Scholarlink

This paper introduces a novel hybrid data mining model aimed at early detection of lung cancer, employing supervised feature selection methods. Experimental results indicate that the Random Tree algorithm attains the highest accuracy (98.4%) along with the lowest error rate (1.62%). Additionally, according to Standardized Coefficients analysis, alcohol consumption emerges as the most significant factor contributing to lung cancer risk.

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

A Hybrid Data Mining Model for Early Detection of Lung Cancer Utilizing Supervised Feature Extraction

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Inssaf El Guabassi,
  • Zakaria Bousalem,
  • Rim Marah,
  • Abdellatif Haj

摘要

This paper introduces a novel hybrid data mining model aimed at early detection of lung cancer, employing supervised feature selection methods. Experimental results indicate that the Random Tree algorithm attains the highest accuracy (98.4%) along with the lowest error rate (1.62%). Additionally, according to Standardized Coefficients analysis, alcohol consumption emerges as the most significant factor contributing to lung cancer risk.