Abstract

Big data applications in the Healthcare sector indicate a high potential for improv- ing the overall efficiency and quality of care delivery. Health data analytics highly relies on the availability of Electronic Health Records (EHRs). The complexity of healthcare informa- tion management is not only due to the amount of data generated but also by its diversity and the challenges of extracting knowledge from unstructured data. Solutions have not proposed until now an integrated solution to process, mine and extract knowledge. In this paper we propose an architecture, TIDA, to deal in an integrated way with all the information con- tained in EHR. TIDA (Text, Image and Data Analytics) makes it possible to address the problem of Spanish text indexing in the healthcare domain by adapting different techniques and technologies, besides components have been included to deal with image segmentation.