Search

Breast cancer stands as one of the world's most perilous and formidable diseases, having recently surpassed lung cancer as the most prevalent cancer type. This disease arises when cells in the breast undergo unregulated proliferation, resulting in the formation of a tumor that has the capacity to invade surrounding tissues. It is not confined to a specific gender; both men and women can be diagnosed with breast cancer, although it is more frequently observed in women. Early detection is pivotal in mitigating its mortality rate. The key to curbing its mortality lies in early detection. However, it is crucial to explain the black-box machine learning algorithms in this field to gain the trust of medical professionals and patients. In this study, we experimented with various machine learning models to predict breast cancer using the Wisconsin Breast Cancer Dataset (WBCD) dataset. We applied Random Forest, XGBoost, Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Gradient Boost classifiers, with the Random Forest model outperforming the others. A comparison analysis between the two methods was done after performing hyperparameter tuning on each method. The analysis showed that the random forest performs better and yields the highest result with 99.46% accuracy. After performance evaluation, two Explainable Artificial Intelligence (XAI) methods, SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), have been utilized to explain the random forest machine learning model. [ABSTRACT FROM AUTHOR]

Breast cancer is cancer that forms in the cells of the breasts and is a severe health issue that affects many people around the world, especially since it is the most deadly cancer in women. By finding it early and using new treatments, patients can overcome this challenge and get back to a healthier life. This study proposed a procedure to fine-tune the Convolutional Neural Networks (CNN) model with data preprocessing and augmentation in classifying mammogram images called the Hybrid Mammogram Classification and Detection Pipeline (HMCaD). After using CNN for classification because it brings higher confidence in classifying tasks, the YOLOv8 has been applied for localization subtask to detect abnormal positions with predicted bounding boxes. The database is provided by the Mammographic Image Analysis Society (MIAS) and is protected by the United Kingdom. It comprises 330 samples, including 79 benign, 54 malignant, and 207 normal images. As a result, the classification in our model based on the custom EfficientNetB3 model and seam carving technique received a great validation accuracy, test accuracy, and F1 score throughout three scenarios at 96.73%, 97.59%, and 97.58%, respectively. Furthermore, the area under the Receiver Operating Characteristic (ROC) curve also has a surprise result of 0.96 (i.e. [Formula: see text]). Moreover, YOLOv8 for detecting abnormal positions in our study achieved 83.22% in Intersection over Union (IoU). This led to the research reaching good results in classifying and detecting breast cancer by considering several performance metrics.

When contemplating the improvement of overall performance in machine learning (ML) models, a critical strategy for optimizing data preparation is feature selection (FS). There has been a significant rise in the popularity of metaheuristic FS algorithms in recent times. This can be attributed to their proficiency in accurately identifying and selecting the most relevant features for ML tasks. This study presents three feature selection strategies that utilize metaheuristic algorithms. The methodologies mentioned include the Gravitational Search Optimization Algorithm (GSA), Emperor Penguin Optimization (EPO), and a hybrid approach of GSA and EPO referred to as hGSAEPO. Previous research has explored the use of baseline algorithms for feature selection in various ML tasks. However, there is a lack of investigation regarding their application specifically in breast cancer(BC) classification. A combination of these two has been utilized for the first occasion. The purpose of selecting BC as the study of investigation is due to the reason that this illness is recognized as the second most prevalent cause of mortality in the female population. If the condition is detected in its initial phases, it can be remedied and can assist individuals in evading superfluous medical processes. The procedure of selecting relevant features holds significant importance in the purpose of predicting ailments like BC. The current research presents an innovative methodology that employs three soft-computing algorithms, EPO, GSA, and their proposed hybrid hGSAEPO to efficiently identify significant features while concurrently decreasing the occurrence of irrelevant ones, simplifying overall complexity and enhancing the accuracy. The utilization of these soft computing methodologies and six ML classifiers presents a viable framework for prognostic research through the classification of data instances on Wisconsin Diagnostic Breast Cancer (WDBC). The experimental findings of eight experiments conducted suggest that the suggested approach exhibits exceptional performance in the context of binary classification for BC by computing astounding results like precision of 0.9800, sensitivity of 0.9700, specificity of 0.9887, F1-score of 0.9539, area under the curve(AUC) surpassing 0.998, with an accuracy of 98.31%. We achieved our objectives by presenting a dependable clinical prediction system for healthcare professionals for efficient diagnosis. [ABSTRACT FROM AUTHOR]

The prediction of breast cancer has evolved significantly with the advent of machine learning models, which offer promising tools for early diagnosis and personalized treatment planning. This systematic literature review examines 31 peer-reviewed analyses undertaken between 2019 and 2024, targeting on the integration of enhanced feature selection methods within explainable machine learning models for breast cancer prediction. The primary goal is to assess how feature selection techniques contribute to model accuracy and interpretability, ensuring that predictions are both reliable and understandable to clinicians and researchers. The reviewed studies highlight a trend towards the use of sophisticated feature selection algorithms that refine input data, yielding models that not only enhance prediction accuracy but also generate actionable insights to inform decisions. This is especially important in healthcare, where the explainability of AI models can enhance trust and adoption by medical professionals, potentially improving patient outcomes. Despite these advancements, the review identifies several challenges, including the need for large, diverse datasets to ensure model generalizability and the difficulty of balancing model complexity with interpretability. Furthermore, the integration of these models into clinical workflows remains a significant hurdle due to varying levels of transparency and the potential for bias in feature selection. Gaps in the current literature suggest that future research concentrate on creating developing standardized frameworks for integrating feature selection with explainable models, ensuring that these tools are both effective and widely applicable in clinical settings. This review aims to guide future research and development efforts towards creating more robust, transparent, and clinically useful predictive models for breast cancer, ultimately contributing to more precise and personalized healthcare solutions. [ABSTRACT FROM AUTHOR]

Breast cancer remains a formidable global health challenge, exacting a heavy toll on women's lives and necessitating advanced diagnostic methodologies. This study delves into the domain with an innovative perspective, addressing pertinent limitations in current approaches. Despite significant progress, the prevalence of misclassifications and inadequate diagnostic accuracy persists as a critical concern. Current methods often rely on isolated classification algorithms, leading to suboptimal outcomes and insufficient reliability. To overcome these shortcomings, this research introduces an ensemble learning (voting) framework that reimagines the diagnostic process. This approach leverages a consortium of distinguished convolutional neural network architectures, including DenseNet169, EfficientNetB4, and Xception, collectively enhancing diagnostic precision. By embracing this holistic methodology, the study strives to bridge the existing gap between diagnostic efficiency and clinical reliability. Through meticulous optimization, the proposed model presents a promising trajectory toward significantly elevating the accuracy of breast cancer diagnosis. This study is conducted using the Breast Cancer Histopathological Database (BreakHis) dataset, encompassing diverse magnification factors (40X, 100X, 200X, and 400X), ultimately showcasing a remarkable 98% accuracy in classifying breast cancer images. The findings herald a paradigm shift in diagnostic accuracy, underscoring the potential to revolutionize breast cancer management and bolster the confidence of medical practitioners in their decision-making processes. [ABSTRACT FROM AUTHOR]

Abstract Breast cancer has rapidly increased in prevalence in recent years, making it one of the leading causes of mortality worldwide. Among all cancers, it is by far the most common. Diagnosing this illness manually requires significant time and expertise. Since detecting breast cancer is a time-consuming process, preventing its further spread can be aided by creating machine-based forecasts. Machine learning and Explainable AI are crucial in classification as they not only provide accurate predictions but also offer insights into how the model arrives at its decisions, aiding in the understanding and trustworthiness of the classification results. In this study, we evaluate and compare the classification accuracy, precision, recall, and F1 scores of five different machine learning methods using a primary dataset (500 patients from Dhaka Medical College Hospital). Five different supervised machine learning techniques, including decision tree, random forest, logistic regression, naive bayes, and XGBoost, have been used to achieve optimal results on our dataset. Additionally, this study applied SHAP analysis to the XGBoost model to interpret the model’s predictions and understand the impact of each feature on the model’s output. We compared the accuracy with which several algorithms classified the data, as well as contrasted with other literature in this field. After final evaluation, this study found that XGBoost achieved the best model accuracy, which is 97%.

One of the essential data pre-processing methods for enhancing the performance of machine learning (ML) models is feature selection. Because they choose the most optimal features for ML problems, metaheuristic feature selection algorithms have gained popularity recently. The Gravitational Search Optimization Algorithm (GSOA), Emperor Penguin Optimization (EPO), and an integrated (hGSEPO) algorithm that combines GSOA and EPO are three metaheuristic feature selection algorithms that are presented in this paper. GSOA performs the global search in hGSEPO, and Emperor Penguin Optimizer (EPO) performs a more thorough local search. In order to find influential features while eliminating irrelevant features and reducing complexity, this article introduces a pioneering hybrid approach that combines the two distinct algorithms GSOA and EPO. While the baseline algorithms have been employed for feature selection in a few ML tasks, the hybrid of these two has been used for the first time for breast cancer (BC) classification. The reason for selecting BC as a case of investigation is due to its recognition as the second leading cause of death in women. According to earlier research, the feature selection (FS) stage is crucial when processing large datasets with the goal of forecasting medical conditions like BC. Based on the selection of the most important features necessary to achieve enhanced accuracy, this intelligent classification system divides the data from the benchmark BC Wisconsin Diagnostic Breast Cancer (WDBC) feature set into two classes. Additionally, the intention of the research is to ascertain the minimum quantity of features necessary to attain a higher level of accuracy. The experimental results show that the proposed approach works auspiciously and categorizes with astounding results, with the highest accuracy of 97.66%, 0.9687 sensitivity, 1.000 specificity, 1.000 precision, 0.9516 F1-score, and 0.9980 area under the curve (AUC). [ABSTRACT FROM AUTHOR]

In recent years, breast cancer is observed to be more prevalent among women. Timely and accurate prediction of the disease enables health care professionals to adopt a strong decision-making system in treatment optimization. Thus, this study employed a deep learning-based strategy for efficient breast cancer diagnosis. In this study, the feature extraction is efficiently performed with the Deep CNN and VGG-16 and the classification process has been processed that intends to classify appropriate features by using the newly introduced CBGAT (CNN-Bi-LSTM-GRU-AM) technique that helps to enhance the accuracy of image recognition and to predict the breast cancer without any human intervention. The complete approach uses MIAS and the CBIS-DDSM dataset for the process of training and for the evaluations. The proposed study aims in minimising the cases of human intervention of breast cancer diagnosis. The approach DL architectures comprising both the Deep CNN and VCG-16, for the process of feature extraction from the breast cancer diagnosis. Further, the proposed approach is embedded with the PCA in enhancing the procedures of feature extraction. This PCA is used in the proposed study as a fusion technique. PCA is used as one of a dimensionality reduction technique, used in capturing the more of exact information from the features. The combination of CNN-Bi-LSTM-GRU-AM classification approach used in the study is considered in analysing the sequential information and in capturing the long-term dependencies also used in focusing the salient features. The Deep-CNN and VCG-16 are incorporated for leveraging the strengths of each of the network, and are used in capturing the range of features. This integration aids in enhancing the representation and the discriminative power of the extracted features. Influencing the use of AM in the classification process is one more an added advantage of the proposed approach. This AM allows the model to be focused on the vita regions of features within the images provided as input.The experimental implementation and performance analysis of the proposed system is undertaken. The accuracy of each proposed classification technique is discussed with respect to their dataset. The analytical outcomes explore that the proposed model is more effective than the traditional methods as the proposed model highlights a higher accuracy rate, F1 score, sensitivity, specificity, and Area under the curve (AUC). The proposed also determined the importance of breast cancer prediction. [ABSTRACT FROM AUTHOR]

Breast cancer has rapidly increased in prevalence in recent years, making it one of the leading causes of mortality worldwide. Among all cancers, it is by far the most common. Diagnosing this illness manually requires significant time and expertise. Since detecting breast cancer is a time-consuming process, preventing its further spread can be aided by creating machine-based forecasts. Machine learning and Explainable AI are crucial in classification as they not only provide accurate predictions but also offer insights into how the model arrives at its decisions, aiding in the understanding and trustworthiness of the classification results. In this study, we evaluate and compare the classification accuracy, precision, recall, and F1 scores of five different machine learning methods using a primary dataset (500 patients from Dhaka Medical College Hospital). Five different supervised machine learning techniques, including decision tree, random forest, logistic regression, naive bayes, and XGBoost, have been used to achieve optimal results on our dataset. Additionally, this study applied SHAP analysis to the XGBoost model to interpret the model's predictions and understand the impact of each feature on the model's output. We compared the accuracy with which several algorithms classified the data, as well as contrasted with other literature in this field. After final evaluation, this study found that XGBoost achieved the best model accuracy, which is 97%. [ABSTRACT FROM AUTHOR]

Breast cancer has been life-threatening for many years as it is the common cause of fatality among women. The challenges of screening such tumors through manual approaches can be overcome by computer-aided diagnosis, which aids radiologists in making precise decisions. The selection of significant features is crucial for the estimation of prediction accuracy. This work proposes a hybrid Genetic Algorithm (GA) and Honey Badger Algorithm (HBA) based Deep Neural Network (DNN), HGAHBA-DNN for the concurrent optimal features selection and parameter optimization; further, the optimal features and parameters extracted are fed into the DNN for the prediction of the breast cancer. It fuses the benefits of HBA with parallel processing and efficient feedback with GA's excellent global convergent rate during the processing stages. The aforementioned method is evaluated on the Wisconsin Original Breast Cancer (WOBC), Wisconsin Diagnostic Breast Cancer (WDBC), and the Surveillance, Epidemiology, and End Results (SEER) datasets. Subsequently, the performance is validated using several metrics like accuracy, precision, Recall, and F1-score. The experimental result shows that HGAHBA-DNN obtains accuracy of 99.42%, 99.84%, and 92.44% for the WOBC, WDBC, and SEER datasets respectively, which is much superior to the other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the most common types of cancer, and its prevalence continues to rise every year. Without surgical biopsy, it can effectively provide auxiliary diagnosis and treatment for doctors and reduce the pain of patients by analyzing various indicators of the nucleus to predict whether the mass is benign or not. Therefore, a breast cancer diagnosis model based on LightGBM algorithm is proposed. Firstly, the borderline- synthetic minority oversampling technique (Borderline-SMOTE) is used to improve the problem of imbalanced breast cancer diagnosis data. Secondly, the PWLCM chaotic map, the new inertia weight and the criss-cross algorithm are introduced into the sparrow search algorithm (SSA) to improve it, and then the improved SSA algorithm is used to automatically optimize the parameters of LightGBM. Then, because LightGBM is sensitive to noise, an OVR-Jacobian regularization method is proposed to reduce the noise of LightGBM. Finally, the improved LightGBM hybrid model is used to diagnose breast cancer. The experimental results show that the proposed hybrid model is superior to the common models in the three indicators of mean square error, coefficient of determination and cross-validation score, showing its better diagnostic effect. [ABSTRACT FROM AUTHOR]

Indonesia is an archipelago with the fourth largest population in the world, with a population of 283 million. In Indonesia, breast cancer ranks first in cancer and is the highest contributor to death. Deaths caused by breast cancer can be minimized by screening and early detection to avoid the risk of more severe cancer. Early detection of breast cancer can delay the growth of cancer cells and increase the chances of recovery. This research proposed a machine learning-based application for screening and early detection of breast cancer independently based on perceived symptoms. However, developing breast cancer early detection applications requires a very high level of accuracy to minimize prediction errors. This research focused on finding the optimal accuracy of the machine learning method so that it could predict breast cancer with a very low error rate. This research aimed to improve the performance of classification methods in breast cancer disease prediction using the correlation feature selection approach and hybrid sampling Smote-Tomek Link. This research utilized Support Vector Machine (SVM) and Naive Bayes classification methods with a combination of Smote-Tomek Link hybrid sampling approach and correlation feature selection. Hybrid Sampling Smote-Tomek Link balanced the data by minimizing noise in the data created. At the same time, the correlation feature selection method was used to select relevant or influential attributes with class attributes based on a strong correlation level (≥ 0.6) between input attributes and classes. The results of this study obtained that the SVM method with hybrid sampling and correlation feature selection obtained the best performance compared to the Naive Bayes method and previous research referred to with an accuracy of 96.80%, sensitivity of 96.80%, and specificity of 96.80%. Thus, using the Smote-Tomek Link hybrid sampling approach and correlation feature selection positively impacted the performance increase in the SVM and Naive Bayes methods for breast cancer prediction.

Breast cancer poses a significant health risk for women, demanding early detection to mitigate its mortality impact. Leveraging the power of Deep Learning (DL) in medical imaging, this paper introduces a hybrid model that integrates YOLOv7 and Half UNet for feature extraction. YOLOv7 identifies and localizes potential cancerous regions, while Half UNet focuses on extracting pertinent features with its encoder-decoder structure. The fusion of these discriminative features, coupled with feature selection via Coati Optimization, ensures a comprehensive and optimized dataset. The selected features then feed into the CatBoost classification algorithm, refining parameters iteratively for precise predictions and minimizing the loss function. Evaluation metrics, including precision, recall, specificity, and accuracy, demonstrate the model's superior performance. Notably, the proposed model surpasses existing methods in early-stage breast cancer detection. Beyond numerical metrics, its significance lies in the potential to positively impact patient outcomes and increase survival rates. By amalgamating cutting-edge DL techniques, the model excels in identifying intricate patterns crucial for early cancer detection. The efficient fusion of YOLOv7 and Half UNet, coupled with feature optimization through Coati Optimization, sets this model apart. This research contributes to the evolving landscape of medical imaging and DL applications, emphasizing the potential for enhanced breast cancer diagnosis and improved patient prognoses. [ABSTRACT FROM AUTHOR]

Indonesia is an archipelago with the fourth largest population in the world, with a population of 283 million. In Indonesia, breast cancer ranks first in cancer and is the highest contributor to death. Deaths caused by breast cancer can be minimized by screening and early detection to avoid the risk of more severe cancer. Early detection of breast cancer can delay the growth of cancer cells and increase the chances of recovery. This research proposed a machine learning-based application for screening and early detection of breast cancer independently based on perceived symptoms. However, developing breast cancer early detection applications requires a very high level of accuracy to minimize prediction errors. This research focused on finding the optimal accuracy of the machine learning method so that it could predict breast cancer with a very low error rate. This research aimed to improve the performance of classification methods in breast cancer disease prediction using the correlation feature selection approach and hybrid sampling Smote-Tomek Link. This research utilized Support Vector Machine (SVM) and Naive Bayes classification methods with a combination of Smote-Tomek Link hybrid sampling approach and correlation feature selection. Hybrid Sampling Smote-Tomek Link balanced the data by minimizing noise in the data created. At the same time, the correlation feature selection method was used to select relevant or influential attributes with class attributes based on a strong correlation level (= 0.6) between input attributes and classes. The results of this study obtained that the SVM method with hybrid sampling and correlation feature selection obtained the best performance compared to the Naive Bayes method and previous research referred to with an accuracy of 96.80%, sensitivity of 96.80%, and specificity of 96.80%. Thus, using the Smote-Tomek Link hybrid sampling approach and correlation feature selection positively impacted the performance increase in the SVM and Naive Bayes methods for breast cancer prediction. [ABSTRACT FROM AUTHOR]

This study investigates the Shapley additive explanation (SHAP) of the extreme boosting (XGBoost) model for breast cancer diagnosis. The study employed Wisconsin’s breast cancer dataset, characterized by 30 features extracted from an image of a breast cell. SHAP module generated different explainer values representing the impact of a breast cancer feature on breast cancer diagnosis. The experiment computed SHAP values of 569 samples of the breast cancer dataset. The SHAP explanation indicates perimeter and concave points have the highest impact on breast cancer diagnosis. SHAP explains the XGB model diagnosis outcome showing the features affecting the XGBoost model. The developed XGB model achieves an accuracy of 98.42% [ABSTRACT FROM AUTHOR]

Abstract Women are prone to breast cancer, which is a major cause of death. One out of every eight women has a lifetime risk of developing this cancer. Early diagnosis of this disease is critical and enhances the success rate of cure. It is extremely important to determine which genes are associated with the disease. However, too many features make studies on gene data challenging. In this study, an attention-based multimodal deep learning model was created by combining data from clinical, copy number alteration and gene expression sources. Attention-based deep learning models can analyze mammography images and identify subtle patterns or abnormalities that may indicate the presence of cancer. These models can also integrate patient data, such as age and family history, to improve the accuracy of predictions. The objective of this study is to help breast cancer prediction tasks and improve efficiency by incorporating attention mechanisms. Our suggested methodology employs multimodal data and generates insightful characteristics to improve the prediction of the prognosis for breast cancer. It is a two-phase model; the first phase generates the stacked features using a sigmoid gated attention convolutional neural network, and the second phase uses flatten, dense and dropout processes for bi-modal attention. Based on our findings, the proposed model produced successful results and has the potential to significantly improve breast cancer detection and diagnosis, ultimately leading to better patient outcomes.

Abstract Background Guidelines recommend shared decision making (SDM) for mammography screening for women ≥ 75 and not screening women with 55 years who completed the 2004 Nurses’ Health Study (NHS) questionnaire, we developed (in 2/3 of the cohort, n = 55,533) a model to predict 10-year non-breast cancer (BC) death. We considered 60 mortality risk factors and used best-subsets regression, the Akaike information criterion, and c-index, to identify the best-fitting model. We examined model performance in the remaining 1/3 of the NHS cohort (n = 27,777) and among 17,380 Black Women’s Health Study (BWHS) participants, ≥ 55 years, who completed the 2009 questionnaire. We then included the identified mortality predictors in a previously developed competing risk BC prediction model and examined model performance for predicting BC risk. Results Mean age of NHS development cohort participants was 70.1 years (± 7.0); over 10 years, 3.1% developed BC, 0.3% died of BC, and 20.1% died of other causes; NHS validation cohort participants were similar. BWHS participants were younger (mean age 63.7 years [± 6.7]); over 10-years 3.1% developed BC, 0.4% died of BC, and 11.1% died of other causes. The final non-BC death prediction model included 21 variables (age; body mass index [BMI]; physical function [3 measures]; comorbidities [12]; alcohol; smoking; age at menopause; and mammography use). The final BC prediction model included age, BMI, alcohol and hormone use, family history, age at menopause, age at first birth/parity, and breast biopsy history. When risk factor regression coefficients were applied in the validation cohorts, the c-index for predicting 10-year non-BC death was 0.790 (0.784–0.796) in NHS and 0.768 (0.757–0.780) in BWHS; for predicting 5-year BC risk, the c-index was 0.612 (0.538–0.641) in NHS and 0.573 (0.536–0.611) in BWHS. Conclusions We developed and validated a novel competing-risk model that predicts 10-year non-BC death and 5-year BC risk. Model risk estimates may help inform SDM around mammography screening.

Objective: Predicting the ability of a breast cancer patient to survive was a difficult research problem for many scholars. Since the early dates of the relevant research, significant progress has been recorded in many related areas. For example, with pioneering biomedical technologies, credits to low-cost computer hardware and software, high-quality data is gathered and stored automatically, and lastly, with better analytical methods, that massive data is processed efficiently and effectively. Therefore, the objective of this document is to submit a report on a research project in which we have benefited from the technological developments available to develop predictive models of breast cancer and whether it exists or not. Methods and materials: artificial neural network, support vector machine, decision trees, naïve bayes, and random forest algorithms are used along with the most common statistical method (logistic regression) to build prediction models using a large data set. We also used the Holdout method. To avoid the unbalanced nature of the classes, the parameters of the performance evaluation are predefined. Results: The results show that the Decision Tree (DT) is the top predictor with 89.1% accuracy on the holdout sample, surpassing all prediction accuracy reported in the literature; Artificial Neural Networks (ANN) came out to be the second with 88.9% accuracy; Naïve Bayes (NB) came out to be the third with 83.3% accuracy, Support Vector Machines (SVM) came out to be the fourth with 83.2% accuracy, and the Random Forest (RF) models came out to be the lowest of the five with 71.2% accuracy. Conclusion: A comparative study of multiple predictive models for breast cancer survival using a large set of data and 5-fold cross-validation gave us an insight into the relative ability to predict different data extraction methods. After analyzing the data, we have reached this conclusion: the model is able to help those who need it by predicting whether they have breast cancer or not. Furthermore, the proposed framework is valuable tool in cancer research and clinical practice.

Research work is to discover the rapid requirement of Artificial Intelligence and Statistics in medical research. Objective is to design a diagnostic prediction system that can detect and predict diseases at an early stage from clinical data sets. Some of major diseases leading reasons of death globally are heart disease and cancer. There are different kinds of cancer, in this study we focused on breast cancer and heart disease. Prediction of these diseases at a very early stage is curable and preventive diagnosis can control death rate. Designed two Artificial Intelligence systems for prediction of above-mentioned diseases using statistics and Deep neural networks (i) Combinatorial Learning (CLSDnn) and (ii) an optimized efficient Combinatorial Learning (eCLSDnn). To evaluate the performance of the proposed system conducted experiments on three different data sets, in which two data sets are of breast cancer namely, Wisconsin-data set of UCI Machine Learning repository and AI for Social Good: Women Coders' Bootcamp data set and Cleveland heart disease data set of UCI Machine Learning repository. The proposed architectures of binary classification are validated for 70%–30% data splitting and on K-fold cross validation. Recognition of Malignant cancerous tumors CLSDnn model achieved maximum accuracy of 98.53% for Wisconsin data set, 95.32% for AI for Social Good: Women Coders' data set and 96.72% for Cleveland data set. Recognition of Malignant cancerous tumors eCLSDnn model achieved 99.36% for Wisconsin data set, 97.12% for AI for Social Good: Women Coders' data set and 99.56% for the Cleveland heart disease data set. [ABSTRACT FROM AUTHOR]

In this study, a machine learning (ML)-based decision support approach was developed to identify breast cancer likelihood in patients, based on their background and physiological data. Two ML models, Naïve Bayes and Logistic Regression were used to evaluate the Breast Cancer Surveillance Consortium dataset that had about 9:1 ratio of non-cancer cases ('Class 0') to cancer cases ('Class 1'). We manually built both balanced and unbalanced training datasets and a non-overlapping testing dataset using a stratified sampling method. For each model, we partitioned the prediction results on testing set into two groups, the 'Agree' group included cases where balanced and unbalanced ML predictions agreed, and the remaining cases come under 'Disagree' group. Sensitivity and Positive Predictive Value were used as the prediction performance measures. For Naïve Bayes, the sensitivity of Class 1 in regular versus 'Agree' group increased from 0.687 to 0.936 and for Logistic Regression, it increased from 0.358 to 0.8306. This indicates the 'Agree' group predictions were more accurate and could be labeled as high-confidence ML predictions. The 'Agree' group consisted of 89% cases in the testing set, so the improved prediction performance was applicable for a large portion of the testing dataset. [ABSTRACT FROM AUTHOR]

Women are prone to breast cancer, which is a major cause of death. One out of every eight women has a lifetime risk of developing this cancer. Early diagnosis of this disease is critical and enhances the success rate of cure. It is extremely important to determine which genes are associated with the disease. However, too many features make studies on gene data challenging. In this study, an attention-based multimodal deep learning model was created by combining data from clinical, copy number alteration and gene expression sources. Attention-based deep learning models can analyze mammography images and identify subtle patterns or abnormalities that may indicate the presence of cancer. These models can also integrate patient data, such as age and family history, to improve the accuracy of predictions. The objective of this study is to help breast cancer prediction tasks and improve efficiency by incorporating attention mechanisms. Our suggested methodology employs multimodal data and generates insightful characteristics to improve the prediction of the prognosis for breast cancer. It is a two-phase model; the first phase generates the stacked features using a sigmoid gated attention convolutional neural network, and the second phase uses flatten, dense and dropout processes for bi-modal attention. Based on our findings, the proposed model produced successful results and has the potential to significantly improve breast cancer detection and diagnosis, ultimately leading to better patient outcomes. [ABSTRACT FROM AUTHOR]

Breast cancer is one of the leading causes of death among women worldwide. Many methods have been proposed for automatic breast cancer diagnosis. One popular technique utilizes a classification-based association called Association Classification (AC). However, most AC algorithms suffer from considerable numbers of generated rules. In addition, irrelevant and redundant features may affect the measures used in the rule evaluation process. As such, they could severely affect the accuracy rates in rule mining. Feature selection identifies the optimal subset of features representing a problem in almost the same context as the original features. Feature selection is a critical preprocessing step for data mining as it tends to increase the prediction speed and accuracy of the classification model and thereby increase performance. In this research, an ensemble filter feature selection method and a wrapper feature selection algorithm in conjunction with the AC approach are proposed for undertaking breast cancer classification. The proposed approach employs optimal discriminative feature subsets for breast cancer prediction. Specifically, it first utilizes a new bootstrapping search strategy that effectively selects the most optimal feature subset that considers the overall weighted average of the relative frequency-based evaluation criteria function. We employ a Weighted Average of Relative Frequency (WARF)-based filter method to compute discriminative features from the ensemble results. The adopted filter algorithms utilize the prioritization ranking technique for selecting a subset of informative features that are used for subsequent AC-based disease classification. Another wrapper feature selection method, namely a hybrid Particle Swarm Optimization (PSO)-WARF filter-based wrapper method, is also proposed for feature selection. Two classification models, i.e., WARF-Predictive Classification Based on Associations (PCBA) and hybrid PSO-WARF-PCBA, are subsequently constructed based on the above filter and wrapper-based feature selection methods for breast cancer prediction. The proposed approach of the two models is evaluated using UCI breast cancer datasets. The empirical results indicate that our models achieve impressive performance and outperform a variety of well-known benchmark AC algorithms consistently for breast cancer diagnosis. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer is prevalent in women and the second leading cause of death. Conventional breast cancer detection methods require several laboratory tests and medical experts. Automated breast cancer detection is thus very important for timely treatment. This study explores the influence of various feature selection technique to increase the performance of machine learning methods for breast cancer detection. Experimental results shows that use of appropriate features tend to show highly accurate prediction. Breast cancer is one of the most common invasive cancers in women and it continues to be a worldwide medical problem since the number of cases has significantly increased over the past decade. Breast cancer is the second leading cause of death from cancer in women. The early detection of breast cancer can save human life but the traditional approach for detecting breast cancer disease needs various laboratory tests involving medical experts. To reduce human error and speed up breast cancer detection, an automatic system is required that would perform the diagnosis accurately and timely. Despite the research efforts for automated systems for cancer detection, a wide gap exists between the desired and provided accuracy of current approaches. To overcome this issue, this research proposes an approach for breast cancer prediction by selecting the best fine needle aspiration features. To enhance the prediction accuracy, several feature selection techniques are applied to analyze their efficacy, such as principal component analysis, singular vector decomposition, and chi-square (Chi2). Extensive experiments are performed with different features and different set sizes of features to investigate the optimal feature set. Additionally, the influence of imbalanced and balanced data using the SMOTE approach is investigated. Six classifiers including random forest, support vector machine, gradient boosting machine, logistic regression, multilayer perceptron, and K-nearest neighbors (KNN) are tuned to achieve increased classification accuracy. Results indicate that KNN outperforms all other classifiers on the used dataset with 20 features using SVD and with the 15 most important features using a PCA with a 100% accuracy score. [ABSTRACT FROM AUTHOR]

Machine learning (ML) was used to develop classification models to predict individual tumor patients' outcomes. Binary classification defined whether the tumor was malignant or benign. This paper presents a comparative analysis of machine learning algorithms used for breast cancer prediction. This study used a dataset obtained from the National Cancer Institute (NIH), USA, which contains 1.7 million data records. Classical and deep learning methods were included in the accuracy assessment. Classical decision tree (DT), linear discriminant (LD), logistic regression (LR), support vector machine (SVM), and ensemble techniques (ET) algorithms were used. Probabilistic neural network (PNN), deep neural network (DNN), and recurrent neural network (RNN) methods were used for comparison. Feature selection and its effect on accuracy were also investigated. The results showed that decision trees and ensemble techniques outperformed the other techniques, as they both achieved a 98.7% accuracy. [ABSTRACT FROM AUTHOR]

Background: Guidelines recommend shared decision making (SDM) for mammography screening for women ≥ 75 and not screening women with < 10-year life expectancy. High-quality SDM requires consideration of women's breast cancer (BC) risk, life expectancy, and values but is hard to implement because no models simultaneously estimate older women's individualized BC risk and life expectancy. Methods: Using competing risk regression and data from 83,330 women > 55 years who completed the 2004 Nurses' Health Study (NHS) questionnaire, we developed (in 2/3 of the cohort, n = 55,533) a model to predict 10-year non-breast cancer (BC) death. We considered 60 mortality risk factors and used best-subsets regression, the Akaike information criterion, and c-index, to identify the best-fitting model. We examined model performance in the remaining 1/3 of the NHS cohort (n = 27,777) and among 17,380 Black Women's Health Study (BWHS) participants, ≥ 55 years, who completed the 2009 questionnaire. We then included the identified mortality predictors in a previously developed competing risk BC prediction model and examined model performance for predicting BC risk. Results: Mean age of NHS development cohort participants was 70.1 years (± 7.0); over 10 years, 3.1% developed BC, 0.3% died of BC, and 20.1% died of other causes; NHS validation cohort participants were similar. BWHS participants were younger (mean age 63.7 years [± 6.7]); over 10-years 3.1% developed BC, 0.4% died of BC, and 11.1% died of other causes. The final non-BC death prediction model included 21 variables (age; body mass index [BMI]; physical function [3 measures]; comorbidities [12]; alcohol; smoking; age at menopause; and mammography use). The final BC prediction model included age, BMI, alcohol and hormone use, family history, age at menopause, age at first birth/parity, and breast biopsy history. When risk factor regression coefficients were applied in the validation cohorts, the c-index for predicting 10-year non-BC death was 0.790 (0.784–0.796) in NHS and 0.768 (0.757–0.780) in BWHS; for predicting 5-year BC risk, the c-index was 0.612 (0.538–0.641) in NHS and 0.573 (0.536–0.611) in BWHS. Conclusions: We developed and validated a novel competing-risk model that predicts 10-year non-BC death and 5-year BC risk. Model risk estimates may help inform SDM around mammography screening. [ABSTRACT FROM AUTHOR]

Simple Summary: This paper presents a breast cancer detection approach where the convoluted features from a convolutional neural network are utilized to train a machine learning model. Results demonstrate that use of convoluted features yields better results than the original features to classify malignant and benign tumors. Breast cancer is a common cause of female mortality in developing countries. Screening and early diagnosis can play an important role in the prevention and treatment of these cancers. This study proposes an ensemble learning-based voting classifier that combines the logistic regression and stochastic gradient descent classifier with deep convoluted features for the accurate detection of cancerous patients. Deep convoluted features are extracted from the microscopic features and fed to the ensemble voting classifier. This idea provides an optimized framework that accurately classifies malignant and benign tumors with improved accuracy. Results obtained using the voting classifier with convoluted features demonstrate that the highest classification accuracy of 100% is achieved. The proposed approach revealed the accuracy enhancement in comparison with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Image classification is widely used to build predictive models for breast cancer diagnosis. Most existing approaches overwhelmingly rely on deep convolutional networks to build such diagnosis pipelines. These model architectures, although remarkable in performance, are black-box systems that provide minimal insight into the inner logic behind their predictions. This is a major drawback as the explainability of prediction is vital for applications such as cancer diagnosis. In this paper, we address this issue by proposing an explainable machine learning pipeline for breast cancer diagnosis based on ultrasound images. We extract first- and second-order texture features of the ultrasound images and use them to build a probabilistic ensemble of decision tree classifiers. Each decision tree learns to classify the input ultrasound image by learning a set of robust decision thresholds for texture features of the image. The decision path of the model predictions can then be interpreted by decomposing the learned decision trees. Our results show that our proposed framework achieves high predictive performance while being explainable.

Although blood DNA methylation (DNAm) profiles are reported to be associated with breast cancer incidence, they have not been widely used in breast cancer risk assessment. Among a breast cancer case–cohort of 2774 women (1551 cases) in the Sister Study, we used candidate CpGs and DNAm estimators of physiologic characteristics to derive a methylation‐based breast cancer risk score, mBCRS. Overall, 19 CpGs and five DNAm estimators were selected using elastic net regularization to comprise mBCRS. In a test set, higher mBCRS was positively associated with breast cancer incidence, showing similar strength to the polygenic risk score (PRS) based on 313 single nucleotide polymorphisms (313 SNPs). Area under the curve for breast cancer prediction was 0.60 for self‐reported risk factors (RFs), 0.63 for PRS, and 0.63 for mBCRS. Adding mBCRS to PRS and RFs improved breast cancer prediction from 0.66 to 0.71. mBCRS findings were replicated in a nested case–control study within the EPIC‐Italy cohort. These results suggest that mBCRS, a risk score derived using blood DNAm, can be used to enhance breast cancer prediction.

PurposeAccurate risk assessment is necessary for decision-making around breast cancer prevention. We aimed to develop a breast cancer prediction model for postmenopausal women that would take into account their individualized competing risk of non-breast cancer death.MethodsWe included 73,066 women who completed the 2004 Nurses' Health Study (NHS) questionnaire (all ≥57 years) and followed participants until May 2014. We considered 17 breast cancer risk factors (health behaviors, demographics, family history, reproductive factors) and 7 risk factors for non-breast cancer death (comorbidities, functional dependency) and mammography use. We used competing risk regression to identify factors independently associated with breast cancer. We validated the final model by examining calibration (expected-to-observed ratio of breast cancer incidence, E/O) and discrimination (c-statistic) using 74,887 subjects from the Women's Health Initiative Extension Study (WHI-ES; all were ≥55 years and followed for 5 years).ResultsWithin 5 years, 1.8 % of NHS participants were diagnosed with breast cancer (vs. 2.0 % in WHI-ES, p = 0.02), and 6.6 % experienced non-breast cancer death (vs. 5.2 % in WHI-ES, p

Breast cancer is often a fatal disease that has a substantial impact on the female mortality rate. Rapidly spreading breast cancer is due to the abnormal growth of malignant cells in the breast. Early detection of breast cancer can increase treatment opportunities and patient survival rates. Various screening methods with computer-aided detection systems have been developed for the effective diagnosis and treatment of breast cancer. Image data plays an important role in the medical and health industry. Features are extracted from image datasets through deep learning, as deep learning techniques extract features more accurately and rapidly than other existing methods. Deep learning effectively assists existing methods, such as mammogram screening and biopsy, in examining and diagnosing breast cancer. This paper proposes an Internet of Medical Things (IoMT) cloud-based model for the intelligent prediction of breast cancer stages. The proposed model is employed to detect breast cancer and its stages. The experimental results demonstrate 98.86% and 97.81% accuracy for the training and validation phases, respectively. In addition, they demonstrate accuracies of 99.69%, 99.32%, 98.96%, and 99.32% for detecting ductal carcinoma, lobular carcinoma, mucinous carcinoma, and papillary carcinoma. The results of the proposed intelligent prediction of breast cancer stages empowered with the deep learning (IPBCS-DL) model exhibits higher accuracy than existing state-of-the-art methods, indicating its potential to lower the breast cancer mortality rate.

Image classification is widely used to build predictive models for breast cancer diagnosis. Most existing approaches overwhelmingly rely on deep convolutional networks to build such diagnosis pipelines. These model architectures, although remarkable in performance, are black-box systems that provide minimal insight into the inner logic behind their predictions. This is a major drawback as the explainability of prediction is vital for applications such as cancer diagnosis. In this paper, we address this issue by proposing an explainable machine learning pipeline for breast cancer diagnosis based on ultrasound images. We extract first- and second-order texture features of the ultrasound images and use them to build a probabilistic ensemble of decision tree classifiers. Each decision tree learns to classify the input ultrasound image by learning a set of robust decision thresholds for texture features of the image. The decision path of the model predictions can then be interpreted by decomposing the learned decision trees. Our results show that our proposed framework achieves high predictive performance while being explainable. [ABSTRACT FROM AUTHOR]

Abstract Background The abundance of molecular profiling of breast cancer tissues entailed active research on molecular marker-based early diagnosis of metastasis. Recently there is a surging interest in combining gene expression with gene networks such as protein-protein interaction (PPI) network, gene co-expression (CE) network and pathway information to identify robust and accurate biomarkers for metastasis prediction, reflecting the common belief that cancer is a systems biology disease. However, controversy exists in the literature regarding whether network markers are indeed better features than genes alone for predicting as well as understanding metastasis. We believe much of the existing results may have been biased by the overly complicated prediction algorithms, unfair evaluation, and lack of rigorous statistics. In this study, we propose a simple approach to use network edges as features, based on two types of networks respectively, and compared their prediction power using three classification algorithms and rigorous statistical procedure on one of the largest datasets available. To detect biomarkers that are significant for the prediction and to compare the robustness of different feature types, we propose an unbiased and novel procedure to measure feature importance that eliminates the potential bias from factors such as different sample size, number of features, as well as class distribution. Results Experimental results reveal that edge-based feature types consistently outperformed gene-based feature type in random forest and logistic regression models under all performance evaluation metrics, while the prediction accuracy of edge-based support vector machine (SVM) model was poorer, due to the larger number of edge features compared to gene features and the lack of feature selection in SVM model. Experimental results also show that edge features are much more robust than gene features and the top biomarkers from edge feature types are statistically more significantly enriched in the biological processes that are well known to be related to breast cancer metastasis. Conclusions Overall, this study validates the utility of edge features as biomarkers but also highlights the importance of carefully designed experimental procedures in order to achieve statistically reliable comparison results.

Although blood DNA methylation (DNAm) profiles are reported to be associated with breast cancer incidence, they have not been widely used in breast cancer risk assessment. Among a breast cancer case–cohort of 2774 women (1551 cases) in the Sister Study, we used candidate CpGs and DNAm estimators of physiologic characteristics to derive a methylation‐based breast cancer risk score, mBCRS. Overall, 19 CpGs and five DNAm estimators were selected using elastic net regularization to comprise mBCRS. In a test set, higher mBCRS was positively associated with breast cancer incidence, showing similar strength to the polygenic risk score (PRS) based on 313 single nucleotide polymorphisms (313 SNPs). Area under the curve for breast cancer prediction was 0.60 for self‐reported risk factors (RFs), 0.63 for PRS, and 0.63 for mBCRS. Adding mBCRS to PRS and RFs improved breast cancer prediction from 0.66 to 0.71. mBCRS findings were replicated in a nested case–control study within the EPIC‐Italy cohort. These results suggest that mBCRS, a risk score derived using blood DNAm, can be used to enhance breast cancer prediction. [ABSTRACT FROM AUTHOR]

Machine learning (ML) was used to develop classification models to predict individual tumor patients’ outcomes. Binary classification defined whether the tumor was malignant or benign. This paper presents a comparative analysis of machine learning algorithms used for breast cancer prediction. This study used a dataset obtained from the National Cancer Institute (NIH), USA, which contains 1.7 million data records. Classical and deep learning methods were included in the accuracy assessment. Classical decision tree (DT), linear discriminant (LD), logistic regression (LR), support vector machine (SVM), and ensemble techniques (ET) algorithms were used. Probabilistic neural network (PNN), deep neural network (DNN), and recurrent neural network (RNN) methods were used for comparison. Feature selection and its effect on accuracy were also investigated. The results showed that decision trees and ensemble techniques outperformed the other techniques, as they both achieved a 98.7% accuracy.

Breast cancer is type of tumor that occurs in the tissues of the breast. It is most common type of cancer found in women around the world and it is among the leading causes of deaths in women. This article presents the comparative analysis of machine learning, deep learning and data mining techniques being used for the prediction of breast cancer. Many researchers have put their efforts on breast cancer diagnoses and prognoses, every technique has different accuracy rate and it varies for different situations, tools and datasets being used. Our main focus is to comparatively analyze different existing Machine Learning and Data Mining techniques in order to find out the most appropriate method that will support the large dataset with good accuracy of prediction. The main purpose of this review is to highlight all the previous studies of machine learning algorithms that are being used for breast cancer prediction and this article provides the all necessary information to the beginners who want to analyze the machine learning algorithms to gain the base of deep learning.