Modeling and Visualization of clinical texts to enhance meaningful and user friendly information retrieval

Access to health data collections such as clinical notes, discharge summaries or medical charts in Electronic Health Records have increased in the last few years due to increase use of electronic health records that provide instant access to patients’ clinical information. The volume and the unstructured nature of these datasets present great challenges in analyses and subsequent applications to healthcare. The growing volume of clinical data generated and stored in electronic health records creates challenges for physicians when reviewing patients records with the aim of understanding individual patients’ health histories. Electronic healthcare records contain large volumes of unstructured data which requires one to read through to get the required information. This is a challenging task due to lack of suitable techniques to quicly extract needed information. Information processing tools in clinical domain that provide support to users in seeking needed information are lacking. The use of data visualizations have been introduced in an attempt to solve this problem; however, no single approach has been widely adopted. In this paper we propose a unique approach for modelling clinical notes using semantics of various units of a clinical text document to aid doctors in reviewing electronic clinical notes. This is achieved by applying supervised machine learning technique to identify and present semantically similar information together, facilitating the identification of relevant information to users.