Academic Communication

[kseverso]

Academic Communication

[kseverso]

Hi Zhang Suixia,
Thank you for your interest in our work. Perhaps you could clarify your specific request? I can say that I am no longer employed at IBM and therefore it is not my choice as to whether additional code and/or the model parameters are shared. You can reach out to researchers at IBM to ask about additional information. With regard to the code that is available, if you are encountering a specific issue, I'm happy to try and help. Thanks,
Kristen

[weijaytanzou]

Dear Dr Kristen： Thanks for your reply,I would like to apply the PIOHMM model to heart failure data for disease state mining.But I can't achieve state assignment of patient visits, this part of the result is how to implement state prediction using the Viterbi algorithm？ Can you share with me specifically? Thank you very much for your kind consideration and I am looking forward to your early reply. Sincerely: Zhang Suixia

…

-----原始邮件----- 发件人:Kristen ***@***.***> 发送时间:2021-11-23 01:24:10 (星期二) 收件人: kseverso/Discovery-of-PD-States-using-ML ***@***.***> 抄送: weijaytanzou ***@***.***>, Author ***@***.***> 主题: Re: [kseverso/Discovery-of-PD-States-using-ML] Academic Communication (Issue #2) Hi Zhang Suixia, Thank you for your interest in our work. Perhaps you could clarify your specific request? I can say that I am no longer employed at IBM and therefore it is not my choice as to whether additional code and/or the model parameters are shared. You can reach out to researchers at IBM to ask about additional information. With regard to the code that is available, if you are encountering a specific issue, I'm happy to try and help. Thanks, Kristen — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.

[kseverso]

I see. I think all the code you will need is available in the related repo: https://github.com/kseverso/DiseaseProgressionModeling-HMM. 'Discovery-of-PD-States-using-ML' is an example of how to use the PIOHMM for Parkinson's disease, but 'DiseaseProgressionModeling-HMM' has the general code.

[weijaytanzou]

Dear Dr Kristen： Thanks for codes of your article. But,I have a few questions want to discuss with you: First, I downloaded the PPMI data from the article, in LD_Data_Processing, I can't achieve the underlined code in the figure below, because the two data dimensions are different. Second,t time points = 31 ,how is it calculated? The following code not calculatet time points. Third,the content in the "get time and observation masks" n, t, d, = x_train.shape, how three dimensions of data are obtained? Probably because I ran the previous program normally. There are some questions, as you are the corresponding author of the article and no other author emails are given, I don't know which person at IBM I can contact either,I hope you can help me with my problem. Thank you very much for your kind consideration and I am looking forward to your early reply.

…

-----原始邮件----- 发件人:Kristen ***@***.***> 发送时间:2021-11-23 22:30:39 (星期二) 收件人: kseverso/Discovery-of-PD-States-using-ML ***@***.***> 抄送: weijaytanzou ***@***.***>, Author ***@***.***> 主题: Re: [kseverso/Discovery-of-PD-States-using-ML] Academic Communication (Issue #2) I see. I think all the code you will need is available in the related repo: https://github.com/kseverso/DiseaseProgressionModeling-HMM. 'Discovery-of-PD-States-using-ML' is an example of how to use the PIOHMM for Parkinson's disease, but 'DiseaseProgressionModeling-HMM' has the general code. — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.