Conference item icon

Conference item

The signature-based model for early detection of sepsis from electronic health records in the intensive care unit

Abstract:

Optimal feature selection leads to enhanced efficiency and accuracy when developing both supervised and unsupervised machine-learning models. In this work, a new signature-based regression model is proposed to automatically identify a patient's risk of sepsis based on physiological data streams and to make a positive or negative prediction of sepsis for every time interval since admission to the intensive care unit. The gradient boosting machine algorithm that uses the features at the current...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.23919/CinC49843.2019.9005805

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Mathematical Institute
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Mathematical Institute
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MSD
Department:
Psychiatry
Role:
Author
ORCID:
0000-0001-9276-2720
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Mathematical Institute
Oxford college:
Christ Church
Role:
Author
ORCID:
0000-0001-7938-370X
Expand authors...
Publisher:
IEEE Publisher's website
Volume:
46
Host title:
2019 Computing in Cardiology (CinC)
Publication date:
2020-02-24
Acceptance date:
2019-10-01
Event title:
2019 Computing in Cardiology (CinC)
Event location:
Singapore
Event website:
http://cinc2019.org/
Event start date:
2019-09-08T00:00:00Z
Event end date:
2019-09-11T00:00:00Z
DOI:
EISBN:
9781728169361
EISSN:
2325-887X
ISSN:
2325-8861
Source identifiers:
1063244
ISBN:
9781728159423
Language:
English
Keywords:
Pubs id:
pubs:1063244
UUID:
uuid:3c3fb505-eaba-4310-8ea8-a377b7f25dce
Local pid:
pubs:1063244
Deposit date:
2019-10-16

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP