Medical data analysis using self-organizing data mining technologies

摘要: Three self-organizing data mining technologies that employ complementary descriptive languages - parametric regression models (GMDH neural networks), fuzzy rules (self-organizing rule induction), and similarity (analog complexing based clustering classification) are applied to generate diagnosis of different levels heart disease. The classification results show an accuracy over 95% in average. Due the strong knowledge extraction capabilities used a nucleus 4 most relevant variables is identified. obtained both identified also important for cost reduction considerations.