Download PDFOpen PDF in browser

Comparative Analysis of Hybrid Feature Selection Methods in Lung Cancer Detection

EasyChair Preprint 12670

8 pagesDate: March 21, 2024

Abstract

Lung cancer is a significant global health concern, and early detection plays a crucial role in improving patient outcomes. Machine learning techniques have shown promise in aiding lung cancer detection, but the selection of informative features remains a challenge. In this study, we present a comparative analysis of hybrid feature selection methods in the context of lung cancer detection.

The objective of this research is to investigate the effectiveness of hybrid feature selection techniques in improving the performance of lung cancer detection models. We compare the performance of individual feature selection methods, such as filter, wrapper, and embedded methods, and evaluate their combination strategies to form hybrid approaches.

Our comparative analysis employs a comprehensive framework that includes the selection of feature selection methods, criteria for evaluation, and appropriate data preprocessing. We utilize a diverse dataset comprising medical imaging and clinical data related to lung cancer.

The results of our study demonstrate the performance comparison of individual feature selection methods, highlighting their strengths and limitations. Furthermore, we evaluate the hybrid feature selection methods by considering their ability to enhance lung cancer detection accuracy, sensitivity, specificity, and overall model performance.

The findings of this study provide valuable insights into the effectiveness of hybrid feature selection methods in the context of lung cancer detection. We discuss the implications of our results for future research and clinical applications. Additionally, we identify the strengths and limitations of hybrid approaches, enabling researchers and practitioners to make informed decisions regarding the selection and utilization of feature selection techniques in lung cancer detection.

Keyphrases: Lung Cancer, Machine Learning Techniques, lung cancer treatment technologies

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:12670,
  author    = {Emmanuel Idowu and Axel Egon and Lucas Doris},
  title     = {Comparative Analysis of Hybrid Feature Selection Methods in Lung Cancer Detection},
  howpublished = {EasyChair Preprint 12670},
  year      = {EasyChair, 2024}}
Download PDFOpen PDF in browser