HOW DIFFERENT FEATURE SELECTION METHODS AFFECT THE PRECISION OF BREAST CANCER PREDICTION MACHINE LEARNING MODELS - A COMPARATIVE STUDY

Aug 4, 2026

Breast cancer remains a critical challenge in developing nations, where early identification strongly influences treatment success. Combining standard diagnostic information with machine learning enables risk evaluation, yet many dataset attributes do not contribute meaningfully to prediction, making feature selection essential for isolating relevant variables. This research compares how Mutual Information, Spearman correlation, and F-test feature selection impact the accuracy of major machine learning models on the public WDBC dataset from UCI. Logistic Regression and Neural Networks show the strongest accuracy and performance across multiple metrics when feature selection is applied.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Abstract

Introduction

Related Works

20(2): S2: 800-809, 2025 [www.thebioscan.com](www.thebioscan.com) HOW DIFFERENT FEATURE SELECTION METHODS AFFECT THE PRECISION OF BREAST CANCER PREDICTION MACHINE LEARNING MODELS: A COMPARATIVE STUDY. Ms. Khamrunissa Hussain1,2, Prof. Narendra Kumar3, Dr. Sudheer Kumar Sharma4 1Research Scholar, NIMS University, India 2Lecturer, Ibn Sina National College for Medical Studies, Jeddah, Saudi Arabia 3Professor, Department of Applied Sciences, NIMS University, Jaipur, India 4Department of Mathematics, NIMS University, Jaipur, India DOI: 10.63001/tbs.2025.v20.i02.S2.pp800-809 KEYWORDS Breast Cancer Diagnostic Dataset, Feature Selection, Machine Learning, Breast Cancer. Received on: 12-04-2025 Accepted on: 15-05-2025 Published on: 21-06-2025 ABSTRACT Breast cancer is common in developing nations, the early identification of breast cancer is critical for successful treatment. When combined with standard diagnostic data, machine learning techniques can be used to evaluate the risk of acquiring breast cancer. While cancer datasets contain a wealth of patient information, not all data points are useful for predicting cancer outcomes, underscoring the importance of feature selection methods in identifying relevant data. Numerous studies in this domain have sought to predict various types of breast tumors, as accurate diagnosis is essential for effective breast cancer treatment. The aim of this research is to compare how various feature selection techniques affect the accuracy of different machine learning algorithms currently in use. K-Nearest Neighbors (KNN), Naive Bayes (NB), Decision Trees (DT), Support Vector Machines (SVM), Logistic Regression (LR), Neural Networks (NN), Random Forest (RF), and Naive Bayes (NB) are the seven machine learning methods being assessed in this study. Mutual Information (MI), Spearman Correlation Coefficient, and F-test Feature Selection are among the feature selection methods examined. The dataset by Wisconsin Diagnostic Breast Cancer (WDBC) is made accessible to the public via the UCI Repository, is used in the studies. According to the results, both the Logistic Regression and Neural Network algorithms outperform other models in terms of accuracy and performance across a wide range of metrics when feature selection is used. INTRODUCTION Cancer is among the most lethal illnesses globally. The newest data on breast cancer cases were released in 2023 (Zhou et al., 2024), counting eleven different types of cancer, notably breast cancer in women. About 31% of females of the world are suffering from breast cancer, which makes it the most prevalent kind of malignancy. It ranks sixth globally in terms of overall cancer mortality and is thought to be the main reason of cancerrelated deaths amid womenfolk. It killed 685,000 people in 2020, and the World Health Organization (WHO) estimates that it will kill over 963,000 people in 2021, surpassing lung cancer with about 2.3 million new cases (Bray et al., 2024) . The incidence of these types of instances of cancer was 25%, whereas the mortality rate among women globally was 17% (Zhou et al., 2024) . The atypical proliferation of breast cells is termed a tumor, which is classified into two categories: malignant and benign. The former is malignant, whereas the latter is benign. Although the etiology of carcinoma of the breast in women remains poorly understood, various factors have been identified as potential contributors to the disease, including familial history, intrauterine environmental issues, adolescent exposures, complications during pregnancy, genetic mutations, alcohol and tobacco use, and advanced maternal age, particularly in developing nations (Uddin et al., 2023) . Therefore, it's critical to regularly contact health professionals for early identification, treatment plan, and a precise clinical evaluation in order to reduce the occurrence of breast cancer and prevent deaths among women. However, incorrect dia

FAQs

Which feature selection methods are evaluated in the study?

The study examines Mutual Information (MI), Spearman Correlation Coefficient, and F-test feature selection methods.

Which machine learning models are compared for breast cancer prediction?

The comparison includes K-Nearest Neighbors (KNN), Naive Bayes (NB), Decision Trees (DT), Support Vector Machines (SVM), Logistic Regression (LR), Neural Networks (NN), and Random Forest (RF).

What dataset is used and what is the main goal of the research?

Experiments use the Wisconsin Diagnostic Breast Cancer (WDBC) dataset from the UCI Repository. The goal is to determine how different feature selection techniques affect predictive accuracy across multiple machine learning algorithms.

Aug 4, 2026

Upload by Evangeline