TY - GEN
T1 - Identification of cancer diagnosis estimation models using evolutionary algorithms
T2 - 13th Annual Genetic and Evolutionary Computation Conference, GECCO'11
AU - Winkler, Stephan
AU - Affenzeller, Michael
AU - Jacak, Witold
AU - Stekel, Herbert
N1 - Copyright:
Copyright 2011 Elsevier B.V., All rights reserved.
PY - 2011
Y1 - 2011
N2 - In this paper we present results of empirical research work done on the data based identification of estimation models for cancer diagnoses: Based on patients' data records including standard blood parameters, tumor markers, and information about the diagnosis of tumors we have trained mathematical models for estimating cancer diagnoses. Several data based modeling approaches implemented in HeuristicLab have been applied for identifying estimators for selected cancer diagnoses: Linear regression, k-nearest neighbor learning, artificial neural networks, and support vector machines (all optimized using evolutionary algorithms) as well as genetic programming. The investigated diagnoses of breast cancer, melanoma, and respiratory system cancer can be estimated correctly in up to 81%, 74%, and 91% of the analyzed test cases, respectively; without tumor markers up to 75%, 74%, and 87% of the test samples are correctly estimated, respectively.
AB - In this paper we present results of empirical research work done on the data based identification of estimation models for cancer diagnoses: Based on patients' data records including standard blood parameters, tumor markers, and information about the diagnosis of tumors we have trained mathematical models for estimating cancer diagnoses. Several data based modeling approaches implemented in HeuristicLab have been applied for identifying estimators for selected cancer diagnoses: Linear regression, k-nearest neighbor learning, artificial neural networks, and support vector machines (all optimized using evolutionary algorithms) as well as genetic programming. The investigated diagnoses of breast cancer, melanoma, and respiratory system cancer can be estimated correctly in up to 81%, 74%, and 91% of the analyzed test cases, respectively; without tumor markers up to 75%, 74%, and 87% of the test samples are correctly estimated, respectively.
KW - cancer diagnosis estimation
KW - data mining
KW - machine learning
KW - statistical analysis
KW - tumor marker data
UR - http://www.scopus.com/inward/record.url?scp=80051922252&partnerID=8YFLogxK
U2 - 10.1145/2001858.2002040
DO - 10.1145/2001858.2002040
M3 - Conference contribution
SN - 9781450306904
T3 - Genetic and Evolutionary Computation Conference, GECCO'11 - Companion Publication
SP - 503
EP - 510
BT - Genetic and Evolutionary Computation Conference, GECCO'11 - Companion Publication
PB - ACM Sigevo
Y2 - 12 July 2011 through 16 July 2011
ER -
