Publicação
Automatically detect diagnostic patterns based on clinical notes through Text Mining
| Resumo: | The importance of standardized treatment for patients is huge because it can reduce waiting times, costs in hospitals and make treatment more effective for patients. According to these patterns, the creation of a tool that can make the admission and interpretation of free text will become an important step in the medical field. For the analysis of the unstructured text, the "RapidMiner" tool was used. Following the text analysis, the word frequency technique will be used in the reports and the respective word counts, as well as the cluster analysis that allows the creation of combinations of words. For the modeling we used several Text Mining techniques focused on the main algorithms, since these are properly scientifically proven and that, normally, they are able to obtain better results. (C) 2019 The Authors. Published by Elsevier B.V. |
|---|---|
| Autores principais: | Ribeiro, Joao |
| Outros Autores: | Duarte, Julio; Portela, Filipe; Santos, Manuel |
| Assunto: | Text Mining Text Analysis |
| Ano: | 2019 |
| 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 |
| Resumo: | The importance of standardized treatment for patients is huge because it can reduce waiting times, costs in hospitals and make treatment more effective for patients. According to these patterns, the creation of a tool that can make the admission and interpretation of free text will become an important step in the medical field. For the analysis of the unstructured text, the "RapidMiner" tool was used. Following the text analysis, the word frequency technique will be used in the reports and the respective word counts, as well as the cluster analysis that allows the creation of combinations of words. For the modeling we used several Text Mining techniques focused on the main algorithms, since these are properly scientifically proven and that, normally, they are able to obtain better results. (C) 2019 The Authors. Published by Elsevier B.V. |
|---|