Developing Concept Enriched Models for Processing Big Data Within the Medical Domain

Abstract

As more and more domains are incorporating cognitive computing tools to develop models to process and understand data in a cohesive, yet effective manner, the medical domain is also seeking advancements aided by artificial intelligence. While the amount of research available to any individual increases regularly, the ability to keep up with new information becomes a challenge due to the sheer quantity of information. The use of artificial intelligence to help process large amounts of information can overcome those barriers. However, progress in this field is hindered by several challenges including: incomplete medical data sets, the confidential nature of data as it holds private information of individuals, the complexity and nuances of natural language (within medicine), and even the unwillingness of health-care providers to adopt newer techniques. Though the data may be specialized, the models and techniques designed and discussed in this paper can help provide a framework, or starting point for those interested in effectively developing, maintaining, and using these models to help improve the quality of health-care. The purpose of this paper is to serve as resource which can be used to start developing similar models and put them to use in everyday practice in the medical domain.