Machine Learning for a Medical Prediction System - Breast Cancer Detection - A use case

Aug 3, 2026

Upload by Patrick

Breast cancer is a widespread, serious illness, making early detection crucial for providing prognostic guidance and supporting lifestyle adjustments that help limit disease progression. Environmental and day-to-day life changes can increase the likelihood of early-stage cancer development, increasing the need for reliable decision support. Machine learning offers efficient data processing, greater automation, and lower error rates. A breast cancer detection and prediction system is developed using KNN, LR, and XGBoost.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Introduction

Breast cancer risk and early detection needs

Machine learning role in disease prediction

Ethical and confidentiality considerations

Related works

Probabilistic and statistical classification approaches

Performance on WDBC and WBC databases

Machine Learning for a Medical Prediction System“Breast Cancer Detection” as a use case ETTAZI Haitam 1 , RAFALIA Najat 1 , ABOUCHABAKA Jaafar1 1Faculty of Sciences, University of Ibn Tofail, Kenitra, Morocco Abstract. Breast cancer is a widespread and serious illness, highlighting the importance of an early detection tool that can provide prognostic information and suggest necessary lifestyle changes to prevent its advancement, also the environmental changes in our daily life have significantly enhance the chances of getting cancer at an early stage of our life. Machine learning has become an indispensable tool in addressing this pressing need, enhancing human capabilities and offering greater automation with reduced errors. In this article, a breast cancer detection and prediction system has been created, utilizing diverse machine learning models including KNN, LR, and XGBoost. Index Terms— Machine Learning, KNN, Environmental changes XGBoost, LR, breast cancer, detection, prediction. 1 Introduction A variety of cancer risk factors are altered differently by habitat type (exposure to ultraviolet light, pollution, habitat fragmentation) . Machine learning has been used to map habitat types in a variety of ecosystems, but also human-induced environmental degradation such as hydrocarbon spill contamination, radioactive fallout, habitat fragmentation. The rising use of machine learning in habitat mapping will improve research into the effects of cancer on species and ecosystems. Machine learning in disease prediction has gained popularity in healthcare due to its ability to process data efficiently. It shows promise in improving early detection and diagnosis of breast cancer, a prevalent and serious disease affecting millions of women worldwide. Machine learning algorithms analyse various medical data, such as mammography images and patient history, to extract meaningful features. These algorithms can develop accurate prediction models to estimate the likelihood of a patient developing breast cancer. They also help identify high-risk individuals who may require closer monitoring or earlier screening. Ethical and confidentiality concerns arise when using machine learning in disease prediction. Medical data contains sensitive information that must be protected against misuse. Proper security measures are crucial to ensure responsible use of data and maintain © The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 ([https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)). patient privacy. Healthcare professionals must prioritize patient confidentiality and take steps to prevent unauthorized access or data breaches. Despite these concerns, machine learning holds great potential in improving patient outcomes and saving lives through early breast cancer detection and diagnosis. Collaboration between healthcare professionals and data scientists is essential to address ethical considerations and implement robust security measures. By striking a balance between the benefits and ethical concerns, machine learning can effectively contribute to better patient outcomes. 2 Related works Over the past decade, research on breast cancer detection has significantly increased. Various approaches have been explored, including probabilistic and statistical methods, as well as tools from artificial intelligence and cognitive science. This literature review focuses on the classification approaches used in breast cancer detection, specifically probabilistic and statistical methods. In recent studies, several statistical and probabilistic approaches have been proposed as classifiers for breast cancer detection. These methods often aim to improve upon traditional approaches such as Bayesian networks, the k-nearest neighbour rule, and the karma method. For instance, [2] introduc

FAQs

What problem does the paper address and why is early breast cancer detection important?

The paper addresses breast cancer prediction and detection, emphasizing that early detection can provide prognostic information and support actions that slow disease advancement.

Which machine learning models are used in the proposed breast cancer detection and prediction system?

The system uses multiple machine learning models, including KNN, LR, and XGBoost, to build prediction capabilities from medical data.

What ethical and confidentiality concerns must be handled when applying machine learning to medical prediction?

Medical data contains sensitive information, so patient privacy must be protected through appropriate security measures to prevent misuse, unauthorized access, and data breaches.

Aug 3, 2026

Upload by Patrick