DESIGN AND DEVELOPMENT OF A HYBRID EVOLUTIONARY METHOD WITH A SPECIAL SELECTION OF ARTIFICIAL IMMUNE SYSTEM FOR STROKE PREDICTION: A BALANCING APPROACH


Creative Commons License

Celikbas S., ORMAN Z., AKGÜNDOĞDU A.

COMPUTING AND INFORMATICS, vol.44, no.5, pp.1101-1122, 2025 (SCI-Expanded, Scopus) identifier identifier

  • Publication Type: Article / Article
  • Volume: 44 Issue: 5
  • Publication Date: 2025
  • Doi Number: 10.31577/cai_2025_5_1101
  • Journal Name: COMPUTING AND INFORMATICS
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, zbMATH
  • Page Numbers: pp.1101-1122
  • Istanbul University Affiliated: No

Abstract

A stroke is a serious neurological condition that occurs due to either blockages or bleeding in the brain, which can lead to death or long-term disability. This study aims to enhance the accuracy of disease diagnosis in imbalanced stroke patient datasets. The model incorporates an artificial immune system algorithm, whose parameters are fine-tuned using the Firefly algorithm to ensure both stability and balanced data. To enhance the performance of the underrepresented class, the One-Sided Selection method is employed. The model's effectiveness was tested in two separate experiments: one utilizing all available features and the other apply-ing the Artificial Bee Colony (ABC) algorithm to select the most relevant features. The models were trained using six different classification algorithms: CatBoost, Light Gradient Boosting Machine (LightGBM), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and Logistic Re-gression (LR). The results were presented using performance metrics. When trained using all features, the model achieved an accuracy of 93%, specificity of 93%, and sensitivity of 80%. When trained using the best features selected by the ABC algo-rithm, the model achieved an accuracy of 93%, specificity of 93%, and sensitivity of 82%. Compared to previous studies, the proposed model was effective in both experiments.