APEHR: Automated prognosis in electronic health records using multi-head self-attention

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade de São Paulo (USP)-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorFlorez, Alexander Y.C.-
Autor(es): dc.creatorScabora, Lucas-
Autor(es): dc.creatorEler, Danilo M [UNESP]-
Autor(es): dc.creatorRodrigues, Jose F-
Data de aceite: dc.date.accessioned2022-08-04T22:10:33Z-
Data de disponibilização: dc.date.available2022-08-04T22:10:33Z-
Data de envio: dc.date.issued2022-04-28-
Data de envio: dc.date.issued2022-04-28-
Data de envio: dc.date.issued2021-06-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1109/CBMS52027.2021.00077-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/222009-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/222009-
Descrição: dc.descriptionAutomated 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.-
Descrição: dc.descriptionUniversity of Sao Paulo, SP-
Descrição: dc.descriptionSao Paulo State University, SP-
Descrição: dc.descriptionSao Paulo State University, SP-
Formato: dc.format277-282-
Idioma: dc.languageen-
Relação: dc.relationProceedings - IEEE Symposium on Computer-Based Medical Systems-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectautomated clinical prediction-
Palavras-chave: dc.subjectclinical trajectory-
Palavras-chave: dc.subjectdeep learning-
Palavras-chave: dc.subjecttransformer-
Título: dc.titleAPEHR: Automated prognosis in electronic health records using multi-head self-attention-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.