Diagnosing Lung Cancer Using Grasshopper Optimization Algorithm and k-Nearest Neighbor Classification

Abstract

Today's, of the major cancers for both females and male is lung cancer. This type of cancer is the most common cause of mortality that accounts for up to 20% of all cancers. The incidence of this cancer has noticeably increased since the beginning of the 19th century. The current study aims to investigate and present a novel method to diagnose lung cancer using Optimization Algorithm (GOA) algorithm and KNN classification. The study method includes three steps. In the first step, pre-processing of lung cancer cell data is used to remove irrelevant and duplicate features. In the second step, the Grasshopper Optimization Algorithm (GOA) method is used to select the high-dimensional feature. In the third step, the selected features are classified into three categories, namely low, medium and high using the KNN nearest neighbor classifier. To evaluate the proposed method, the UCI dataset is used. The results indicate that this method has superior performance with the accuracy of 98.65, specificity of 96.7, and sensitivity of 94.10, demonstrating the superiority of this method over others. The results show that diagnosis of lung cancer using data mining techniques provides the physician with the most detailed and accurate information in the shortest possible time.

Lung cancer Prediction and Classification based on Correlation Selection method Using Machine Learning Techniques

“…Primary lung cancer originates elsewhere in the body and spreads to the lungs, while secondary lung cancer starts elsewhere in the body and then spreads from there. It's one of the most aggressive types of cancer and a life-threatening threat to the human body [17]. If this unchecked development can be identified correctly at an early point, it can help to diagnose the likelihood of unnecessary surgery and improve the chance of recovery.…”

“…Each of researchers in [16][17] they used same dataset (LIDC-IDRI) the researchers in [16] could obtained 86% sensitivity while, researchers in [17] depending on 2 features and applied different classifiers they obtained a good result (Random Forest 70%, SVM 80% and, ANN 96%).also the researchers in [18], [19] by using the same dataset and number of feature selection which is( 23),but the researchers in [18] obtained higher accuracy 100% by using KNN classifier and genetic algorithm for feature selection. while the researchers in [19] obtained (Decision Tree 97%, K-NN 94% and, Neural Networks 96%).…”