Classification of anemia using Harris hawks optimization method and multivariate adaptive regression spline

Creative Commons License

Yagmur N., DAĞ İ., Temurtas H.

Neural Computing and Applications, cilt.36, sa.11, ss.5653-5672, 2024 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 36 Sayı: 11
  • Basım Tarihi: 2024
  • Doi Numarası: 10.1007/s00521-023-09379-y
  • Dergi Adı: Neural Computing and Applications
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Applied Science & Technology Source, Biotechnology Research Abstracts, Compendex, Computer & Applied Sciences, Index Islamicus, INSPEC, zbMATH
  • Sayfa Sayıları: ss.5653-5672
  • Anahtar Kelimeler: Anemia prediction, Classification, Harris hawks optimization method, Multivariate adaptive regression spline
  • Eskişehir Osmangazi Üniversitesi Adresli: Evet

Özet

Data mining methods are important for the diagnosis and prediction of diseases. Early and accurate diagnosis of patients is vital for their treatment. Various methods have been used in the literature to classify anemia. However, due to the different characteristics of patient datasets, changes in dataset sizes, different parameter numbers and features, and different numbers of patient records, algorithm performances vary according to datasets. In this study, the Harris hawks algorithm (HHA) and the multivariate adaptive regression spline (MARS) were used to classify anemia based on blood data of 1732 patients from the Kaggle database of patients with and without anemia. Six different algorithms were proposed to determine the parameters of the linear anemia approximation, namely multilinear form HHA, multilinear quadratic form HHA, multilinear exponential form HHA, first-order MARS model, second-order MARS model, and the best performing MARS model. The performance of the six proposed algorithms has been analyzed and found to be better than the previous studies in the literature.