APEHR: Automated prognosis in electronic health records using multi-head self-attention
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , |
Tipo de documento: | Artigo de conferência |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1109/CBMS52027.2021.00077 http://hdl.handle.net/11449/222009 |
Resumo: | Automated prognosis has been a topic of intense research. Many works have sought to learn from Electronic Health Records using Recurrent Neural Networks that, despite promising results, have been overcome by novel techniques. We introduce APEHR, a Transformer approach that leverages medical prognosis using the latest technology Neural Network Transformer, which has demonstrated superior results in problems whose data is organized in sequential fashion. We contribute with an innovative problem modeling along with a detailed discussion of how Transformers can be used in the medical domain. Our results demonstrate a prognostic performance that surpasses previous works by at least 6% for metric Recall@k in the public dataset MIMIC-III. |
id |
UNSP_479c7d2d979074c47f3957e223052791 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/222009 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
APEHR: Automated prognosis in electronic health records using multi-head self-attentionautomated clinical predictionclinical trajectorydeep learningtransformerAutomated prognosis has been a topic of intense research. Many works have sought to learn from Electronic Health Records using Recurrent Neural Networks that, despite promising results, have been overcome by novel techniques. We introduce APEHR, a Transformer approach that leverages medical prognosis using the latest technology Neural Network Transformer, which has demonstrated superior results in problems whose data is organized in sequential fashion. We contribute with an innovative problem modeling along with a detailed discussion of how Transformers can be used in the medical domain. Our results demonstrate a prognostic performance that surpasses previous works by at least 6% for metric Recall@k in the public dataset MIMIC-III.University of Sao Paulo, SPSao Paulo State University, SPSao Paulo State University, SPUniversidade de São Paulo (USP)Universidade Estadual Paulista (UNESP)Florez, Alexander Y.C.Scabora, LucasEler, Danilo M [UNESP]Rodrigues, Jose F2022-04-28T19:41:55Z2022-04-28T19:41:55Z2021-06-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject277-282http://dx.doi.org/10.1109/CBMS52027.2021.00077Proceedings - IEEE Symposium on Computer-Based Medical Systems, v. 2021-June, p. 277-282.1063-7125http://hdl.handle.net/11449/22200910.1109/CBMS52027.2021.000772-s2.0-85110861789Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengProceedings - IEEE Symposium on Computer-Based Medical Systemsinfo:eu-repo/semantics/openAccess2022-04-28T19:41:55Zoai:repositorio.unesp.br:11449/222009Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T17:08:57.482603Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
APEHR: Automated prognosis in electronic health records using multi-head self-attention |
title |
APEHR: Automated prognosis in electronic health records using multi-head self-attention |
spellingShingle |
APEHR: Automated prognosis in electronic health records using multi-head self-attention Florez, Alexander Y.C. automated clinical prediction clinical trajectory deep learning transformer |
title_short |
APEHR: Automated prognosis in electronic health records using multi-head self-attention |
title_full |
APEHR: Automated prognosis in electronic health records using multi-head self-attention |
title_fullStr |
APEHR: Automated prognosis in electronic health records using multi-head self-attention |
title_full_unstemmed |
APEHR: Automated prognosis in electronic health records using multi-head self-attention |
title_sort |
APEHR: Automated prognosis in electronic health records using multi-head self-attention |
author |
Florez, Alexander Y.C. |
author_facet |
Florez, Alexander Y.C. Scabora, Lucas Eler, Danilo M [UNESP] Rodrigues, Jose F |
author_role |
author |
author2 |
Scabora, Lucas Eler, Danilo M [UNESP] Rodrigues, Jose F |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade de São Paulo (USP) Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Florez, Alexander Y.C. Scabora, Lucas Eler, Danilo M [UNESP] Rodrigues, Jose F |
dc.subject.por.fl_str_mv |
automated clinical prediction clinical trajectory deep learning transformer |
topic |
automated clinical prediction clinical trajectory deep learning transformer |
description |
Automated prognosis has been a topic of intense research. Many works have sought to learn from Electronic Health Records using Recurrent Neural Networks that, despite promising results, have been overcome by novel techniques. We introduce APEHR, a Transformer approach that leverages medical prognosis using the latest technology Neural Network Transformer, which has demonstrated superior results in problems whose data is organized in sequential fashion. We contribute with an innovative problem modeling along with a detailed discussion of how Transformers can be used in the medical domain. Our results demonstrate a prognostic performance that surpasses previous works by at least 6% for metric Recall@k in the public dataset MIMIC-III. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-06-01 2022-04-28T19:41:55Z 2022-04-28T19:41:55Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/conferenceObject |
format |
conferenceObject |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1109/CBMS52027.2021.00077 Proceedings - IEEE Symposium on Computer-Based Medical Systems, v. 2021-June, p. 277-282. 1063-7125 http://hdl.handle.net/11449/222009 10.1109/CBMS52027.2021.00077 2-s2.0-85110861789 |
url |
http://dx.doi.org/10.1109/CBMS52027.2021.00077 http://hdl.handle.net/11449/222009 |
identifier_str_mv |
Proceedings - IEEE Symposium on Computer-Based Medical Systems, v. 2021-June, p. 277-282. 1063-7125 10.1109/CBMS52027.2021.00077 2-s2.0-85110861789 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Proceedings - IEEE Symposium on Computer-Based Medical Systems |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
277-282 |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128762836942848 |