Performance Evaluation of Ensembles Algorithms in Prediction of Breast Cancer

Abstract

Breast Cancer is the most dominant cause of mortality in women. Early diagnosis and treatment of the disease can stop the spreading of cancer in the breast. Due to this nature of the problem, accurate prediction is the most important measure of the predictive model. This paper proposes the comparison of ensemble learning techniques in predicting breast cancer. Ensemble learning is widely used for performance improvement of the predictive task. The ensembles algorithms used in this research study are AdaBoost, Random Forest, and XGBoost with data from Wisconsin hospitals. The result indicates that the random forest is the best predictive model for this dataset. The model has the following performance measure, accuracy 97%, sensitivity 96%, and specificity 96%. The experiment is executed using scikit-learn machine learning library. With this high level of accuracy offered by the model, the model can help the doctor to identify whether the patient has malignant or benign tumor cancer cells with high precision.

Breast Cancer Detection Using Machine Learning Algorithms

“…In [5], ensemble learning methods are used to predict BCs such AdaBoost, Random Forest, and XGBoost, their results indicate that random forest achieves 97% accuracy. In [6], Support vector machine (SVM) achieved 96.25% accuracy in predicting BCs on Wisconsin BC dataset.…”

Influence Distribution Training Data on Performance Supervised Machine Learning Algorithms

“…The methods used are Artificial Neural Network, Support Vector Machine and K-Nearest Neighbours classifiers. Through the machine learning methods used for breast cancer classification [7], crime prediction [8], and banknotes are generally divided into two classes. Then make the supervised learning method comparison to measure the level of accuracy in each method [9].…”

“…Some sources of data came from the result of the extra image that is used for classification [9][4] [5]. Then the machine learning methods are implemented in GNU Octave [1], scikit-learn machine learning library on anaconda distribution [7], MATLAB (version 8.4.0 (64bit)) [5], and Python [11]. In this paper, the authors classify Banknote with machine learning methods.…”