Fusion of clinical data: A case study to predict the type of treatment of bone fractures

Abstract

Clinical data is characterized not only by its constantly increasing volume but also by its diversity. Information collected in clinical information systems such as electronic health records is highly heterogeneous and it includes structured laboratory and examination reports, unstructured clinical notes, images, and more often genetic data. This heterogeneity poses a significant challenge when constructing diagnostic and therapeutic decision models that should use data from all available sources to provide a comprehensive support. A possible response to this challenge is offered by the concept of data fusion and associated techniques. In this paper, we briefly describe the foundations of data fusion and present its application in a case study aimed at building a decision model to predict the type of treatment for patients with bone fractures. Specifically, the model should distinguish between patients who should undergo a surgery and those who should be treated non-surgically.