Self-organizing discovery, recognition, and prediction of hemodynamic patterns in the intensive care unit /

(ANNS) is proposed to automate the discovery, recognition,

Bibliographic Details
Main Author: Spencer, Ronald Glen
Format: Thesis eBook
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1994.
Subjects:
Online Access:Link to OAKTrust copy
Description
Summary:(ANNS) is proposed to automate the discovery, recognition,
and prediction of such hemodynarmic patterns in real-time and
arrangement of self-organizing artificial neural networks
clinician is left to manually sift through an excess of data
environments because they are very trainable and have a
for determining immediate dangers, it does not provide much
hemodynamic patterns. In a typical ICU a variety of
In order to properly care for critically ill patients in the
in the interest of generating information. In this study, an
information about temporal patterns. As a result, the
information beyond that provided by instantaneous high/low
intensive care unit (ICU), clinicians must be aware of
intermittently in an attempt to provide clinicians with the
knowledge, thus reducing the need for a priori knowledge in
limit checking. While instantaneous limit checking is useful
most accurate and precise data needed for recognizing such
patterns. However, the data are disjointed, yielding little
physiologic measurements are made continuously and
presented.
suited for pattern recognition and prediction in a data-rich
symbolic form. Results from actual clinical data are
tendency to discover their own internal representations of
ultimately lessen the burden on clinicians. ANNs are well
Item Description:"Major subject: Bioengineering".
Vita.
Physical Description:ix, 77 leaves : illustrations ; 28 cm.
Also available online.
Bibliography:Includes bibliographical references.