Unified framework for clinical data analytics (U-CDA)

Abstract

In spite of significant progress in the area of data management and integration, heterogeneous nature of clinical data makes it challenging to develop a unified view of clinical data. Therefore, a central question we are trying to address is how we can utilize data analytics to discover insightful knowledge from the scattered & large amount of clinical data to simplify clinical decision making. We propose a Unified Framework for Clinical Data Analytics (U-CDA) for mining large amounts of heterogeneous data to build enhanced clinical data analytics system. This requires addressing several challenges: · A substantial amount of patient data is stored in unstructured data sources such as patient diaries, clinical notes. It is challenging to aggregate and analyze such data. · Capturing a large amount of clinical data of dynamic nature in static schema may not be feasible, thus, there is a need to port the data to SQL like environments which facilitate the analytics. · In several cases, environmental and spatial factors affect health of patients. Building such contextaware intelligent system is critical to facilitating the decision making. · Web mining of online public health discussion forums where patients voluntarily post information about treatments, adverse drug reactions can also be effectively utilized to provide insights into decision making.