Investigate the Ensemble Model by Intelligence Analysis to Improve the Accuracy of the Classification Data in the Diagnostic and Treatment Interventions for Prostate Cancer

Abdelrahman Elsharif Karrar

doi:10.14569/ijacsa.2022.0130122

Abstract

Class imbalance problem become greatest issue in data mining, imbalanced data appears in daily application, especially in the health care. This research aims at investigating the application of ensemble model by intelligence analysis to improving the classification accuracy of imbalanced data sets on prostate cancer. The primary requirements obtained for this study included the datasets, relevant tools for pre-processing to identify the missing values, models for attribute selection and cross validation, data resembling framework, and intelligent algorithms for base classification. Additionally, the ensemble model and meta-learning algorithms were acquired in preparation for performance evaluation by embedding feature selecting capabilities into the classification model. The experimental results led to the conclusion that the application of ensemble learning algorithm on resampled data sets provides highly accurate classification results on single classifier J48. The study further suggests that gain ratio and ranker techniques are highly effective for attribute selection in the analysis of prostate cancer data. The lowest error rate and optimal performance accuracy in the classification of imbalanced prostate cancer data is achieved using when Adaboost algorithm is combined with single classifier J48.

Highlights

This Prostate cancer is among the leading causes of death in men worldwide
The process in which prostate cancer develops is known as Prostatic Intraepithelial Neoplasia (PIN) While most research studies on the pathogenesis of prostate cancer report inconclusive findings, etiological factors such as genetic inheritance and family history, vasectomy, environmental carcinogens, low carotenoid intake, and high intake of saturated fats and other unhealthy dietary/lifestyle habits are known to increase the risks significantly
The experimental results led to the conclusion that the application of ensemble learning algorithm on resampled data sets provides highly accurate classification results on single classifier J48

Summary

Introduction

This Prostate cancer is among the leading causes of death in men worldwide. The prostate is a glandular structure located in the male productive system and its functions is to promote spermatic health and enhance fertility by adding a nutrient-rich alkaline fluid to the semen [1]. Malignant tumors that lead to prostate cancer state to develop when the rate of cell multiplication is higher than cell death. This alters the genetic structure leading to mutations and tumor metastasis on the urothelial lining. The prostate has a higher malignancy rate due to the heavy reliance on the androgenic signaling of hormones such as testosterone, abnormal Gli-1 oncogene expression, and Sonic Hedgehog (Shh) expression, which stimulate cellular proliferation and stromal tumor growth. The process in which prostate cancer develops is known as Prostatic Intraepithelial Neoplasia (PIN) While most research studies on the pathogenesis of prostate cancer report inconclusive findings, etiological factors such as genetic inheritance and family history, vasectomy, environmental carcinogens, low carotenoid intake, and high intake of saturated fats and other unhealthy dietary/lifestyle habits are known to increase the risks significantly

Objectives

Methods

Results

Conclusion