Scholarlink

<p>A timely diagnosis is crucial for effective treatment of illnesses and thyroid disease is a significant chronic endocrine issue that poses a substantial health hazard. Thyroid diseases develop when the thyroid gland malfunctions and causes the secretion of hormones that regulate the metabolism in humans. The conditions known as hyperthyroidism and hypothyroidism are common thyroid ailments that pose major health hazards. This article proposes a novel hybrid algorithm that combines the Cuttlefish Optimization Algorithm (CFA) and Adaptive Simulated Annealing (ASA) to select the best features for finding thyroid disease. The study uses machine-learning models for classification, to assess algorithm performance, we use performance measures including accuracy, F1-score, precision, recall and standard deviation. We applied preprocessing steps that included feature normalization, handling missing values and categorical encoding.The research demonstrates promising results with an accuracy of 99.01% and an F1-score of 94.98% which showcases the robustness of the proposed algorithms on a benchmark UCI Thyroid Disease dataset and outperforms baseline models CFA, ASA and Particle Swarm Optimization (PSO) in all key metrics The integration of machine learning and nature-inspired optimization significantly enhances the diagnostic capabilities of healthcare systems and enables prompt diagnosis and treatment planning for thyroid disorders. The findings hold potential to improve clinical decision-making processes. This study advances medical diagnostics by combining machine learning algorithms with nature-inspired optimization techniques to detect thyroid illnesses in their early stages.</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

CFA–ASA: An Adaptive Hybrid Feature Selection Approach for Thyroid Disease Prediction

  • 期刊论文

  • 发表日期：

    2025年8月29日

查看全文
  • Kapil Shrivastava,
  • Munish Khanna

摘要

A timely diagnosis is crucial for effective treatment of illnesses and thyroid disease is a significant chronic endocrine issue that poses a substantial health hazard. Thyroid diseases develop when the thyroid gland malfunctions and causes the secretion of hormones that regulate the metabolism in humans. The conditions known as hyperthyroidism and hypothyroidism are common thyroid ailments that pose major health hazards. This article proposes a novel hybrid algorithm that combines the Cuttlefish Optimization Algorithm (CFA) and Adaptive Simulated Annealing (ASA) to select the best features for finding thyroid disease. The study uses machine-learning models for classification, to assess algorithm performance, we use performance measures including accuracy, F1-score, precision, recall and standard deviation. We applied preprocessing steps that included feature normalization, handling missing values and categorical encoding.The research demonstrates promising results with an accuracy of 99.01% and an F1-score of 94.98% which showcases the robustness of the proposed algorithms on a benchmark UCI Thyroid Disease dataset and outperforms baseline models CFA, ASA and Particle Swarm Optimization (PSO) in all key metrics The integration of machine learning and nature-inspired optimization significantly enhances the diagnostic capabilities of healthcare systems and enables prompt diagnosis and treatment planning for thyroid disorders. The findings hold potential to improve clinical decision-making processes. This study advances medical diagnostics by combining machine learning algorithms with nature-inspired optimization techniques to detect thyroid illnesses in their early stages.