered factor? Thank you!

Hi, The start date is used to measure the baseline period and the end date is used to measure the follow-up period in order to construct a valid user cohort.

ruoqi-liu commented 1 year ago

Hi Ruoqi, I found the paper to be interested, and thank you for making the codes available. Before I planned on applying the model to our real data problem, I was running your code with the simulation data you have provided. While I have followed the direction provided (including using same version of the libraries), I have been getting several errors while running the Bash/python command: "bash run_lstm.sh" (I have also tried to change the pkl files in the FILES, but did not had any luck). I was wondering if you happened to get any errors when you run it? Another question I had was if I understood your code and paper properly, it's okay to add and modify demographic information (and changing the pre_demo.py) would make the code to work properly. Is this correct, or would the model only work in this particular frame for real data?

Thanks very much to your response or help!

Hi,

Could you please share the error message you got?

haolx commented 1 year ago

Thank you Ruoqi! The methods section is super helpful. As I read more about your paper, I find it more fantastic!

On Thu, Oct 27, 2022 at 8:29 AM Ruoqi Liu @.***> wrote:

One basic question please, why insurance enrollment start and end dates are needed? Is that because in the RCT step you consider all the patients that had a valid insurance only / balanced-out the insurance-covered/non-covered factor? Thank you!

Hi, The start date is used to measure the baseline period and the end date is used to measure the follow-up period in order to construct a valid user cohort.

— Reply to this email directly, view it on GitHub https://github.com/ruoqi-liu/DeepIPW/issues/2#issuecomment-1293528949, or unsubscribe https://github.com/notifications/unsubscribe-auth/AW4KBXVORBRFSFDTMZ6SMADWFJ7TVANCNFSM5UKFW3CQ . You are receiving this because you commented.Message ID: @.***>