Structured and unstructured data integration with electronic medical records

• Autor(a) principal: Baptista, Diogo Veiga Amorim Santos
• Data de Publicação: 2019
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10071/20470
• topic: Structured data; Unstructured data; Natural language processing; Data integration; Electronic medical records; Dados estruturados; Dados não estruturados; Processamento natural da língua; Integração de dados; Registos médicos eletrónicos

In recent years there has been a great population and technological evolution all over the world. At the same time, more areas beyond technology and information technology have also developed, namely medicine, which has led to an increase in average life expectancy which in turn, leads to a greater need for healthcare. In order to provide the best possible treatments and healthcare services, nowadays the hospitals store large amounts of data regarding patients and diseases (in the form of electronic medical records) or the logistics of some departments in their storage systems. Therefore, computer science techniques such as data mining and natural language processing have been used to extract knowledge and value from these information-rich sources in order not only to develop, for example, new models for disease prediction, as well as improving existing processes in healthcare centres and hospitals. This data storage can be done in one of three ways: structured, unstructured or semi-structured. In this paper, the author tested the integration of structured and unstructured data from two different departments of the same Portuguese hospital, in order to extract knowledge and improve hospital processes. Aiming to reduce the value loss of loading data that is not used in the healthcare providers systems.