A Comparative Analysis of Breast Cancer Detection and Diagnosis Using Data Visualization and Machine Learning Applications.

Muhammet Fatih Ak

doi:10.3390/healthcare8020111

Abstract

In the developing world, cancer death is one of the major problems for humankind. Even though there are many ways to prevent it before happening, some cancer types still do not have any treatment. One of the most common cancer types is breast cancer, and early diagnosis is the most important thing in its treatment. Accurate diagnosis is one of the most important processes in breast cancer treatment. In the literature, there are many studies about predicting the type of breast tumors. In this research paper, data about breast cancer tumors from Dr. William H. Walberg of the University of Wisconsin Hospital were used for making predictions on breast tumor types. Data visualization and machine learning techniques including logistic regression, k-nearest neighbors, support vector machine, naïve Bayes, decision tree, random forest, and rotation forest were applied to this dataset. R, Minitab, and Python were chosen to be applied to these machine learning techniques and visualization. The paper aimed to make a comparative analysis using data visualization and machine learning applications for breast cancer detection and diagnosis. Diagnostic performances of applications were comparable for detecting breast cancers. Data visualization and machine learning techniques can provide significant benefits and impact cancer detection in the decision-making process. In this paper, different machine learning and data mining techniques for the detection of breast cancer were proposed. Results obtained with the logistic regression model with all features included showed the highest classification accuracy (98.1%), and the proposed approach revealed the enhancement in accuracy performances. These results indicated the potential to open new opportunities in the detection of breast cancer.

Highlights

IntroductionData science has become one of the most popular research areas of interest in the world
Data science has become one of the most popular research areas of interest in the world.Many datasets can be useful in different situations such as marketing, transportation, social media, and healthcare [1]
Logistic regression is a technique that firstly used for biological studies in the early twentieth century

Summary

Introduction

Data science has become one of the most popular research areas of interest in the world. Many datasets can be useful in different situations such as marketing, transportation, social media, and healthcare [1]. Only a few of them have been interpreted by data science researchers, and they believe that these datasets can be useful for predictions. Many of the marketers have started to analyze their datasets because of the big information they have on hand, and they want to turn these data into meaningful information for future predictions. Data mining and machine learning techniques are straightforward and effective ways to understand and predict future data. Data analysis techniques are popular in many companies and have an impact on different study areas.

Methods

Results

Conclusion