Publicação

Intelligent decision support system for precision medicine: time series multi-variable approach for data processing

Ver documento

Detalhes bibliográficos
Resumo:This study has introduced a new approach to clinical data processing. Clinical data is unstructured, heterogeneous, and comes from various resources. Although, the challenges associated with processing such data have been discussed widely in literature, addressing those aspects is fragmented and case-based. This paper presents the initial outcome of applying the Time series Multi-Variables model (TsMV) to 12 different datasets from Intensive Care Units (ICU), medications, and laboratories. TsMV supports the development of an Intelligent Decision Support System for PM (IDSS4PM) by preparing effective data. Moreover, the CRISP-DM methodology was employed, and based on the proposed solution, we have adjusted the significant steps to CRISP-DM, where those extra phases are essential for taking future works.
Autores principais:Mosavi, Nasimsadat
Outros Autores:Santos, Manuel
Assunto:Data Processing Intelligent Decision Support Intensive Care Unit Optimization Precision Medicine
Ano:2022
País:Portugal
Tipo de documento:comunicação em conferência
Tipo de acesso:acesso aberto
Instituição associada:Universidade do Minho
Idioma:inglês
Origem:RepositóriUM - Universidade do Minho
Descrição
Resumo:This study has introduced a new approach to clinical data processing. Clinical data is unstructured, heterogeneous, and comes from various resources. Although, the challenges associated with processing such data have been discussed widely in literature, addressing those aspects is fragmented and case-based. This paper presents the initial outcome of applying the Time series Multi-Variables model (TsMV) to 12 different datasets from Intensive Care Units (ICU), medications, and laboratories. TsMV supports the development of an Intelligent Decision Support System for PM (IDSS4PM) by preparing effective data. Moreover, the CRISP-DM methodology was employed, and based on the proposed solution, we have adjusted the significant steps to CRISP-DM, where those extra phases are essential for taking future works.