TY - JOUR
T1 - Evolving Rule-Based Systems in two Medical Domains using Genetic Programming
AU - Tsakonas, A.
AU - Dounias, G.
AU - Jantzen, Jan
AU - Axer, H.
AU - Bjerregaard, B.
AU - Keyserlingk, D. G. v.
PY - 2004
Y1 - 2004
N2 - We demonstrate, compare and discuss the application of two genetic programming methodologies for the construction of rule-based systems in two medical domains: the diagnosis of Aphasia's subtypes and the classification of Pap-Smear Test examinations. The first approach consists of a scheme that combines genetic programming and heuristic hierarchical crisp rule-base construction. The second model is composed by a grammar driven genetic programming system for the generation of fuzzy rule-based systems. Results are also compared for their efficiency, accuracy and comprehensibility, to those of a standard entropy based machine learning approach and to those of a standard genetic programming symbolic expression approach. In the diagnosis of subtypes of Aphasia, two models for crisp rule-bases are presented. The first one discriminates between four major types and the second attempts the classification between all common types. A third model consisting of a GP-generated fuzzy rule-based system is tested on the same field. In the classification of Pap-Smear Test examinations, a crisp rule-based system is constructed. Results denote the effectiveness of the proposed systems. Comments and comparisons are made between the proposed methods and previous attempts on the selected fields of application.
AB - We demonstrate, compare and discuss the application of two genetic programming methodologies for the construction of rule-based systems in two medical domains: the diagnosis of Aphasia's subtypes and the classification of Pap-Smear Test examinations. The first approach consists of a scheme that combines genetic programming and heuristic hierarchical crisp rule-base construction. The second model is composed by a grammar driven genetic programming system for the generation of fuzzy rule-based systems. Results are also compared for their efficiency, accuracy and comprehensibility, to those of a standard entropy based machine learning approach and to those of a standard genetic programming symbolic expression approach. In the diagnosis of subtypes of Aphasia, two models for crisp rule-bases are presented. The first one discriminates between four major types and the second attempts the classification between all common types. A third model consisting of a GP-generated fuzzy rule-based system is tested on the same field. In the classification of Pap-Smear Test examinations, a crisp rule-based system is constructed. Results denote the effectiveness of the proposed systems. Comments and comparisons are made between the proposed methods and previous attempts on the selected fields of application.
M3 - Journal article
SN - 0933-3657
VL - 32
SP - 195
EP - 216
JO - Artificial Intelligence in Medicine
JF - Artificial Intelligence in Medicine
IS - 3
ER -