Performance enhancement of machine learning algorithm for breast cancer diagnosis using hyperparameter optimization

Aug 3, 2026

Breast cancer is a leading cause of female cancer mortality, making early, accurate diagnosis essential. This study evaluates the classification efficiency of multiple machine learning models for breast cancer diagnosis using hyperparameter optimization with grid search and random search. Hyperparameter selection directly affects model performance. Results show k-nearest neighbor achieves 100.00% recall with grid-search-tuned hyperparameters, while k-NN, logistic regression, and multilayer perceptron reach 99.42% accuracy. Overall gains occur with grid search except for XGBoost.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

Breast cancer background and need for early diagnosis

Machine learning in computer-aided diagnosis

Hyperparameters, HPO, and search strategies

Methods

Models and classifiers used

Dataset and training setup

Results

Performance after hyperparameter optimization

Comparison across algorithms

Performance enhancement of machine learning algorithm for breast cancer diagnosis using hyperparameter optimization Rashidul Hasan Hridoy1, Arindra Dey Arni2, Shomitro Kumar Ghosh2, Narayan Ranjan Chakraborty2, Imran Mahmud1 1Department of Software Engineering, Faculty of Science and Information Technology, Daffodil International University, Dhaka, Bangladesh 2Department of Computer Science and Engineering, Faculty of Science and Information Technology, Daffodil International University, Dhaka, Bangladesh Article history: Received Sep 18, 2023 Revised Dec 16, 2023 Accepted Dec 18, 2023 Keywords: Breast cancer Machine learning Hyperparameter optimization Grid search Random search Logistic regression K-nearest neighbor Corresponding Author: Breast cancer is the most fatal women’s cancer, and accurate diagnosis of this disease in the initial phase is crucial to abate death rates worldwide. The demand for computer-aided disease diagnosis technologies in healthcare is growing significantly to assist physicians in ensuring the effectual treatment of critical diseases. The vital purpose of this study is to analyze and evaluate the classification efficiency of several machine learning algorithms with hyperparameter optimization techniques using grid search and random search to reveal an efficient breast cancer diagnosis approach. Choosing the optimal combination of hyperparameters using hyperparameter optimization for machine learning models has a straight influence on the performance of models. According to the findings of several evaluation studies, the k-nearest neighbor is addressed in this study for effective diagnosis of breast cancer, which got a 100.00% recall value with hyperparameters found utilizing grid search. k-nearest neighbor, logistic regression, and multilayer perceptron obtained 99.42% accuracy after utilizing hyperparameter optimization. All machine learning models showed higher efficiency in breast cancer diagnosis with grid search-based hyperparameter optimization except for XGBoost. Therefore, the evaluation outcomes strongly validate the effectiveness and reliability of the proposed technique for breast cancer diagnosis. This is an open access article under the CC BY-SA license. Rashidul Hasan Hridoy Department of Software Engineering, Faculty of Science and Information Technology, Daffodil International University Daffodil Smart City, Birulia, Savar, Dhaka, Bangladesh Email: [rashidulhasanhridoy@gmail.com](rashidulhasanhridoy@gmail.com) Article Info ABSTRACT 1. INTRODUCTION Breast cancer (BC) originates in breast tissues, where the growth of cells becomes uncontrollable, and cells build a tumor [1] . BC is mostly seen in adults which is the major cause of female deaths in 95% of countries and over 2.3 million (M) incidents of BC happen every year [2] . BC has a detrimental impact on human health and hinders the quality of life. According to several institutions of research, 0.4 M females die for BC every year. Radiation therapy, surgical removal, and medication are often used for controlling the growth and spreading of BC and early identification is highly crucial for effective BC treatment [3] . The early treatment and prevention of BC is an enormous challenge in healthcare and a remarkable improvement carried out in elementary research and clinical treatment in recent decades [4] . Computer-aided technologies used for BC diagnosis and analysis make the treatment of BC easier and reduce fatality [5] . Due to the shortage of proficient physicians and technologies, a notable number of countries are now facing several types of issues, where machine learning (ML) brings immense hope for its effective performance. ML-based tools already yielded satisfactory results and proved their capability in the diagnosis of different types of critical diseases. Applications of ML are now extensively used in healthcare and remarkably enhance the accuracy and speed of physicians'

FAQs

What problem does the study address in breast cancer diagnosis?

The study targets improving the classification performance for early breast cancer diagnosis, where accurate detection can reduce worldwide mortality rates.

Which hyperparameter optimization strategies are used?

The study applies hyperparameter optimization using grid search and random search to find effective hyperparameter combinations for multiple machine learning models.

Which model shows the best recall and what accuracy is reported after optimization?

k-nearest neighbor reaches 100.00% recall with hyperparameters selected via grid search, and k-nearest neighbor, logistic regression, and multilayer perceptron achieve 99.42% accuracy after hyperparameter optimization.

Aug 3, 2026

Upload by Emma Wilson