Document Type
Thesis
Date of Award
10-31-1991
Degree Name
Master of Science in Electrical Engineering - (M.S.)
Department
Electrical Engineering
First Advisor
Peter Engler
Second Advisor
Stanley Martin Dunn
Third Advisor
Stanley S. Reisman
Abstract
The intriguing words for the nineteen nineties are "Expert Systems", and "Artificial Intelligence". To a layman these terms conjure up thoughts of spaceships and futuristic beings. In reality they exemplify man's capability to harness technology.
Expert systems are computer software programs that make use of previously accumulated knowledge to assist in solving complex problems.
In recent years the practice of medicine has changed dramatically from a fundamentally individually deductive approach to an Artificial Intelligence based science. The modern physician no longer draws conclusions simply by examining the patient. Today the physician employs sophisticated computer based diagnostic tools to generate a diagnosis.
Clearly, Expert Systems are a means of minimizing a high degree of uncertainty. Margins of error are greatly reduced so that the majority of diagnostic conclusions have a greater percentage of accuracy. Bayesian theory is commonly applied to generate conditional probabilities which take into account the frequency of occurrence of events in specific domains. Bayesian Theory has been employed in the development of a new Expert System called CANMOL.
In theory CANMOL could be applied as a diagnostic tool to a broad range of medical applications. By altering the knowledge base the application would change, while the program itself would remain consistent.
For the purpose of this thesis CANMOL will be employed to: 1) predict the occurrence of Breast Cancer, and 2) the probability of complications arising from extraction or retention of the third molar. CANMOL's flexibility is exhibited by its application to two distinct and unrelated areas within the sphere of medicine.
Recommended Citation
Hemani, Kulin, "CANMOL : expert system in medicine" (1991). Theses. 2494.
https://digitalcommons.njit.edu/theses/2494