C4.5: programs for machine learning
C4.5: programs for machine learning
Machine Learning
IWLCS '01 Revised Papers from the 4th International Workshop on Advances in Learning Classifier Systems
Classifier fitness based on accuracy
Evolutionary Computation
Post-processing clustering to reduce XCS variability
GECCO '05 Proceedings of the 7th annual workshop on Genetic and evolutionary computation
Hypothesis testing with classifier systems for rule-based risk prediction
EvoBIO'07 Proceedings of the 5th European conference on Evolutionary computation, machine learning and data mining in bioinformatics
The subsumption mechanism for XCS using code fragmented conditions
Proceedings of the 15th annual conference companion on Genetic and evolutionary computation
| Hi-index | 0.00 |
In medical research, being able to justify decisions is generally as important as taking the right ones. Interpretability is then one of the chief characteristics a learning algorithm must have, in order to be successfully applied to a medical data set. Other important features are seamless treatment of different data types, and ability to cope well with missing values. XCS and decision trees both appear to have this desirable characteristics; we compared them on a data set regarding Head and neck squamous cell carcinoma (HNSCC). This kind of oral cancer already been found to be associated with smoking and alcohol drinking habits. However the individual risk could be modified by genetic polymorphisms of enzymes involved in the metabolism of tobacco carcinogens and in the DNA repair mechanisms. To study this relationship, the data set comprised demographic and life-style (age, gender, smoke and alcohol), and genetic data (the individual genotype of 11 polymorphic genes), with the information on 124 HNSCC patients and 231 healthy controls. Results with both algorithms are presented and analyzed.