Information Technology Reference
In-Depth Information
later use by the triage team. TriageBot would also give tentative, possible diagnoses
to the triage nurse, along with recommendations for non-physician care.
San Pedro and colleagues [38] proposed a Mobile Decision Support for Triage in
Emergency Departments based on decision support strategies that include the use of
heuristic and fuzzy reasoning that allow the system to support nurse's ability to use
his/her expert judgment and justify his/her decision using natural language.
Finally, Aronsky et al. [1] described an integrated, computerized triage applica-
tion which exchanges information with other information systems, including the ED
patient tracking board, the longitudinal electronic medical record, the computerized
provider order entry, and the medication reconciliation application. The application
includes decision support capabilities such as assessing the patients' acuity level,
age-dependent alerts for vital signs, and clinical reminders.
Research using empirical results from a clinical trial of an emergency DSS with a
decision model based on expert knowledge has shown [18] that there are differences
in how clinician groups of the same specialty, but different level of expertise, elicit
necessary emergency DSS input variables and use these variables in their clinical
decisions.
The following sections will introduce a novel development approach for a Deci-
sion Support System based on Fuzzy Cognitive Maps and will describe, in detail,
how to include actual factors taken into consideration, as well as to present the out-
comes for case studies presented to the emergency room.
27.4
Fuzzy Cognitive Maps Designing and Development
Procedure
Since the ESI instrument categorizes ED patients into 5 mutually exclusive cate-
gories, the type of Fuzzy Cognitive Map that will be used here is the Competitive
Fuzzy Cognitive Map (CFCM) where the possible decision outcomes are mutually
exclusive and compete with each other [14, 15].
Many different approaches have been proposed to develop and construct FCMs
either based only to human experts who are invited to design conceptual structures
that correspond the operation and model of a system or based on available quantita-
tive historical data or both of them [25, 41, 44, 45]. The construction methodology
and the possible implementation of learning algorithm has great importance to suf-
ficiently model any system. Here a new hybrid method for it is proposed developing
Fuzzy Cognitive Map Decision Support Systems (FCM-MDSS) mainly based on a
group of experts who are used to transform their reasoning approach on inferring
decision into an aggregated decision making model. The proposed methodology
extracts the knowledge from the experts and exploits their experience on decision-
making and evaluating diagnosis [44] and it is further complemented with generally
expected bibliographic input.
The proposed approach here is not only based on the human experts, but, also,
it introduces the use of existent widely accepted procedures and bibliographic data,
constituting a hybrid methodology. It is proposed to use the experience and human
