Multi-source Integrated Platform for Answering Clinical Questions
What obstacles deter physicians from pursuing answers to their clinical questions? In a series of studies,
Ely and colleagues (Ely et al., 2005) investigate the obstacles to answering questions posed by healthcare
professionals. They conclude that physician-related obstacles include "the failure to recognize an information
need, the decision to pursue questions only when answers are thought to exist, the preference for the most
convenient resource rather than the most appropriate one and the tendency to formulate questions that are
difficult to answer with general resources." Resource-related obstacles include "the excessive time and effort
required to find answers in existing resources, the lack of access to information resources, the difficulty
navigating the overwhelming body of literature to find the specific information that is needed, the inability
of literature search technology to directly answer clinical questions, and the lack of evidence that addresses
questions arising in practice."
The Center for Computational Language and Education Research (CLEAR) has teamed up with Mayo Clinic to pursue the shared
goal of creating a Multi-source Integrated Platform for Answering Clinical Questions (MIPACQ) intended to remove
or mitigate many of the preceding obstacles impeding physicians' pursuit of answers to clinical questions.
MIPACQ aims to provide concise summary responses to clinical questions by accessing multiple data sources - the integrated
patient's electronic medical record, a physician-vetted knowledge of the most frequently asked questions, the World
Wide Web and the scientific literature in MedLine - and by focusing on the semantic processing of the language
through a unified semantic representation thus "understanding" the question and the meaning of related narratives.
This focus on semantic representation and understanding of the clinical domain and the integration of multiple
complementary data sources sets our effort apart from prior work. Prior research focused almost exclusively on using
the keyword searches (for example, Demner-Fushman and Lin, 2006). Semantically-based question processing and information
extraction from multiple data sources will fuse complementary information for more comprehensive and relevant fact
and event retrieval.
MIPACQ establishes another use for the patient electronic medical record (EMR) as an information-rich source for a variety of
applications. This further emphasizes the inherent importance and significance of EMR systems, which are currently viewed
by most hospital administrators as serving only the important but limited function of billing.
This work has the potential to facilitate significant improvement in and impact on healthcare delivery, as it addresses
well-documented and studied health care professional needs (Ely et al., 2005). We aim to provide a unified multi-source
solution for semantic retrieval, analysis and summarization of relevant information at the point of care or the lab.
As such, the proposed clinical QA system has the potential to play a vital and important decision-support role for the
physician or the clinical/biomedical investigator.