search

MIT-LCP / physionet

A collection of tools for working with the PhysioNet repository.
http://physionet.org/
MIT License
69 stars 17 forks source link

problem about The MIT-BIH Supraventricular Arrhythmia Database #112

Open sanqiaiziji opened 5 years ago

sanqiaiziji commented 5 years ago

“https://physionet.org/physiobank/database/svdb/” only described very simple information。

and in the paper "Greenwald SD. Improved detection and classification of arrhythmias in noise-corrupted electrocardiograms using contextual information. Ph.D. thesis, Harvard-MIT Division of Health Sciences and Technology, 1990.” I did not find the relevant answer: the ECG1 and ECG2 belong to which channel? MLII or V2 or V5?

I hope to get help from all of you. wangxiangqing@bupt.edu.cn

banchuangliangyue commented 4 years ago

So is there any reply?

“https://physionet.org/physiobank/database/svdb/” only described very simple information。

and in the paper "Greenwald SD. Improved detection and classification of arrhythmias in noise-corrupted electrocardiograms using contextual information. Ph.D. thesis, Harvard-MIT Division of Health Sciences and Technology, 1990.” I did not find the relevant answer: the ECG1 and ECG2 belong to which channel? MLII or V2 or V5?

I hope to get help from all of you. wangxiangqing@bupt.edu.cn

rgmark commented 4 years ago

Those are Holter recordings. Leads are usually approximately modified lead II and a modified lead V2, but lead attachments are not particularly consistent. Hope that helps, but the precise lead configurations are not important.

RGM

On 4/4/2020 4:11 AM, banchuangliangyue wrote:

So is there any reply?

“https://physionet.org/physiobank/database/svdb/”
<https://physionet.org/physiobank/database/svdb/%E2%80%9D> only
described very simple information。

and in the paper "Greenwald SD. Improved detection and
classification of arrhythmias in noise-corrupted
electrocardiograms using contextual information. Ph.D. thesis,
Harvard-MIT Division of Health Sciences and Technology, 1990.” I
did not find the relevant answer: the ECG1 and ECG2 belong to
which channel? MLII or V2 or V5?

I hope to get help from all of you. wangxiangqing@bupt.edu.cn
<mailto:wangxiangqing@bupt.edu.cn>

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/MIT-LCP/physionet/issues/112#issuecomment-608993817, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABYOOSTIGHF6TPHV2BTYNDLRK3TUPANCNFSM4HZFIQXA.

-- Roger G. Mark, M.D., Ph.D. Distinguished Professor in Health Sciences and Technology, Post-tenure Institute of Medical Engineering and Science Room E25-505 MIT Cambridge, MA 02139 Tel 617-253-7818 Fax 617-258-7859

banchuangliangyue commented 4 years ago

Thanks.! But I still have a question. Does ECG1 correspond to MLII and ECG2 corresponds to V2?

rgmark commented 4 years ago

Yes, generally.

On 4/4/2020 9:46 AM, banchuangliangyue wrote:

Thanks.! But I still have a question. Does ECG1 correspond to MLII and ECG2 corresponds to V2?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/MIT-LCP/physionet/issues/112#issuecomment-609031067, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABYOOSXW62AFUKC3GI7OYZ3RK422ZANCNFSM4HZFIQXA.

-- Roger G. Mark, M.D., Ph.D. Distinguished Professor in Health Sciences and Technology, Post-tenure Institute of Medical Engineering and Science Room E25-505 MIT Cambridge, MA 02139 Tel 617-253-7818 Fax 617-258-7859

banchuangliangyue commented 4 years ago

@rgmark. Hello, rgmark! I am using the MITDB data set to design a heartbeat classification algorithm. However, I have seen some papers divide the heartbeat of category 'j' and 'e' into category 'N' according to the AAMI standard, and some papers divide them into category 'S'. Do you know which division method is correct?

smolendawid commented 4 years ago

I've got the question too: does anyone know whether each recording is a recording of a different person? @rgmark @banchuangliangyue @sanqiaiziji

rgmark commented 4 years ago

Yes, each recording is from a different Holter recording (and different person).

On 7/11/2020 9:51 AM, smolendawid wrote:

I've got the question too: does anyone know whether each recording is a recording of a different person? @rgmark https://github.com/rgmark @banchuangliangyue https://github.com/banchuangliangyue @sanqiaiziji https://github.com/sanqiaiziji

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/MIT-LCP/physionet/issues/112#issuecomment-657065840, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABYOOSWSVLDPOGWNJ374I5LR3BU7FANCNFSM4HZFIQXA.

-- Roger G. Mark, M.D., Ph.D. Distinguished Professor in Health Sciences and Technology, Post-tenure Institute of Medical Engineering and Science Room E25-505 MIT Cambridge, MA 02139 Tel 617-253-7818 Fax 617-258-7859