Bf. Bohren et al., EXTRACTING KNOWLEDGE FROM LARGE MEDICAL DATABASES - AN AUTOMATED APPROACH, Computers and biomedical research, 28(3), 1995, pp. 191-210
Tools which can uncover patterns in patients' records and then make pr
edictions based on that knowledge are and will continue to be high pri
ority in many medical informatics groups. These tools are impacting th
e performance of outcome studies by discovering patterns which can the
n be verified with standard statistical tools. This paper demonstrates
INC2.5, a general classification system, as a tool for assisting phys
icians in the decision making process. INC2.5 gathers information from
patient records and builds a decision tree which is used to assist ph
ysicians in predicting the outcome of new patients. The decision tree
will also reveal any patterns which the system found in the data. Succ
essful results of such a system can be used to enhance outcome studies
as well as to spread clinical information to areas with fewer resourc
es. (C) 1995 Academic Press, Inc.