[Retracted] Feature Importance Score‐Based Functional Link Artificial Neural Networks for Breast Cancer Classification

Abstract

Growth of malignant tumors in the breast results in breast cancer. It is a cause of death of many women across the world. As a part of treatment, a woman might have to go through painful surgery and chemotherapy that may further lead to severe side effects. However, it is possible to cure it if it is diagnosed in the initial stage. Recently, many researchers have leveraged machine learning (ML) techniques to classify breast cancer. However, these methods are computationally expensive and prone to the overfitting problem. A simple single-layer neural network, i.e., functional link artificial neural network (FLANN), is proposed to overcome this problem. Further, the F-score is used to reduce the issue of overfitting by selecting features having a higher significance level. In this paper, FLANN is proposed to classify breast cancer using Wisconsin Breast Cancer Dataset (WBCD) (with 699 samples) and Wisconsin Diagnostic Breast Cancer (WDBC) (with 569 samples) datasets. Experimental results reveal that the proposed models can diagnose breast cancer with higher performance. The proposed model can be used in the early breast cancer diagnosis with 99.41% accuracy.

Breast Cancer-Risk Factors and Prediction Using Machine-Learning Algorithms and Data Source: A Review of Literature

“…The result showed that the model achieved 99.85% accuracy. S. Singh et al [121] used the ANN model to predict BC using the WDBC. The result showed that the model achieved 99.41% accuracy.…”

Analysis of Different Machine Learning Techniques with PCA in the Diagnosis of Breast Cancer

“…In the classification algorithms used (LR, DTC, RFC, KNN, SVM, ABC), the KNN and SVM algorithms gave the highest results with 94.74 in the data obtained before the SMOTE technique, and a much more sensitive and higher rate in the KNN algorithm with a rate of 95.32 after SMOTE provided [9]. S. Singh et al (2022) stated that Machine Learning algorithms are used in the diagnosis of diseases in the health field, but there are errors in these classification techniques, and in order to minimize these errors, they are minimized by using various supporting applications such as Features selection or Features extraction to the data sets before classification algorithms. FLANN, one of the simple single-layer neural network models, was used to minimize these errors.…”

“…FLANN, one of the simple single-layer neural network models, was used to minimize these errors. Classification was carried out by applying it to two different breast cancer diagnostic datasets existing in the literature, and the experimental results obtained achieved a high accuracy of 99.41% in the diagnosis of early-stage breast cancer [10]. Prithwish Ghosh (2022) stated that the XGboost algorithm in diagnosing breast cancer provides faster results than other existing algorithms in diagnosing the disease.…”

Classification Prediction of Breast Cancer Based on Machine Learning

“…Jia et al [ 18 ] proposed a new population optimization algorithm, Whale Optimization Algorithm (WOA), which intelligently adjusts the parameters of the SVM model, and the experimental results show that the performance of the WOA-SVM model is significantly better than that of the traditional breast cancer recognition model, with an accuracy of 97.5%. In order to solve the problem of overfitting of machine learning techniques in breast cancer classification, Singh et al [ 19 ] proposed a functionally connected artificial neural network (FLANN) and experimentally found that the model has high accuracy for early diagnosis of breast cancer. Mahesh et al [ 20 ] propose a breast cancer prediction XGBoost ensemble technique based on known feature patterns, first using synthetic minority oversampling technology (SMOTE) to deal with data imbalance and noise problems and then using naïve Bayes classifier, decision tree classifier, and random forest, respectively, combined with XGBoost and classifying the data.…”