Advancing breast cancer prediction - machine learning, data balancing, and ant colony optimization

Aug 5, 2026

Upload by Levi

Breast cancer represents a major global health burden, with the World Health Organization reporting millions of new cases annually. This study develops and compares multiple machine learning models for breast cancer prediction by combining data preprocessing, data balancing, and feature selection. Experiments on the Coimbra dataset (116 records, 10 medical attributes) achieve strong classification performance, with 89.74% accuracy and 89.68% AUC-ROC. Results demonstrate the potential of the proposed pipeline to support earlier detection and more effective clinical decision-making.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

Article Info

Abstract

Introduction

Related Work

Advancing breast cancer prediction: machine learning, data balancing, and ant colony optimization Abd Allah Aouragh1, Mohamed Bahaj1, Fouad Toufik2 1MIET Laboratory, Faculty of Sciences and Techniques, Hassan 1st University, Settat, Morocco 2Computer Sciences Laboratory, Higher School of Technology, Mohammed V University, Rabat, Morocco Article history: Received Feb 10, 2024 Revised Jun 8, 2024 Accepted Jun 26, 2024 Keywords: Adaptive synthetic sampling Ant colony optimization Breast cancer Machine learning Synthetic minority oversampling technique Corresponding Author: Breast cancer constitutes a significant threat to women's health worldwide. The World Health Organization (WHO) reports around 2.3 million new cases each year, making this disease the primary reason for cancer-related fatalities among women. In light of this alarming situation, developing innovative tools for early detection and optimal treatment is imperative, as it directly addresses the pressing need to enhance our capabilities in the quest to overcome breast cancer. This study fits in with this approach, introducing a comparative assessment of multiple machine learning algorithms and integrating data preprocessing, data balancing and feature selection techniques. The studied Coimbra dataset, composed of 116 records and including 10 medical characteristics, exhibited promising performance in all classification metrics, reaching an accuracy of 89.74%, and an area under the receiver operating characteristic curve (AUC-ROC) of 89.68% . These findings highlight the significant potential of our approaches to improve breast cancer treatment and detection systems, providing health practitioners with more efficient resources. This is an open access article under the CC BY-SA license. Abd Allah Aouragh MIET Laboratory, Faculty of Sciences and Techniques, Hassan 1st University Settat, Morocco Email: [abdallahaouragh@gmail.com](abdallahaouragh@gmail.com) Article Info ABSTRACT 1. INTRODUCTION Breast cancer is a prevalent global ailment, ranking as the most frequent cancer among women, constituting more than a third of all new cancer diagnoses within the female population [1] . The symptoms of this disease are diverse, including the presence of nodules, changes in skin texture, chest pain, unusual nipple discharge, and alterations in breast size or shape [1], [2] . Every year, the World Health Organization (WHO) registers around 2.3 million new breast cancer cases, making it the primary contributor to cancer-related fatalities among women. A proper diagnosis, based on various techniques such as mammography, ultrasound and biopsy, is essential to determine the nature and severity of the disease [1], [2] . Numerous treatments exist for breast cancer management, encompassing surgical interventions, radiation therapy, chemotherapy , and targeted therapeutic approaches. These treatment options, which vary according to the stage of the disease and its specific characteristics, offer multiple approaches to address the individual requirements of each patient [2], [3] . However, beyond the complexity of treatment, the most important factor in improving breast cancer management remains its early recognition [2], [3] . An early diagnosis of the disease facilitates the initiation of more effective interventions, thereby maximizing the chances of recovery [2], [3] . In the fight against breast cancer, machine learning, which is a subset of artificial intelligence, empowers computers to acquire knowledge and make decisions without the need for explicit programming. The early detection strategy based on machine learning takes advantage of the growing availability of varied medical data [4], [5] . The integration of machine learning algorithms, along with advanced data balancing and feature selection techniques, revolutionizes the assessment of clinical data, notably enhancing the sensitivity of breast cancer testing [6]–[8] . These advancements, spec

FAQs

What is the main goal of the study on breast cancer prediction?

To build and compare machine learning approaches that improve early breast cancer detection by integrating preprocessing, data balancing, and feature selection.

Which dataset and performance results are reported?

The study uses the Coimbra dataset with 116 records and 10 medical characteristics, reporting about 89.74% accuracy and 89.68% AUC-ROC.

How does data balancing contribute to the proposed pipeline?

Data balancing and feature selection techniques are used together with machine learning algorithms to better handle clinical data and enhance prediction sensitivity.

Aug 5, 2026

Upload by Levi