Scholarlink

<p>Cardiovascular disease (CVD) continues to pose a significant global health challenge. This study presents an advanced diagnostic approach that combines Honey Badger Optimization for feature selection with a modified deep learning model for accurate classification of CVD. For clinical data preprocessing, the method applies min–max scaling, followed by feature selection using the Honey Badger Optimization (HBO) algorithm. A Deep Learning Modified Neural Network (DLMNN) is then used for effective CVD classification. To further enhance model performance, hyperparameter tuning is conducted using Bayesian optimization. By focusing on essential aspects such as feature selection and hyperparameter adjustment, the model addresses the challenges posed by increasingly large and complex healthcare datasets. The combination of HBO and DLMNN offers a novel and efficient approach for accurate and timely CVD diagnosis. Experimental results on benchmark clinical datasets show that the proposed model achieves significant improvements in classification accuracy compared to existing methods. This research highlights the potential of the proposed approach to improve diagnostic precision and deepen insights into key feature relationships within cardiovascular healthcare.</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

Automated Cardiovascular Disease Diagnosis using Honey Badger Optimization with Modified Deep Learning Model

  • 期刊论文

  • 发表日期：

    2025年9月21日

查看全文
  • Allam Pranitha Reddy,
  • P. Eben Sophia,
  • S. Stewart Kirubakaran

摘要

Cardiovascular disease (CVD) continues to pose a significant global health challenge. This study presents an advanced diagnostic approach that combines Honey Badger Optimization for feature selection with a modified deep learning model for accurate classification of CVD. For clinical data preprocessing, the method applies min–max scaling, followed by feature selection using the Honey Badger Optimization (HBO) algorithm. A Deep Learning Modified Neural Network (DLMNN) is then used for effective CVD classification. To further enhance model performance, hyperparameter tuning is conducted using Bayesian optimization. By focusing on essential aspects such as feature selection and hyperparameter adjustment, the model addresses the challenges posed by increasingly large and complex healthcare datasets. The combination of HBO and DLMNN offers a novel and efficient approach for accurate and timely CVD diagnosis. Experimental results on benchmark clinical datasets show that the proposed model achieves significant improvements in classification accuracy compared to existing methods. This research highlights the potential of the proposed approach to improve diagnostic precision and deepen insights into key feature relationships within cardiovascular healthcare.