Performance Analysis of Breast Cancer Classification Using Feature Selection and Machine Learning

Breast cancer is a common cause of female mortality in developing countries. Early detection and treatment are crucial for successful outcomes. Breast cancer develops from breast cells and is considered a leading cause of death in women. This disease is classified into two subtypes: invasive ductal carcinoma (IDC) and ductal carcinoma in situ (DCIS). The advancements in artificial intelligence (AI) and machine learning (ML) techniques have made it possible to develop more accurate and reliable models for diagnosing and treating this disease. From the literature, it is evident that the incorporation of MRI and convolutional neural networks (CNNs) is helpful in breast cancer detection and prevention. In addition, the detection strategies have shown promise in identifying cancerous cells. The CNN Improvements for Breast Cancer Classification (CNNI-BCC) model helps doctors spot breast cancer using a trained deep learning neural network system to categorize breast cancer subtypes. However, they require significant computing power for imaging methods and preprocessing. Therefore, in this research, we proposed an efficient deep learning model that is capable of recognizing breast cancer in computerized mammograms of varying densities. Our research relied on three distinct modules for feature selection: the removal of low-variance features, univariate feature selection, and recursive feature elimination. The craniocaudally and medial-lateral views of mammograms are incorporated. We tested it with a large dataset of 3002 merged pictures gathered from 1501 individuals who had digital mammography performed between February 2007 and May 2015. In this paper, we applied six different categorization models for the diagnosis of breast cancer, including the random forest (RF), decision tree (DT), k-nearest neighbors (KNN), logistic regression (LR), support vector classifier (SVC), and linear support vector classifier (linear SVC). The simulation results prove that our proposed model is highly efficient, as it requires less computational power and is highly accurate.

Background: Cardiovascular diseases belong to the top three leading causes of mortality in the Philippines with 17.8 % of the total deaths. Lifestyle-related habits such as alcohol consumption, smoking, poor diet and nutrition, high sedentary behavior, overweight, and obesity have been increasingly implicated in the high rates of heart disease among Filipinos leading to a significant burden to the country's healthcare system. The objective of this study was to predict the presence of heart disease using various machine learning algorithms (support vector machine, naïve Bayes, random forest, logistic regression, decision tree, and adaptive boosting) evaluated on an anonymized publicly available cardiovascular disease dataset. Methodology: Various machine learning algorithms were applied on an anonymized publicly available cardiovascular dataset from a machine learning data repository (IEEE Dataport). A web-based application system named Heart Alert was developed based on the best machine learning model that would predict the risk of developing heart disease. An assessment of the effects of different optimization techniques as to the imputation methods (mean, median, mode, and multiple imputation by chained equations) and as to the feature selection method (recursive feature elimination) on the classification performance of the machine learning algorithms was made. All simulation experiments were implemented via Python 3.8 and its machine learning libraries (Scikit-learn, Keras, Tensorflow, Pandas, Matplotlib, Seaborn, NumPy). Results: The support vector machine without imputation and feature selection obtained the highest performance metrics (90.2% accuracy, 87.7% sensitivity, 93.6% specificity, 94.9% precision, 91.2% F1-score and an area under the receiver operating characteristic curve of 0.902) and was used to implement the heart disease prediction system (Heart Alert). Following very closely were random forest with mean or median imputation and logistic regression with mode imputation, all having no feature selection which also performed well. Conclusion: The performance of the best four machine learning models suggests that for this dataset, imputation technique for missing values may or may not be done. Likewise, recursive feature elimination for feature selection may not apply as all variables seem to be important in heart disease prediction. An early accurate diagnosis leading to prompt intervention efforts is very crucial as it improves the patient's quality of life and diminishes the risk of developing cardiac events.

to predict vestibular schwannoma (VS) response to radiosurgery by applying machine learning (ML) algorithms on radiomic features extracted from pre-treatment magnetic resonance (MR) images. patients with VS treated with radiosurgery in two Centers from 2004 to 2016 were retrospectively evaluated. Brain T1-weighted contrast-enhanced MR images were acquired before and at 24 and 36 months after treatment. Clinical and treatment data were collected contextually. Treatment responses were assessed considering the VS volume variation based on pre- and post-radiosurgery MR images at both time points. Tumors were semi-automatically segmented and radiomic features were extracted. Four ML algorithms (Random Forest, Support Vector Machine, Neural Network, and extreme Gradient Boosting) were trained and tested for treatment response (i.e., increased or non-increased tumor volume) using nested cross-validation. For training, feature selection was performed using the Least Absolute Shrinkage and Selection Operator, and the selected features were used as input to separately build the four ML classification algorithms. To overcome class imbalance during training, Synthetic Minority Oversampling Technique was used. Finally, trained models were tested on the corresponding held out set of patients to evaluate balanced accuracy, sensitivity, and specificity. 108 patients treated with Cyberknife® were retrieved; an increased tumor volume was observed at 24 months in 12 patients, and at 36 months in another group of 12 patients. The Neural Network was the best predictive algorithm for response at 24 (balanced accuracy 73% ± 18%, specificity 85% ± 12%, sensitivity 60% ± 42%) and 36 months (balanced accuracy 65% ± 12%, specificity 83% ± 9%, sensitivity 47% ± 27%). radiomics may predict VS response to radiosurgery avoiding long-term follow-up as well as unnecessary treatment.

Breast cancer has always been one of the most dangerous diseases that threaten women's lives. If the disease is not detected in the early stages, it can result in the death of the patient. The term breast cancer is referring to a malignant tumor that happened due to the unexpected development of breast's cells which can probably have the ability to spread through other different parts of the patient's body. The occurrence of cancer is often a result of the abnormal growth of cells in our bodies. Cancers generally are classified into two types, Benign (non-cancerous cell) and Malignant (cancerous cell). The earlier the cancer is diagnosed, the better the patient's chance of recovery. Being able to accurately predict breast cancer present in patients has always been an important issue for cancer researchers. Machine Learning (ML) and Data Mining (DM) have always been a point of interest in the scientific community in the hope that they can yield accurate results. We aimed in this study to predict the tumor at early stages using some classification algorithms. After the dataset was collected and the outliers and skewness in the data set were removed, different classification algorithms were applied, focusing on the effect of the feature selection step in the model building phase. After conducting multiple experiments, we got the best overall accuracy by Support Vector Machine (SVM) classifier based on feature selection using Recursive Feature Elimination (RFE) with Random Forest (RF) technique with an accuracy of 98.25%.

Machine learning today becomes more and more effective instrument to solve many particular problems, where there are difficulties to apply well known and described math model. In other words - it is a great tool to describe nonlinear phenomena. We tried to use this technique to improve existing process of stratigraphy and lithology interpretation and reduce costs on site by applying computer leaded predictions on the basis of existing on-field collected data. Article describes usage of machine learning algorithms for several geology data stratigraphy and lithology boundaries classification based on geophysics logging data for deposits in Kazakhstan. Correct marking of stratigraphy and lithology from geophysics logging data is complex non-linear task. To solve this task we applied several algorithms of machine learning: random forest, logistic regression, gradient boosting (scikit-learn library), k - nearest neighbour (KNN) and XGBoost.

While there are many factors which could contribute to the occurrence of breast cancer, it is very difficult to attribute the exact environmental and other factors contributing to it, but still it has significance in determining the occurrence of cancer. Using machine learning techniques and regular diagnosis information, we can achieve our goal of assessing the risk of occurrence of breast cancer. Cancer data sets contain many attributes of patient information, but not every feature is relevant in predicting cancer. Feature selection techniques are useful in such scenarios for retaining the relevant feature set. In this paper we are doing a comparative study of the effect of feature selection techniques on the accuracies given by existing machine learning algorithms. For this purpose we have considered the following machine learning algorithms - Logistic Regression, Naive Bayes and Random Forest. The following feature selection techniques have been considered - Sequential Forward Feature Selection, Recursive Feature Elimination, f-test and correlation.The publicly available Breast Cancer Wisconsin (Diagnostic) Data Sets from UCI Repository have been used in this work. The results show that random forest algorithm gives the highest accuracy with feature selection. Furthermore f-test gives better results for the smaller dataset and Sequential Forward Selection for the larger dataset.

Stroke is a disease that occurs in the brain and can cause both vocal and global brain dysfunction. Stroke research mainly aims to predict risk and mortality. Machine learning can be used to diagnose and predict diseases in the healthcare field, especially in stroke prediction. However, collecting medical record data to predict a disease usually makes much noise because not all variables are important and relevant to the prediction process. In this case, dimensionality reduction is essential to remove noisy (i.e., irrelevant) and redundant features. This study aims to predict stroke using Recursive Feature Elimination as feature selection, Principal Component Analysis as feature extraction, and a combination of Recursive Feature Elimination and Principal Component Analysis. The dataset used in this research is stroke prediction from Kaggle. The research methodology consists of pre-processing, SMOTE, 10-fold Cross-Validation, feature selection, feature extraction, and machine learning, which includes SVM, Random Forest, Naive Bayes, and Linear Discriminant Analysis. From the results obtained, the SVM and Random Forest get the highest accuracy value of 0.8775 and 0.9511 without using PCA and RFE, Naive Bayes gets the highest value of 0.7685 when going through PCA with selection of 20 features followed by RFE feature selection with selection of 5 features, and LDA gets the highest accuracy with 20 features from feature selection and continued feature extraction with a value of 0. 7963. It can be concluded in this study that SVM and Random Forest get the highest accuracy value without PCA and RFE techniques, while Naive Bayes and LDA show better performance using a combination of PCA and RFE techniques. The implication of this research is to know the effect of RFE and PCA on machine learning to improve stroke prediction.

6 - Machine learning and deep learning algorithms for fault diagnosis of photovoltaic systems

Breast cancer is one of the diseases with a high number of deaths every year and has become very prominent among Indian women in recent times. Cancer must be detected at the early stages of its formation to improve the mortality rates. This paper focuses on a comparison of multiple machine learning models with the use of different filters for the detection of breast cancer. Models used in this experiment include logistic regression, random forest, extreme gradient boosting, Gaussian Naive Bayes, K-nearest neighbors, and it is observed that the performance of these models significantly improve with the implementation of various data manipulation techniques. The best model for classification is found to be random forest (Accuracy = 98.04% and F1-Score = 96.27%) and XGBoost classifier (Accuracy = 98.32% and F1-Score = 98.31%).KeywordsLogistic regressionRandom forestExtreme gradient boostingGaussian Naive BayesK-nearest neighborsBreast cancerEarly detection

Introduction: Breast cancer is one of the most common cancers among women compared to all other ones. Machine learning techniques can bring a large contribute on the process of prediction and early diagnosis of breast cancer, became a research hotspot and has been proved as a strong technique. Using machine learning models performed on multidimensional dataset, this article aims to find the most efficient and accurate machine learning models for tumor classification prediction.Materials & Methods: Several supervised machine learning algorithms were utilized to diagnosis and prediction of cancer tumor such as Logistic Regression Decision Tree, Random Forest and KNN. The algorithms are applied to a dataset taken from the UCI repository including 699 samples. The dataset includes Breast cancer features. To enhance the algorithms’ performance, these features are analyzed, the feature importance score and cross validation are considered. In this paper ML algorithms improved coupled by limited and selective features to produce high classification accuracy in tumor classification.Results: As a result of evaluation, Logistic Regression algorithm with accuracy value equal to 99.14%, AUC ROC equal to 99.6%, Extra Tree algorithm with accuracy value equal to 99.14% and AUC ROC equal to 99.1% have better performance than other algorithms. therefore, these techniques can be useful for diagnosis and prediction of cancer tumor and prescribe it correctly.Conclusions: The technique of machine learning can be used in medicine for analyzing the related data collections to a disease and its prediction. The area under the ROC curve and evaluating criteria related to a number of classifying algorithms of machine learning to evaluate breast cancer and indeed, the diagnosis and prediction of breast cancer is compared to determine the most appropriate classifier.

Breast cancer ranks among the most prevalent cancers in women globally, with its treatment efficacy heavily reliant on the early identification and diagnosis of the disease. The importance of early detection and diagnosis cannot be overstated in enhancing the survival prospects of those afflicted with breast cancer. With the increasing application of machine learning technology in the medical field, algorithm-based diagnostic tools provide new possibilities for early prediction of breast cancer. In this study, we introduced a novel feature selection approach, which leverages Shapley additive explanation (SHAP) values as the basis for Recursive Feature Elimination (RFE), utilizing a Random Forest (RF) algorithm within the RFE framework. To address the data imbalance challenge, we incorporated Borderline-SMOTE1. The efficacy of the proposed method was assessed using five machine learning models, K-Nearest Neighbor (KNN), Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), and Light Gradient Boosting Machine (LightGBM), applied to the Wisconsin Breast Cancer Diagnosis (WBCD) datasets. Optimizing hyperparameters of five models using the Particle Swarm Optimization (PSO) algorithm. In the datasets, 26 features were filtered using our recommended algorithm, the LightGBM-PSO model demonstrated an outstanding performance. The model demonstrated an impressive accuracy of 99.0% in differentiating between benign and malignant cases, boasting a specificity and precision of 100%, a recall rate of 97.40%, an F-measure of 98.68%, an AUC of 0.9870, and a 10-fold cross-validation accuracy of 0.9808. Subsequently, we developed a corresponding online tool (https://breast-cancer-prediction-tool-cgbjlhkns7yig6bmzvztmc.streamlit.app/) based on this model for predicting the risk of breast cancer. Feature selection using recommended algorithm and optimization of the LightGBM model through PSO can significantly enhance the accuracy of breast cancer prediction. This could potentially improve the prognosis for patients diagnosed with breast cancer.

Advancements in the implementation of quantum hardware have enabled the acquisition of data that are intractable for emulation with classical computers. The integration of classical machine learning (ML) algorithms with these data holds potential for unveiling obscure patterns. Although this hybrid approach extends the class of efficiently solvable problems compared to using only classical computers, this approach has been only realized for solving restricted problems because of the prevalence of noise in current quantum computers. Here, we extend the applicability of the hybrid approach to problems of interest in many-body physics, such as predicting the properties of the ground state of a given Hamiltonian and classifying quantum phases. By performing experiments with various error-reducing procedures on superconducting quantum hardware with 127 qubits, we managed to acquire refined data from the quantum computer. This enabled us to demonstrate the successful implementation of theoretically suggested classical ML algorithms for systems with up to 44 qubits. Our results verify the scalability and effectiveness of the classical ML algorithms for processing quantum experimental data.

Alzheimer’s disease is a progressive neurodegenerative disorder for which early detection remains a significant challenge due to the complexity of clinical features and the high dimensionality of medical data. This study aims to improve the accuracy and reliability of Alzheimer’s disease detection by evaluating the performance of multiple machine learning algorithms integrated with intelligent feature selection strategies. Five classification models, Decision Tree, Naïve Bayes, Random Forest, Logistic Regression, and Deep Learning, were investigated under two experimental scenarios: without feature selection and with feature selection using Recursive Feature Elimination, Binary Particle Swarm Optimization, and Variance Threshold. Model performance was evaluated using K-fold cross-validation based on accuracy, precision, recall, and F1-score metrics. The results demonstrate that feature selection consistently enhances classification performance, particularly for conventional machine learning models such as Random Forest and Logistic Regression. Although the Deep Learning model achieves competitive accuracy, its reduced precision and F1-score indicate limitations when applied to reduced feature spaces. These findings highlight the importance of incorporating appropriate feature selection techniques to address data complexity and improve the effectiveness of early Alzheimer’s disease detection.

Predicting lodging severity in dry peas using UAS-mounted RGB, LIDAR, and multispectral sensors

The process of building new dataset and the existence of such a data followed the urgent need for the existence of datasets that are specialized in educational lectures, so this will need an accurate classification algorithm to classify it, the benefit of classify such dataset is to minimize the workload of classifying each file manually and individually. In the present paper, authors perform experimentations for conducting an empirical deep learning study, especially, convolutional neural network, for three new datasets of educational lectures which are (PDF, Word and PowerPoint datasets), The three new datasets using real data educational resources lectures collected from various document projects of different universities and institutions. The architecture has been applied to the task of the text classification in the domain of the document with documents data-sets have been obtained from a variety of projects on actual document cases. The aim of the present study is to initially test the performance of each dataset (PDF, Word, and PowerPoint dataset) through using four machine learning classification algorithms which are (Bayes Net, Random Forest, Random Committee, and OneR). Second goal is experimenting the efficiency of the approach of the deep learning in the tasks of classification and after that, comparing the efficiencies with the efficiencies of traditional machine learning classification methods. Mainly two classification techniques used to maximize the benefits of the classification process, the first one is to use the deep learning algorithm which shows an accuracy of classifying file between (95 and 96%) for three new dataset files and standard machine learning algorithms (OneR, Random forest, Bayes net, and Random Committee ) these algorithm shows accuracy 91% for PDF Dataset using random forest and random committee algorithms, for Word dataset the accuracy is 46% using random committee, and for the last dataset PowerPoint the accuracy is 77% using random forest, Therefore, we will choose Deep learning algorithm because it gives higher results and accuracy than machine learning algorithms.