Analysis and Classification of Biomedical Data Using Machine Learning Techniques

Breast Cancer (BC) is the second most common cancer in women after skin cancer and has become a major health issue. As a result, it is very important to diagnose BC correctly and categorizing the tumors into malignant or benign groups. We know that Machine Learning (ML) techniques have unique advantages and that is why they are widely used to analyze complex BC dataset and predict the disease. Wisconsin Diagnosis Breast Cancer (WDBC) dataset has been used to develop predictive models for BC by researchers in this field. The dataset has 573 instances and 32 features. In this paper, we have proposed a method for analyzing and predicting BC on the same dataset using Apache Spark. This big data framework is a very powerful tool for working on huge volume of data, such as healthcare data [4]. Principle Component Analysis (PCA) has been applied on the dataset for selecting the most important features. We have run experiments with top 6 and 10 features. The experiments are executed on Hadoop cluster, a cloud platform provided by the Electrical Engineering and Computer Science (EECS) department of University of Cincinnati. We have also made a comparison between the performance of different machine learning techniques: Decision Tree and Random Forest Classifier. We have set the performance of Decision Tree with top 10 features as a benchmark in our work. Random forest Classifier performs better than Decision Tree algorithm with top 6 as well as top 10 features. Random Forest achieves 97.52 % accuracy using top 10 features. Our results show that selecting the right features significantly improves accuracy in predicting BC.

Breast cancer is the second largest cause of cancer death among U.S. women and the leading cause of cancer death among women worldwide. Genome-wide association studies (GWAS) have identified several genetic variants associated with susceptibility to breast cancer, but these still explain less than half of the estimated genetic contribution to the disease. Combinations of variants (i.e. genetic interactions) may play an important role in breast cancer susceptibility. However, due to a lack of statistical power, the current tests for genetic interactions from GWAS data mainly leverage prior knowledge to focus on small sets of genes or SNPs that are known to have an association with breast cancer. Thus, many genetic interactions, particularly among novel variants, remain understudied. Reverse-genetic interaction screens in model organisms have shown that genetic interactions frequently cluster into highly structured motifs, where members of the same pathway share similar patterns of genetic interactions. Based on this key observation, we recently developed a method called BridGE to search for such structured motifs in genetic networks derived from GWAS studies and identify pathway-level genetic interactions in human populations. We applied BridGE to six independent breast cancer cohorts and identified significant pathway-level interactions in five cohorts. Joint analysis across all five cohorts revealed a high confidence consensus set of genetic interactions with support in multiple cohorts. The discovered interactions implicated the glutathione conjugation, vitamin D receptor, purine metabolism, mitotic prometaphase, and steroid hormone biosynthesis pathways as major modifiers of breast cancer risk. Notably, while many of the pathways identified by BridGE show clear relevance to breast cancer, variants in these pathways had not been previously discovered by traditional single variant association tests, or single pathway enrichment analysis that does not consider SNP-SNP interactions.

Machine Learning Techniques for Breast Cancer Prediction

<p>Breast cancer is ranked as a significant cause of mortality among females globally. Its complex nature poses principal challenges for physicians and researchers for rapid diagnosis and prognosis. Hence, machine learning algorithms are employed to forecast and identify diseases. This study discusses the comparative analysis of seven machine learning models, e.g., logistic regression (LR), support vector machine (SVM), k-nearest neighbor classifier (KNN), decision tree classifier (DT), random forest classifier (RF), Naïve Bayes (NB), and artificial neural network (ANN) to predict breast cancer using Wisconsin breast cancer and breast cancer datasets. In the Wisconsin breast cancer dataset, KNN depicted 99% accuracy, followed by RF (98%), SVM (96%), NB (96%), LR (96%), ANN (93%), and DT (92%). On the contrary, in the breast cancer (BC) dataset, the highest accuracy was achieved by LR at 83%, and the lowest was achieved by DT (65%), which depicted that the numeric dataset WBC has better accuracy than the breast cancer dataset.</p>

Breast cancer is one of the leading causes of increasing deaths in women worldwide. The complex nature (microcalcification and masses) of breast cancer cells makes it quite difficult for radiologists to diagnose it properly. Subsequently, various computer-aided diagnosis (CAD) systems have previously been developed and are being used to aid radiologists in the diagnosis of cancer cells. However, due to intrinsic risks associated with the delayed and/or incorrect diagnosis, it is indispensable to improve the developed diagnostic systems. In this regard, machine learning has recently been playing a potential role in the early and precise detection of breast cancer. This paper presents a new machine learning-based framework that utilizes the Random Forest, Gradient Boosting, Support Vector Machine, Artificial Neural Network, and Multilayer Perception approaches to efficiently predict breast cancer from the patient data. For this purpose, the Wisconsin Diagnostic Breast Cancer (WDBC) dataset has been utilized and classified using a hybrid Multilayer Perceptron Model (MLP) and 5-fold cross-validation framework as a working prototype. For the improved classification, a connection-based feature selection technique has been used that also eliminates the recursive features. The proposed framework has been validated on two separate datasets, i.e., the Wisconsin Prognostic dataset (WPBC) and Wisconsin Original Breast Cancer (WOBC) datasets. The results demonstrate improved accuracy of 99.12% due to efficient data preprocessing and feature selection applied to the input data.

In the developing world, cancer death is one of the major problems for humankind. Even though there are many ways to prevent it before happening, some cancer types still do not have any treatment. One of the most common cancer types is breast cancer, and early diagnosis is the most important thing in its treatment. Accurate diagnosis is one of the most important processes in breast cancer treatment. In the literature, there are many studies about predicting the type of breast tumors. In this research paper, data about breast cancer tumors from Dr. William H. Walberg of the University of Wisconsin Hospital were used for making predictions on breast tumor types. Data visualization and machine learning techniques including logistic regression, k-nearest neighbors, support vector machine, naïve Bayes, decision tree, random forest, and rotation forest were applied to this dataset. R, Minitab, and Python were chosen to be applied to these machine learning techniques and visualization. The paper aimed to make a comparative analysis using data visualization and machine learning applications for breast cancer detection and diagnosis. Diagnostic performances of applications were comparable for detecting breast cancers. Data visualization and machine learning techniques can provide significant benefits and impact cancer detection in the decision-making process. In this paper, different machine learning and data mining techniques for the detection of breast cancer were proposed. Results obtained with the logistic regression model with all features included showed the highest classification accuracy (98.1%), and the proposed approach revealed the enhancement in accuracy performances. These results indicated the potential to open new opportunities in the detection of breast cancer.

To estimate the impact of smoking-attributable cancer mortality on trends in cancer mortality in New South Wales (NSW), Australia, between 1972 and 2008. The study is a retrospective analysis of cancer mortality in NSW using NSW Central Cancer Registry data. Smoking-attributable cancer deaths were estimated using the smoking impact ratio method, which provides an indirect estimate of exposure to tobacco in the NSW population using lung cancer mortality. Trends in age-standardised cancer mortality rates by cancer type and the number of years of life lost due to smoking-attributable cancer deaths were estimated. In NSW, the cancer mortality rate decreased in males by 26% and females by 19% between 1989 and 2008. Nearly half (44%) of the decrease for males was a result of the decline in smoking-attributable cancer deaths. Despite a decline in the female all-cancer mortality rate, the smoking-attributable cancer mortality rate increased from 20.3 per 100 000 to 26.8 per 100 000 between 1989 and 2008. Smoking-attributable cancer deaths in women increased from around 150 per year in the early 1970s to 1186 in 2008; for men, the number remained stable at just over 2000 deaths per year since the 1980s. Although the lung cancer mortality rate declined in men, lung cancer remains the largest cause of cancer death. Lung cancer has overtaken breast cancer to be the largest cause of cancer death among women, with 17.1% (n = 998) of cancer deaths due to lung cancer in 2008. Despite declining all-cancer mortality in NSW, around 3330 cancer deaths in 2008 were due to the accumulated hazard of smoking in current and ex-smokers. This highlights the importance of tobacco control as part of a comprehensive cancer control plan.

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.

The major consequence of breast cancer is death. It has been proven in many studies that machine learning techniques are more efficient in diagnosing breast cancer. These algorithms have also been used to estimate a person's likelihood of surviving breast cancer. In this study, we employed machine learning algorithms to predict breast cancer. A total of 569 breast cancer datasets were obtained from kaggle sites. Some of the machine learning algorithms that we use are K-Nearest Neighbor (KNN), besides Random Forest (RF), there is also Gradient Boosting (GB), then Gaussian Naive Bayes (GNB), Vector Support Machine (SVM), and then Logistic Regression (LR). Before algorithms were used to train and test breast cancer datasets, StandardScaler was leveraged to transform training datasets and test datasets for improved algorithm performance. As a result of this utilization, the performance measurement carried out succeeded in producing high accuracy. The highest results were obtained from the Logistic Regression algorithm with an accuracy value of 99%. The value of precison is 99% benign, and 100% malignant. The recall results are 100% benign, and 98% malignant. The F1-Score results show 99% benign, and 99% malignant. It is hoped that this research can help the medical party to determine the next step in dealing with breast cancer.

Breast cancer is the second largest cause of cancer deaths among women. At the same time, it is also among the most curable cancer types if it can be diagnosed early. The automatic diagnosis of breast cancer is an important, real-world medical problem. In this article is introduced a new approach for diagnosis of breast cancer. The proposed approach uses Fuzzy c-means (FCM) algorithm and pattern recognition method. Algorithm has been applied to breast cancer clinic instances obtained from the University of Wisconsin. Using FCM algorithm clinic instances are grouped into two clusters, one with benign instances and other with malign instances. Further, input data are divided in train data and test data and success of each is evaluated. In pattern recognition method each input test data is assigned to one of the clusters obtained from the process of FCM classification. The proposed system has showed that the recommended system has a high accuracy.

Significant advancements have been achieved recently in the use of artificial intelligence (AI) to solve healthcare-related problems. A potential method for identifying and treating many illnesses is machine learning (ML). The “Breast Cancer Dataset” was used in this work to perform classification tasks using ML techniques including Support Vector Machine (SVM), Random Forest (RF) and MultiLayer Perceptron (MLP) for identifying the forms of breast cancer, either Benign or Malignant. The SVM, RF, and MLP achieved impressive PR scores exceeding 0.98. However, MLP exhibited superior performance among these algorithms, achieving an exceptional AUC value of 99.71. Conversely, SVM slightly outperformed the other algorithms in terms of training accuracy, with a value of 97.90%. This work used shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME) to shed light on how these categorization algorithms made judgments. These interpretability methodologies showed that the majority of characteristics consistently predicted the presence of malignant or benign cancer types. This study demonstrates how ML algorithms' decision-making procedures may be understood, possibly promoting the use of ML in clinical settings for medical diagnosis.

Breast cancer (BC) is one of the most common cancers among women worldwide, representing the majority of new cancer cases and cancer-related deaths according to global statistics, making it a significant public health problem in today’s society. The early diagnosis of BC can improve the prognosis and chance of survival significantly, as it can promote timely clinical treatment to patients. Further accurate classification of benign tumours can prevent patients undergoing unnecessary treatments. Thus, the correct diagnosis of BC and classification of patients into malignant or benign groups is the subject of much research. Because of its unique advantages in critical features detection from complex BC datasets, machine learning (ML) is widely recognised as the methodology of choice in BC pattern classification and forecast modelling. In this paper, we aim to review ML techniques and their applications in BC diagnosis and prognosis. Firstly, we provide an overview of ML techniques including artificial neural networks (ANNs), support vector machines (SVMs), decision trees (DTs), and k-nearest neighbors (k-NNs). Then, we investigate their applications in BC. Our primary data is drawn from the Wisconsin breast cancer database (WBCD) which is the benchmark database for comparing the results through different algorithms. Finally, a healthcare system model of our recent work is also shown.

An immune-inspired semi-supervised algorithm for breast cancer diagnosis

Passive non-invasive sensing signals from wearable devices and smartphones are typically collected continuously without user input. This passive and continuous data collection makes these signals suitable for moment-by-moment monitoring of health-related outcomes, disease diagnosis, and prediction modeling. A growing number of studies have utilized machine learning (ML) approaches to predict and analyze health indicators and diseases using passive non-invasive signals collected via wearable devices and smartphones. This systematic review identified peer-reviewed journal articles utilizing ML approaches for digital phenotyping and measuring digital biomarkers to analyze, screen, identify, and/or predict health-related outcomes using passive non-invasive signals collected from wearable devices or smartphones. PubMed, PubMed with Mesh, Web of Science, Scopus, and IEEE Xplore were searched for peer-reviewed journal articles published up to June 2024, identifying 66 papers. We reviewed the study populations used for data collection, data acquisition details, signal types, data preparation steps, ML approaches used, digital phenotypes and digital biomarkers, and health outcomes and diseases predicted using these ML techniques. Our findings highlight the promising potential for objective tracking of health outcomes and diseases using passive non-invasive signals collected from wearable devices and smartphones with ML approaches for characterization and prediction of a range of health outcomes and diseases, such as stress, seizure, fatigue, depression, and Parkinson’s disease. Future studies should focus on improving the quality of collected data, addressing missing data challenges, providing better documentation on study participants, and sharing the source code of the implemented methods and algorithms, along with their datasets and methods, for reproducibility purposes.

Diabetes is a major chronic syndrome caused by a series of metabolic abnormalities in which blood glucose levels are abnormally high for an indeterminate amount of time. It influences various organs in the human body, resulting in a variety of complex diseases such as stroke, renal disease, pulmonary embolism, eyesight, and so on. Diabetes Disorders (DD) are presently one of the healthcare top causes of mortality. Predictive analytics in the health care system is a huge obstacle, but if accurate early prediction is achieved, the potential risk and degree of diabetes may be significantly decreased. Machine learning (ML) techniques are now used to analyze medical datasets at an earlier stage of life in keeping people safe. In this research, we utilized several ML approaches notably Logistic Regression, Decision Tree (DT), XGBoost, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest (RF) on PIMA Indian Diabetes Dataset in order to monitor and evaluate their performances in diabetes prediction. The performance of the various ML algorithms employed in this research suggests which algorithm is most suitable in diabetes prediction. It is observed that among all the models XGBoost had outperformed the other ML techniques with an accuracy of 80.73% while SVM was the second-best performing model with a classification accuracy of 80.21%. Thus, employing ML techniques, this study aims to assist doctors as well as clinicians in the early detection of diabetes.