According to the WHO, Cancer is a prominent cause of mortality worldwide, accounting for ~ 10 million fatalities at the end of 2020. The most common types of cancers include Lung, Breast, CNS, Leukemia, Colon, and Cervical Cancer. Early detection of cancer can decrease the death toll. According to the study, if the cancer is identified at its early stage, the death rate can be reduced to ~85%. In order to reduce the death toll, machine learning (ML) emerges as a significant solution. When it comes to cancer research with ML, biopsy and microarray data come into the front. The biopsy data is less useful as it excludes a patient’s genetic information. However, due to the genetic information, the microarray data emerges as a solution to detecting cancer disease. Dealing with microarray data also has some consequences, and high dimensionality is one of them. This article reports an ML-based ensemble model to tackle microarray data issues and provide an effective model for cancer detection. The reported model uses Minimum Redundancy Maximum Relevance (MRMR) as the feature selection algorithm. The Whale Optimization Algorithm (WOA) is implemented for the featured dataset to select the optimistic number of features without affecting microarray data relevance. Then, four ML-based classification models, including Support Vector Machine, Decision Tree, Multi-Layer Perceptron, and Random Forest, are applied as the base learners to make initial predictions. Finally, the voting ensemble technique is applied to the initial prediction to develop an ensemble model for cancer prediction. The proposed En-MinWhale model is evaluated over six different types of cancer microarray datasets, including Lung, Leukemia, Ovarian, CNS, Breast, and Colon Cancer. Finally, the performance of the proposed model is evaluated using 11 various evaluative parameters, including accuracy, precision, specificity, sensitivity, F-β score, etc. The En-MinWhale model shows 94.09%, 95.83%, 94.86%, 95.00%, 94.85%, and 96.77% accuracy for Lung, Leukemia, Ovarian, CNS, Breast, and Colon Cancer datasets, respectively, that outperforms other considered hybrid models and can help out the physicians in Cancer diagnosis.

Objective: The cancer death rate has accelerated at an alarming rate, making accurate diagnosis at the primary stages crucial to enhance prognosis. This has deepened the issue of cancer mortality, which is already at an exponential scale. It has been observed that concentration on datasets drawn from supporting primary sources using machine learning algorithms brings the accuracy expected for cancer diagnosis. Methods: This research presents an innovative cancer classification technique that combines fast minimum redundancy-maximum relevance-based feature selection with Binary Portia Spider Optimization Algorithm to optimize features. The features selected, with the aid of fast mRMR and tested with a range of classifiers, Support Vector Machine, Weighted Support Vector Machine, Extreme Gradient Boosting, Adaptive Boosting, and Random Forest classifier, are tested for comprehensively proofed performance. Results: The classification efficiency of the advanced model is tested on six different cancer datasets that exhibit classification challenges. The empirical analysis confirms that the proposed methodology FmRMR-BPSOA is effective since it reached the highest accuracy of 99.79%. The result is of utmost significance as the proposed model emphasizes the need for alternative and highly efficient greater precision cancer diagnosis. The classification accuracy concludes that the model holds great promise for real-life medical implementations.

Relapse and metastasis occur in 30–40% of breast cancer patients, even after targeted treatments like trastuzumab for HER2-positive breast cancer. Accurate individual prognosis is essential for determining appropriate adjuvant treatment and early intervention. This study aims to enhance relapse and metastasis prediction using an innovative framework with machine learning (ML) and ensemble learning (EL) techniques. The developed framework is analyzed using The Cancer Genome Atlas (TCGA) data, which has 123 HER2-positive breast cancer patients. Our two-stage experimental approach first applied six basic ML models (support vector machine, logistic regression, decision tree, random forest, adaptive boosting, and extreme gradient boosting) and then ensembled these models using weighted averaging, soft voting, and hard voting techniques. The weighted averaging ensemble approach achieved enhanced performances of 88.46% accuracy, 89.74% precision, 94.59% sensitivity, 73.33% specificity, 92.11% F-Value, 71.07% Mathew’s correlation coefficient, and an AUC of 0.903. This framework enables the accurate prediction of relapse and metastasis in HER2-positive breast cancer patients using H&E images and clinical data, thereby assisting in better treatment decision-making.

The second leading cause of death for women is breast cancer, which is growing. Some cancer cells may remain in the body, so relapse is possible even if treatment begins soon after diagnosis. Since there are now many machine learning (ML) approaches to recurrence prediction in breast cancer, it is important to compare and contrast them to find the most effective one. Datasets with many features often lead to incorrect predictions because of this. In this study, correlation-based feature selection (CFS) and the flower pollination algorithm (FPA) are used to improve the quality of the wisconsin prognostic breast cancer (WPBC) and University Medical Centre, Institute of Oncology (UMCIO) breast cancer relapse datasets respectively. Data imputation, scaling, pre-process raw data. The second stage uses CFS to select discriminative features based on important feature correlations. The FPA chose the optimum attribute combination for the most precise answer. We tested the approach using 10-fold cross-validation stratification. Various trials show 84.85% and 83.92% accuracy on the WPBC and UMCIO breast cancer relapse datasets, respectively. The hybrid method performed well in feature selection, increasing the accuracy of the relapse classification for breast cancer.

Diagnosis and prognosis are especially difficult areas of medical research related to cancer due to the high incidence of breast cancer, which has surpassed all other cancers in terms of female mortality. Another factor that has a substantial influence on the quality of life of cancer patients is the fear that they may experience a relapse of their disease. The objective of the study is to give medical practitioners a more effective strategy for using ensemble learning techniques to forecast when breast cancer may recur. This research aimed to investigate the usage of deep neural networks (DNNs) and artificial neural networks (ANNs) in addition to machine learning (ML) based approaches, including bagging, averaging, and voting, to enhance the efficacy of breast cancer relapse diagnosis on two breast cancer relapse datasets. Results from the empirical study demonstrate that the proposed ensemble learning-enabled approach improves accuracies by 96.31% and 95.81%, precisions by 96.70% and 96.15%, sensitivities by 98.88% and 98.68%, specificities by 84.62% in both, F1-scores by 97.78% and 97.40%, and area under the curve (AUCs) of 0.987 and 0.978, with University Medical Centre, Institute of Oncology (UMCIO) and Wisconsin prognostic breast cancer (WPBC) datasets respectively. Consequently, these improved disease outcomes may encourage physicians to use this model to make better treatment choices.