Towards of automatically detecting brain death patterns through text mining

Abstract

In the area of medicine, x-rays are very useful to check if the patient suffers from brain death. Their diagnosis is made using free text. This type of record difficult the process of making qualitative analysis in order to automatically detect possible brain problems. This project aims to make qualitatively and quantitatively analysis of Brain Computed Tomography (CT) diagnosis using text analysis tools as is Natural Language Processing and Text Mining. In this work a set of related words that can means patterns in CT reports was detected. The dataset was provided by the Centro Hospitalar do Porto-Hospital de Santo António and it contains information about patient deaths and CT done to the brain. With the analysis made, a new research and analysis perspectives of structured and unstructured texts in this field was opened.