Association and Classification Data Mining Algorithms Comparison over Medical Datasets

Autores/as

  • Bruno Fernandes Chimieski Pontifical Catholic University of Rio Grande do Sul
  • Rubem Dutra Ribeiro Fagundes Pontifical Catholic University of Rio Grande do Sul

Palabras clave:

Data Mining, Classification, Association

Resumen

Objectives: Compare Data Mining algorithms related to Classification and Association tasks over medical datasets about dermatology, vertebral column and breast cancer patients, analyzing which is the best one over each of these datasets. Methods: The classification algorithms are ran over these datasets and compared using precision, F-measure, ROC curve and Kappa performance metrics. For associaton task, the Apriori algorithm is ran to get a significant number of rules with confidence above 90%. Results: For diagnostics prediction about breast cancer and dermatology issues, the best classification algorithm was BayesNet and for vertebral column was the Logistic Model Tree. For association task, were extracted 100 knowledge rules for breast cancer and dermatology issues with confidence higher than 90% while for vertebral column were found 18 with same confidence. Conclusion: The comparison was useful to prove the possibility of using Data Mining algorithms to help Medicine decision engine with good precision.

Biografía del autor/a

Bruno Fernandes Chimieski, Pontifical Catholic University of Rio Grande do Sul

Graduated in Computer Engineering at PUCRS in 2009/2 and student of master degree course in Electrical Engineering also at PUCRS.

Interesting areas in Mobile applications and Artificial Intelligence.

Rubem Dutra Ribeiro Fagundes, Pontifical Catholic University of Rio Grande do Sul

Possui graduação em Engenharia Elétrica pela Pontifícia Universidade Católica do Rio Grande do Sul (1989), Mestrado em Engenharia Elétrica pela Universidade de São Paulo (1993) e Doutorado em Engenharia Elétrica pela Universidade de São Paulo (1998).

Descargas

Publicado

2013-06-30

Cómo citar

Chimieski, B. F., & Fagundes, R. D. R. (2013). Association and Classification Data Mining Algorithms Comparison over Medical Datasets. Journal of Health Informatics, 5(2). Recuperado a partir de https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/226

Número

Vol. 5 Núm. 2 (2013)

Sección

Artículo Original

Licencia

La sumisión de un artículo a el Journal of Health Informatics es entendida como exclusiva y que no esta siendo considerado para publicación en otro periódico. La permisión de los autores para la publicación de su artículo en lo JHI implica en la exclusiva autorización concedida a los editores para su inclusión en la revista. Al someter un artículo, a lo autor será solicitada la permisión electrónica de una Nota de Copyright. Una mensaje electrónica será enviada a lo autor correspondiente confirmando el recibo del manuscrito y lo aceite de la Nota de Copyright.