Learning similarities between irregularly sampled short multivariate time series from EHRs
Presentation from the 3rd International Workshop on Pattern Recognition for Healthcare Analytics at ICPR 2016. Held in Cancun, 04.12.2016. A large fraction of the Electronic Health Records consists of clinical multivariate time series. Building models for extracting information from these is importa...
Main Authors: | , , , , , , |
---|---|
Format: | Conference Object |
Language: | English |
Published: |
2016
|
Subjects: | |
Online Access: | https://hdl.handle.net/10037/10223 |
id |
ftunivtroemsoe:oai:munin.uit.no:10037/10223 |
---|---|
record_format |
openpolar |
spelling |
ftunivtroemsoe:oai:munin.uit.no:10037/10223 2023-05-15T17:39:23+02:00 Learning similarities between irregularly sampled short multivariate time series from EHRs Mikalsen, Karl Øyvind Bianchi, Filippo Maria Soguero-Ruiz, Cristina Skrøvseth, Stein Olav Lindsetmo, Rolv-Ole Revhaug, Arthur Jenssen, Robert 2016-12-04 https://hdl.handle.net/10037/10223 eng eng FRIDAID 1437149 https://hdl.handle.net/10037/10223 openAccess VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420 VDP::Technology: 500::Information and communication technology: 550 VDP::Mathematics and natural science: 400::Information and communication science: 420 VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550 VDP::Medical disciplines: 700::Clinical medical disciplines: 750::Gastroscopic surgery: 781 VDP::Medisinske Fag: 700::Klinisk medisinske fag: 750::Gasteroenterologisk kirurgi: 781 Conference object Konferansebidrag 2016 ftunivtroemsoe 2021-06-25T17:55:01Z Presentation from the 3rd International Workshop on Pattern Recognition for Healthcare Analytics at ICPR 2016. Held in Cancun, 04.12.2016. A large fraction of the Electronic Health Records consists of clinical multivariate time series. Building models for extracting information from these is important for improving the understanding of diseases, patient care and treatment. Such time series are oftentimes particularly challenging since they are characterized by multiple, possibly dependent variables, length variability and irregular samples. To deal with these issues when such data are processed we propose a probabilistic approach for learning pairwise similarities between the time series. These similarities constitute a kernel matrix that can be used for many different purposes. In this work it is used for clustering and data characterization. We consider two different multivariate time series datasets, one of them consisting of physiological measurements from the Department of Gastrointestinal Surgery at The University Hospital of North Norway and we show the proposed method’s robustness and ability of dealing with missing data. Finally we give a clinical interpretation of the clustering results. Conference Object North Norway University of Tromsø: Munin Open Research Archive Norway |
institution |
Open Polar |
collection |
University of Tromsø: Munin Open Research Archive |
op_collection_id |
ftunivtroemsoe |
language |
English |
topic |
VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420 VDP::Technology: 500::Information and communication technology: 550 VDP::Mathematics and natural science: 400::Information and communication science: 420 VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550 VDP::Medical disciplines: 700::Clinical medical disciplines: 750::Gastroscopic surgery: 781 VDP::Medisinske Fag: 700::Klinisk medisinske fag: 750::Gasteroenterologisk kirurgi: 781 |
spellingShingle |
VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420 VDP::Technology: 500::Information and communication technology: 550 VDP::Mathematics and natural science: 400::Information and communication science: 420 VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550 VDP::Medical disciplines: 700::Clinical medical disciplines: 750::Gastroscopic surgery: 781 VDP::Medisinske Fag: 700::Klinisk medisinske fag: 750::Gasteroenterologisk kirurgi: 781 Mikalsen, Karl Øyvind Bianchi, Filippo Maria Soguero-Ruiz, Cristina Skrøvseth, Stein Olav Lindsetmo, Rolv-Ole Revhaug, Arthur Jenssen, Robert Learning similarities between irregularly sampled short multivariate time series from EHRs |
topic_facet |
VDP::Matematikk og Naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420 VDP::Technology: 500::Information and communication technology: 550 VDP::Mathematics and natural science: 400::Information and communication science: 420 VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550 VDP::Medical disciplines: 700::Clinical medical disciplines: 750::Gastroscopic surgery: 781 VDP::Medisinske Fag: 700::Klinisk medisinske fag: 750::Gasteroenterologisk kirurgi: 781 |
description |
Presentation from the 3rd International Workshop on Pattern Recognition for Healthcare Analytics at ICPR 2016. Held in Cancun, 04.12.2016. A large fraction of the Electronic Health Records consists of clinical multivariate time series. Building models for extracting information from these is important for improving the understanding of diseases, patient care and treatment. Such time series are oftentimes particularly challenging since they are characterized by multiple, possibly dependent variables, length variability and irregular samples. To deal with these issues when such data are processed we propose a probabilistic approach for learning pairwise similarities between the time series. These similarities constitute a kernel matrix that can be used for many different purposes. In this work it is used for clustering and data characterization. We consider two different multivariate time series datasets, one of them consisting of physiological measurements from the Department of Gastrointestinal Surgery at The University Hospital of North Norway and we show the proposed method’s robustness and ability of dealing with missing data. Finally we give a clinical interpretation of the clustering results. |
format |
Conference Object |
author |
Mikalsen, Karl Øyvind Bianchi, Filippo Maria Soguero-Ruiz, Cristina Skrøvseth, Stein Olav Lindsetmo, Rolv-Ole Revhaug, Arthur Jenssen, Robert |
author_facet |
Mikalsen, Karl Øyvind Bianchi, Filippo Maria Soguero-Ruiz, Cristina Skrøvseth, Stein Olav Lindsetmo, Rolv-Ole Revhaug, Arthur Jenssen, Robert |
author_sort |
Mikalsen, Karl Øyvind |
title |
Learning similarities between irregularly sampled short multivariate time series from EHRs |
title_short |
Learning similarities between irregularly sampled short multivariate time series from EHRs |
title_full |
Learning similarities between irregularly sampled short multivariate time series from EHRs |
title_fullStr |
Learning similarities between irregularly sampled short multivariate time series from EHRs |
title_full_unstemmed |
Learning similarities between irregularly sampled short multivariate time series from EHRs |
title_sort |
learning similarities between irregularly sampled short multivariate time series from ehrs |
publishDate |
2016 |
url |
https://hdl.handle.net/10037/10223 |
geographic |
Norway |
geographic_facet |
Norway |
genre |
North Norway |
genre_facet |
North Norway |
op_relation |
FRIDAID 1437149 https://hdl.handle.net/10037/10223 |
op_rights |
openAccess |
_version_ |
1766140137665724416 |