An Ensemble Machine Learning based Framework for Early Detection of Breast Cancer - paper summary

Aug 4, 2026

Upload by Sage

Breast cancer involves abnormal breast-cell growth with malignant types differing by origin and spread. A stacked ensemble learning framework is presented to support early diagnosis by distinguishing malignant from benign cells. The study uses the Wisconsin Breast Cancer Dataset from the UCI repository with 30 extracted features and evaluates specificity, sensitivity, F1-score, and accuracy. Using Decision Tree, AdaBoost, Gaussian NB, and MLP, the model attains 96.66% accuracy and is positioned as an adaptable approach for related medical classification tasks.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages8

Reading Time20 min

AccessFree to download

Introduction

Related Work and Motivation

Dataset and Feature Representation

Model Design and Ensemble Strategy

Evaluation Metrics and Results

Conclusion and Future Applicability

An Ensemble Machine Learning based Framework for Early Detection of Breast Cancer SEEJPH Volume XXVI, S1,2025, ISSN: 2197-5248; Posted:05-01-25 An Ensemble Machine Learning based Framework for Early Detection of Breast Cancer Isha Yadav1, Sanjive Tyagi2, Sudhir Goswami3, Gundeep Tanwar4, Paresh Pathak5, Charu Mukhija6* 1Assistant Professor, NIMS School of Computing and Artificial Intelligence, NIET, NIMS University, Jaipur, Rajasthan, INDIA, Email: [isha.24211@gmail.com](isha.24211@gmail.com) 2Associate Professor, Department of Computer Science Engineering, Faculty of Engineering & Technology, Swami Vivekanand Subharti University, Meerut, UP, INDIA, Orcid:0000-0003-2769-7023, Email: [tosanjive@gmail.com](tosanjive@gmail.com) 3Assistant Professor, Department of Information Technology, Rajkiya Engineering College Bijnor, Uttar Pradesh, INDIA, Email: [sudhir.it@recb.ac.in](sudhir.it@recb.ac.in) 4Assistant Professor, Department of Computer Science & Engineering, RPS College of Engineering & Technology, Mahendergarh, Haryana, INDIA, [Email: mr.tanwar@gmail.com](Email: mr.tanwar@gmail.com) 5Assistant Professor, School of Computer Science and Application, IIMT University, Meerut, Uttar Pradesh, INDIA, Email: [pareshbhu@gmail.com](pareshbhu@gmail.com) 6*Assistant professor, Department of Computer Applications, Panipat Institute of Engineering and Technology (PIET), Samalkha, Panipat, Haryana, INDIA, Email: [charu.mca@piet.co.in](charu.mca@piet.co.in) (*Corresponding Author) KEYWORDS Breast Disease Classification, Machine Learning, Decision Tree, NB, AdaBoost, Ensemble learning ABSTRACT: Breast cancer is a disease characterized by the abnormal growth of breast cells, with different types based on the origin and spread of malignant cells. The most common types include infiltrative ductal carcinoma, which starts in the breast ducts and spreads to surrounding tissues, and infiltrative lobular carcinoma, which originates in the lobules and can metastasize to other parts of the body. Given the increasing interest in artificial intelligence for medical diagnostics, various machine learning techniques have been employed to predict breast cancer. In this study, the Wisconsin Breast Cancer Dataset (WBCD) from the UCI Machine Learning Repository was utilized, containing 30 extracted features, including mean, standard error, and worst values for various attributes. To evaluate model performance, key metrics such as specificity, F1-score, sensitivity, and accuracy were analyzed. A stacked ensemble classifier was developed using Decision Tree, AdaBoost, Gaussian NB, and MLP classifiers, achieving a high accuracy of 96.66%, surpassing existing approaches. The results indicate that the proposed ensemble model effectively distinguishes between malignant and benign cancer cells, facilitating early detection and improving treatment outcomes. Additionally, this ensemble approach can be adapted to other medical and classification problems, demonstrating its broader applicability. 1. INTRODUCTION Breast cancer remains one of the most prevalent and life-threatening diseases affecting women worldwide. Early detection plays a crucial role in improving survival rates, reducing treatment complexity, and enhancing the quality of life for patients. Traditional diagnostic methods, such as mammography, ultrasound, and biopsy, have significantly contributed to early detection; however, they also pose challenges, including high false-positive rates, variability in interpretation, and accessibility issues. To overcome these limitations, the integration of machine learning (ML) techniques into medical diagnostics has emerged as a promising approach. Breast cancer detection has historically relied on conventional diagnostic methods such as mammography, ultrasound, and biopsy, which, while effective, have limitations in terms of accuracy and accessibility. Early computational approaches, including statistical modeling and simple mach

FAQs

Why is early detection critical for breast cancer outcomes?

Early detection improves survival rates, reduces treatment complexity, and enhances patients’ quality of life by identifying disease before it progresses.

Which dataset and features were used for training and evaluation?

The Wisconsin Breast Cancer Dataset (WBCD) from the UCI Machine Learning Repository was used, containing 30 extracted features such as mean, standard error, and worst values.

What models are combined in the proposed stacked ensemble framework?

The stacked ensemble integrates Decision Tree, AdaBoost, Gaussian Naive Bayes, and MLP classifiers to improve robustness and predictive performance.

Aug 4, 2026

Upload by Sage