Proximate Breast Cancer Factors Using Data Mining Classification Techniques

Proximate Breast Cancer Factors Using Data Mining Classification Techniques

Alice Constance Mensah (Accra Technical University, Accra, Ghana) and Isaac Ofori Asare (Vita Verde Consult, Accra, Ghana)
Copyright: © 2019 |Pages: 10
DOI: 10.4018/IJBDAH.2019010104

Abstract

Breast cancer is the most common of all cancers and is the leading cause of cancer deaths in women worldwide. The classification of breast cancer data can be useful to predict the outcome of some diseases or discover the genetic behavior of tumors. Data mining technology helps in classifying cancer patients and this technique helps to identify potential cancer patients by simply analyzing the data. This study examines the determinant factors of breast cancer and measures the breast cancer patient data to build a useful classification model using a data mining approach. In this study of 2397 women, 1022 (42.64%) were diagnosed with breast cancer. Among the four main learning techniques such as: Random Forest, Naive Bayes, Classification and Regression Model (CART), and Boosted Tree model were used for the study. The Random Forest technique had the better accuracy value of 0.9892(95%CI,0.9832 -0.9935) and a sensitivity value of about 92%. This means that the Random Forest learning model is the best model to classify and predict breast cancer based on associated factors.
Article Preview
Top

Literature Review

Breast cancer occurrence is increasing globally and one of the major causes of death in women compared to all other cancers. Chaurasia and Pal (2017) breast cancer is a major health problem and represents a significant worry for many women. To reduce life losses, detecting breast cancer early is very essential and it calls for accurate and reliable diagnosis procedure. One of the major problems in medical applications is medical diagnosis Liou and Chang (2015). The application of machine learning methods is widely used nowadays in medical diagnosis for prediction. One of the most interesting and challenging tasks is to develop data mining applications in the prediction of an outcome of a disease. Saleema el al. (2014) posited that, the production and availability of large volumes of the medical data by the medical research groups has resulted in making data mining techniques a popular research tool. This tool is used to identify and exploit patterns and relationships among large number of variables and also to predict an outcome of a disease using the historical datasets.

Various studies have been done on the application of data mining techniques in diagnosing breast cancer. One of such studies was by (Bellaachia & Guven, 2006), who reported that C4.5 algorithm, gave the best performance of 86.7% accuracy having used the SEER data to compare three prediction models for detecting breast cancer. The use of the genetic algorithm model on the data of breast cancer patients explored by (Chang & Liou,2008) yielded a better result than other data mining models for the analysis of the overall accuracy of the patient classification, expression and complexity of the classification rule. Investigation by (Abdelaal el al., 2010) revealed that SVM techniques show a promising result for increasing diagnostic accuracy of classifying the cases witnessed by the largest area under the ROC curve comparable to values for tree boost and tree forest. The approach by (Christobel & Sivaprakasam, 2011) decision tree classifier (CART) for breast cancer diagnosis, attained an accuracy of 69.23%. Comparing the classification accuracy of Support Vector Machine (SVM), IBK, BF Tree algorithms, the SVM had the best accuracy (Lavanya and Rani,2012). Asri el al. (2016) applied the performance of Support Vector Machine (SVM), Decision Tree (C4.5), Naive Bayes (NB) and k Nearest Neighbors (kNN) on the Wisconsin Breast Cancer datasets. The results indicated that SVM had the best performance in term of accuracy (97.13%). A study on breast cancer comparing data mining techniques for breast cancer shows that C4.5 is the best classification technique for breast cancer as it had an accuracy rate of 86.70%(Zand,2015). Shajahaan et al. (2013) in their study shown that, Random Tree was the best data mining technique to classify and predict breast cancer with an accuracy rate of 100%.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 5: 2 Issues (2020): Forthcoming, Available for Pre-Order
Volume 4: 2 Issues (2019): 1 Released, 1 Forthcoming
Volume 3: 2 Issues (2018)
Volume 2: 2 Issues (2017)
Volume 1: 1 Issue (2016)
View Complete Journal Contents Listing