In every aspect of patient treatment, questions arise for
which a search of the published medical evidence is appropriate, as it
is very likely that the answer has already been found from the work of
other clinicians. For example:
Q: In a child with asthma, do increased
doses of inhaled corticosteroids lead to a decrease in growth?
A: Growth was significantly slower in
the group receiving higher dose inhaled steroids (3.6 cm, 95%CI 3.0 to
4.2 with double dose beclometasone v 5.1 cm, 95% CI 4.5 to 5.7 with
salmeterol v 4.5 cm, 95% CI 3.8 to 5.2 with placebo).
(Stuart Barton, Clinical Evidence, BMJ Publishing Group, London 2002.)
Studies have shown that searching in the literature can help
clinicians in answering questions generated in patient treatment.
It has also been found that if high-quality evidence is available in
this way at the point of care -- for example, the patient's bedside --
clinicians will use it in their decision-making, and it frequently
results in additional or changed decisions. The practice
of using the current best evidence to help clinicians in making
decisions on the treatment of patients is called Evidence-Based
The EPoCare project aims to provide fast access for clinicians to EBM
resources at the point of care, that is, while seeing a patient either
in an office or on clinical rounds in a hospital. Clinicians will be
able to query resources that summarize and appraise evidence about the
diagnosis, treatment, prognosis, etiology and prevalence of medical
conditions. In order to make it available at the point of care, the
question-answering system is accessible using hand-held computers.
Questions are answered based on the semantics of the domain,
evidence-based medicine. Both the questions and the EBM sources from
which the answers are drawn are understood in terms of a lightweight
ontology of evidence-based medicine. This ontology constitutes a model
of the sorts of things that exist in the domain and the sorts of
relationships that can hold among them. The fact that the system has
such a common understanding of the queries and information sources is
the key to providing accurate answers.
The Knowledge Management Lab's research on answering clinical questions
is part of an interdisciplinary collaboration that involves research in
several disciplines. Project members in Industrial Engineering and
Cognitive Psychology are investigating the design of the system through
a user-centred design process, in which requirements are elicited from
end users who are also involved in the evaluation of prototypes.
Project members in Database Management provide support in dealing with
data sources in XML format. And project members in Health Informatics
will test the influence of the system on clinical decision-making and