Diagnosis of heart disease using an intelligent method: A hybrid ANN – GA approach

Akgül M., Sönmez Ö. E., Özcan T.

International Conference on Intelligent and Fuzzy Systems, INFUS 2019, İstanbul, Türkiye, 23 - 25 Temmuz 2019, cilt.1029, ss.1250-1257, (Tam Metin Bildiri) identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 1029
  • Doi Numarası: 10.1007/978-3-030-23756-1_147
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Sayfa Sayıları: ss.1250-1257
  • İstanbul Üniversitesi-Cerrahpaşa Adresli: Hayır

Özet

© 2020, Springer Nature Switzerland AG.Heart disease is the most important public health problem for many countries. Early diagnosis of heart disease is extremely crucial for the survival of the patient. At this point, classification algorithms are widely used for medical diagnosis. In this study, firstly, artificial neural network (ANN) with default parameters is used to diagnose heart disease. Then, a hybrid approach, combining artificial neural network (ANN) and genetic algorithm (GA), is proposed to improve classification accuracy. Finally, the effectiveness of the proposed approach is illustrated with ‘Cleveland’ dataset taken from UCI machine learning repository. Experimental results show that the proposed hybrid ANN - GA approach outperforms Naive Bayes, K- Nearest Neighbor and C4.5 algorithms in terms of accuracy rate, precision, recall and F-measure.