A hybrid machine learning feature selection model—HMLFSM to enhance gene classification applied to multiple colon cancers dataset

Aug 5, 2026

Upload by Finn

Colon cancer poses a major global health challenge where early detection is pivotal for improving survival. Conventional approaches such as colonoscopies are invasive and uncomfortable, prompting interest in non-invasive classification using machine learning over genetic data and patient information. High-dimensional gene expression and variable signals limit traditional transductive ML accuracy and increase overfitting. This paper introduces a hybrid feature selection model (HMLFSM) combining Information Gain with Genetic Algorithms and mRMR with Particle Swarm Optimization, tested on multiple datasets, achieving substantial accuracy gains and identifying key discriminative genes through selective feature extraction.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages27

Reading Time1 h 8 min

AccessFree to download

Abstract

Introduction

PLOS ONE OPEN ACCESS Citation: Al-Rajab M, Lu J, Xu Q, Kentour M, Sawsa A, Shuweikeh E, et al. (2023) A hybrid machine learning feature selection model—HMLFSM to enhance gene classification applied to multiple colon cancers dataset. PLoS ONE 18(11): e0286791 . [https://doi.org/10.1371/journal](https://doi.org/10.1371/journal). pone.0286791 Editor: Mohamed Hammad, Menoufia University, EGYPT Received: January 27, 2023 Accepted: May 20, 2023 Published: November 2, 2023 Copyright: © 2023 Al-Rajab et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Data Availability Statement: All relevant data are within the paper and its Supporting Information files. Funding: M. AlRajab, J. Lu, and E. Sheweikeh would like to thank Abu Dhabi University, UAE for the great support (ADU Grant No. 19300568) . [www.adu.ac.ae](www.adu.ac.ae The funders)[ The funders](www.adu.ac.ae The funders) had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. RESEARCH ARTICLE A hybrid machine learning feature selection model—HMLFSM to enhance gene classification applied to multiple colon cancers dataset Murad Al-Rajab1,2 *, Joan Lu2, Qiang Xu2, Mohamed Kentour2, Ahlam Sawsa2,3, Emad Shuweikeh2, Mike Joy4, Ramesh Arasaradnam5 1 College of Engineering, Abu Dhabi University, Abu Dhabi, United Arab Emirates, 2 School of Computing and Engineering, University of Huddersfield, Huddersfield, United Kingdom, 3 Bradford Teaching Hospitals NHS Foundation Trust, Bradford, United Kingdom, 4 University of Warwick, Coventry, United Kingdom, 5 University Hospital Coventry & Warwickshire, Coventry, United Kingdom * [murad.al-rajab@adu.ac.ae](murad.al-rajab@adu.ac.ae) Abstract Colon cancer is a significant global health problem, and early detection is critical for improving survival rates. Traditional detection methods, such as colonoscopies, can be invasive and uncomfortable for patients. Machine Learning (ML) algorithms have emerged as a promising approach for non-invasive colon cancer classification using genetic data or patient demographics and medical history. One approach is to use ML to analyse genetic data, or patient demographics and medical history, to predict the likelihood of colon cancer. However, due to the challenges imposed by variable gene expression and the high dimensionality of cancer-related datasets, traditional transductive ML applications have limited accuracy and risk overfitting. In this paper, we propose a new hybrid feature selection model called HMLFSM–Hybrid Machine Learning Feature Selection Model to improve colon cancer gene classification. We developed a multifilter hybrid model including a two-phase feature selection approach, combining Information Gain (IG) and Genetic Algorithms (GA), and minimum Redundancy Maximum Relevance (mRMR) coupling with Particle Swarm Optimization (PSO) . We critically tested our model on three colon cancer genetic datasets and found that the new framework outperformed other models with significant accuracy improvements (95%, ~97%, and ~94% accuracies for datasets 1, 2, and 3 respectively) . The results show that our approach improves the classification accuracy of colon cancer detection by highlighting important and relevant genes, eliminating irrelevant ones, and revealing the genes that have a direct influence on the classification process. For colon cancer gene analysis, and along with our experiments and literature review, we found that selective input feature extraction prior to feature selection is essential for improving predictive performance. PLOS ONE | [https://doi.org/10.1371/journal.pone.0286791](https://doi.org/10.1371/journal.pone.0286791) November 2, 2023 1 / 27 Competing interests: The authors have declared that no competing

FAQs

Why is colon cancer early detection important in this work?

Early detection is emphasized as critical for improving survival rates. The document contrasts it with the limitations of invasive screening methods such as colonoscopies.

What problem do the authors aim to address with traditional transductive ML?

The authors state that variable gene expression and high dimensionality reduce accuracy and increase the risk of overfitting, which can also cause loss of information needed for feature importance.

How does HMLFSM improve gene classification performance?

HMLFSM uses a multifilter hybrid, two-phase feature selection strategy combining Information Gain with Genetic Algorithms and mRMR coupled with Particle Swarm Optimization. The approach highlights relevant genes, removes irrelevant ones, and relies on selective input feature extraction before feature selection.

Aug 5, 2026

Upload by Finn