Discusses learning roles and causal structures for
capturing patterns and causality relationships. The
authors present their approach for knowledge discovery
from two specific medical databases. First, rules are
learned to represent the interesting patterns of the
data. Second, Bayesian networks are induced to act as
causality relationship models among the attributes. The
Bayesian network learning process is divided into two
phases. In the first phase, a discretization policy is
learned to discretize the continuous variables, and
then Bayesian network structures are induced in the
second phase. The authors employ advanced evolutionary
algorithms such as generic genetic programming,
evolutionary programming, and genetic algorithms to
conduct the learning tasks. From the fracture database,
they discovered knowledge about the patterns of child
fractures. From the scoliosis database, they discovered
knowledge about the classification of scoliosis. They
also found unexpected rules that led to discovery of
errors in the database. These results demonstrate that
the knowledge discovery process can find interesting
knowledge about the data, which can provide novel
clinical knowledge as well as suggest refinements of
the existing knowledge.
%0 Journal Article
%1 wong:2000:dkm
%A Wong, Man Leung
%A Lam, Wai
%A Leung, Kwong Sak
%A Ngan, Po Shun
%A Cheng, Jack C. Y.
%D 2000
%J IEEE Engineering in Medicine and Biology Magazine
%K Bayesian advanced algorithms, causality child classification, clinical continuous database database, databases, discovery, errors evolutionary fracture fractures, genetic knowledge knowledge, learning management medical models, network networks, novel process, programming, relationship scoliosis systems, tasks, variables,
%N 4
%P 45--55
%T Discovering knowledge from medical databases using
evolutionory algorithms
%U http://ieeexplore.ieee.org/iel5/51/18543/00853481.pdf
%V 19
%X Discusses learning roles and causal structures for
capturing patterns and causality relationships. The
authors present their approach for knowledge discovery
from two specific medical databases. First, rules are
learned to represent the interesting patterns of the
data. Second, Bayesian networks are induced to act as
causality relationship models among the attributes. The
Bayesian network learning process is divided into two
phases. In the first phase, a discretization policy is
learned to discretize the continuous variables, and
then Bayesian network structures are induced in the
second phase. The authors employ advanced evolutionary
algorithms such as generic genetic programming,
evolutionary programming, and genetic algorithms to
conduct the learning tasks. From the fracture database,
they discovered knowledge about the patterns of child
fractures. From the scoliosis database, they discovered
knowledge about the classification of scoliosis. They
also found unexpected rules that led to discovery of
errors in the database. These results demonstrate that
the knowledge discovery process can find interesting
knowledge about the data, which can provide novel
clinical knowledge as well as suggest refinements of
the existing knowledge.
@article{wong:2000:dkm,
abstract = {Discusses learning roles and causal structures for
capturing patterns and causality relationships. The
authors present their approach for knowledge discovery
from two specific medical databases. First, rules are
learned to represent the interesting patterns of the
data. Second, Bayesian networks are induced to act as
causality relationship models among the attributes. The
Bayesian network learning process is divided into two
phases. In the first phase, a discretization policy is
learned to discretize the continuous variables, and
then Bayesian network structures are induced in the
second phase. The authors employ advanced evolutionary
algorithms such as generic genetic programming,
evolutionary programming, and genetic algorithms to
conduct the learning tasks. From the fracture database,
they discovered knowledge about the patterns of child
fractures. From the scoliosis database, they discovered
knowledge about the classification of scoliosis. They
also found unexpected rules that led to discovery of
errors in the database. These results demonstrate that
the knowledge discovery process can find interesting
knowledge about the data, which can provide novel
clinical knowledge as well as suggest refinements of
the existing knowledge.},
added-at = {2008-06-19T17:35:00.000+0200},
author = {Wong, Man Leung and Lam, Wai and Leung, Kwong Sak and Ngan, Po Shun and Cheng, Jack C. Y.},
biburl = {https://www.bibsonomy.org/bibtex/256a071c333eb10500364f3eb19a5451d/brazovayeye},
interhash = {47e08e2a3bf1d6901ca68f42d73630ec},
intrahash = {56a071c333eb10500364f3eb19a5451d},
issn = {0739-5175},
journal = {IEEE Engineering in Medicine and Biology Magazine},
keywords = {Bayesian advanced algorithms, causality child classification, clinical continuous database database, databases, discovery, errors evolutionary fracture fractures, genetic knowledge knowledge, learning management medical models, network networks, novel process, programming, relationship scoliosis systems, tasks, variables,},
month = {July-August},
number = 4,
pages = {45--55},
size = {11 pages},
timestamp = {2008-06-19T17:54:23.000+0200},
title = {Discovering knowledge from medical databases using
evolutionory algorithms},
url = {http://ieeexplore.ieee.org/iel5/51/18543/00853481.pdf},
volume = 19,
year = 2000
}