2006 · 172 citations · 7 references
ComputingBiomedical InformaticsOncologyBreast OncologyData MiningMachine LearningClinical Knowledge RepresentationComputational OncologyDimensionality ReductionPredictive Health ModelingPrincipal Component AnalysisBreast Cancer PrognosisClinical Data MiningClinical Knowledge DiscoveryMachine Learning For DiagnosisMachine Learning For HealthcareNetwork-based PrognosticsNeural Network ModelingRadial Basis Function Networks
The study aims to predict breast cancer survivability using data mining techniques. The authors used the SEER public‑use database (151,886 records with 16 fields) and applied Naive Bayes, back‑propagated neural networks, and C4.5 decision trees in multiple experiments. The models achieved performance comparable to existing methods, with the C4.5 decision tree outperforming Naive Bayes and neural networks.
In this paper we present an analysis of the prediction of survivability rate of breast cancer patients using data mining techniques. The data used is the SEER Public-Use Data. The preprocessed data set consists of 151,886 records, which have all the available 16 fields from the SEER database. We have investigated three data mining techniques: the Naive Bayes, the back-propagated neural network, and the C4.5 decision tree algorithms. Several experiments were conducted using these algorithms. The achieved prediction performances are comparable to existing techniques. However, we found out that C4.5 algorithm has a much better performance than the other two techniques.
7