Scholarlink

<p>Heart Disease (HD) significantly impacts global health, making its accurate prediction critical for reducing death rates. This paper proposes a novel optimization-based HD prediction system leveraging metaheuristic algorithms. Harris Hawk Optimization (HHO) is employed for optimal feature selection due to its efficiency in high-dimensional datasets, faster convergence, and reduced risk of overfitting, while Particle Swarm Optimization (PSO) optimizes the weights of an Artificial Neural Network (ANN) for its computational efficiency and robust global optimization capabilities. The proposed method is evaluated on the Cleveland and Statlog datasets using metrics such as accuracy, precision, recall, F1-score, and AUC. It achieves 92.45% and 91.51% accuracy for the Cleveland and Statlog datasets, respectively, outperforming existing optimization techniques. Moreover, the proposed method outperforms other feature and weight optimization techniques, showcasing its effectiveness in enhancing HD diagnosis.</p> Graphical Abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Enhancing Heart Disease Diagnosis with Meta-Heuristic Algorithms: A Combined HHO and PSO Approach

  • 期刊论文

  • 发表日期：

    2025年2月21日

查看全文
  • Farzana Begum,
  • J. Arul Valan

摘要

Heart Disease (HD) significantly impacts global health, making its accurate prediction critical for reducing death rates. This paper proposes a novel optimization-based HD prediction system leveraging metaheuristic algorithms. Harris Hawk Optimization (HHO) is employed for optimal feature selection due to its efficiency in high-dimensional datasets, faster convergence, and reduced risk of overfitting, while Particle Swarm Optimization (PSO) optimizes the weights of an Artificial Neural Network (ANN) for its computational efficiency and robust global optimization capabilities. The proposed method is evaluated on the Cleveland and Statlog datasets using metrics such as accuracy, precision, recall, F1-score, and AUC. It achieves 92.45% and 91.51% accuracy for the Cleveland and Statlog datasets, respectively, outperforming existing optimization techniques. Moreover, the proposed method outperforms other feature and weight optimization techniques, showcasing its effectiveness in enhancing HD diagnosis.

Graphical Abstract