Information Technology Reference
In-Depth Information
several studies showing the effectiveness of these systems in clinical practice in terms
of improving the quality of care, the safety, and the efficiency. One such example is a
1998 computer-based clinical reminder system showing evidence that a particular
clinical act - discussing advance directives with a patient - was significantly better
performed with the clinical reminders under evaluation than without them. More
generally prescription decision-support systems (PDSS) and clinical reminder sys-
tems, often based on clinical guidelines implementation, have consistently shown
clinical outcomes in several studies. However clinical outcomes are rarely measured,
while process variables and user satisfaction are often measured. Obviously computer
system intrinsic measures are always reported.
The successful development and deployment of expert systems also called knowl-
edge-based systems in medicine gave tremendous incentive to the researchers to ex-
plore this field further. The brittleness of expert systems and the enormous effort
involved in the development and maintenance of knowledge bases prompted re-
searchers to look for other approaches. Computational intelligence approaches based
on neural networks, fuzzy, logic, case based reasoning, evolutionary computation and
the like, filled this perceived need by adding a new dimension to our quest for the
application of these techniques in healthcare.
The success of computational intelligence in the healthcare is explained by the shift
of focus from centering the system success on the computational performance versus
the application domain performance. Indeed successful systems provide a practical
solution to a specific healthcare or health research problem. The systems presenting
the largest impact, such as the clinical reminders, do not have to represent a challeng-
ing conceptual or technical difficulty, but they have to fit perfectly well the clinical
domain in which they are embedded - they are application domain driven - versus
artificial intelligence driven.
The main purpose of this topic is to bring together, under one cover, some of the
important developments in the use of computational intelligence to address the chal-
lenging problems in the field of healthcare.
2 Chapters Included in the Topic
This topic is divided into four parts. The first part includes one chapter. This chapter
introduces the topic and sets a scene related to the advances in computational intelli-
gence in healthcare.
The second part of the topic includes five chapters on Artificial Agents in health-
care. Chapter 2 in the topic is on Clinical Semantics. It presents the discussion on a
flexible and evolving clinical practice supported by open clinical agents for both
clinical professionals and patients capable of learning at a human abstraction level.
Chapter 3 presents the practical applications of agents in healthcare. The challenges
and the future research directions are discussed. Chapter 4 presents three cases regard-
ing the applications of agents in healthcare. The first one is related to the gathering of
patient record. The second application involves the retrievial of partial information
from an emergency scene. The final application is related to the analysis of the Mo-
bile Agent Electronic Triage Tag System. Chapter 5 is on a joint Bayesian framework
for MR Brain scan tissue and structure segmentation based on distributed Markovian
Search WWH ::
Custom Search