Search

• A soft-computing and machine learning based medical decision support system is proposed for breast cancer disease classification. • Two soft-computing algorithms eagle strategy optimization (ESO) algorithm and the gravitational search optimization (GSO) algorithm are employed for the first time for this problem. A novel intelligent classification approach based on these two algorithms for breast cancer infection is also proposed. • 12 experiments have been performed using three soft-computing algorithms(for feature selection) and 6 state-of-the-art machine learning classifier(for classification).WDBC dataset is used for the method evaluation. • We have been able to attain astonishing results with accuracy up to 98.9578%, sensitivity up to 0.9696, specificity up to 1.000, precision 1.000, F1- score up to 0.9696, and an AUC 0.9980(close to maximum i.e., 1.0000). Feature selection, which picks the optimal subset of characteristics related to the target data by deleting unnecessary data, is one of the most important aspects of the machine learning area. A major part of big data preprocessing is feature selection (reduction). There are 2n alternative feature subsets for every n features, making it difficult to choose the best set of features from a dataset using typical feature selection techniques. Consequently, the present study proposes and suggests a unique feature selection method based on the Eagle Strategy(ESO) Optimization, Gravitational Search Optimization (GSO) algorithm, and their hybrid algorithm. We chose this infection as our subject of investigation since the number of women with breast cancer is increasing rapidly on a global scale. After lung cancer, which affects more women than any other kind of cancer, breast cancer is the second leading cause of cancer mortality. The goal of this study is to categorize breast cancer into two groups using the benchmark feature set (Wisconsin Diagnostic Breast Cancer (WDBC)) and to choose the fewest features (feature selection) to achieve maximum accuracy. This work also provides a hybrid technique for finding important features that combines two algorithms, ESO and the GSO algorithm, while reducing insignificant characteristics (features) and complexity. Soft computing technologies and machine learning algorithms provide a framework for prognostic research by classifying data instances as relevant or irrelevant depending on cancer severity. Thus, this work presented a new approach for classifying breast cancer tumors. In this research, we coupled soft computing methodologies—our implemented algorithms are applied for the first time to this problem—with artificial intelligence-based machine learning strategies to create a prediction model. The efficacy of our suggested technique was evaluated using WDBC breast cancer data sets, and the findings show that our proposed hybrid algorithm performs very well in breast cancer classification. We have been able to attain astonishing results with accuracy up to 98.9578%, sensitivity up to 0.9705, specificity up to 1.000, precision up to 1.000, F1-score up to 0.9696, and an AUC up to 0.9980 (close to maximum, i.e., 1.0000). Our study's goal is to incorporate our findings into a valid clinical prediction system, allowing visual science specialists to make more accurate and effective judgments in the future. Furthermore, our suggested technology might be used to detect a wide range of diseases. [ABSTRACT FROM AUTHOR]

• We 65 extracted structural and non-structural feature sets for glaucoma prediction. • Our selected three nature-computing algorithms and two novel algorithms have been applied first time to these glaucoma datasets in combination with these characteristics. As a result, the results from this series of experiments are entirely novel. • The performance test of Bat Algorithm and Binary Cuckoo Search on two typical publicly accessible datasets demonstrates that they are highly efficient in glaucoma prediction. Extensive testing and analysis were conducted (3 machine learning and 5 soft computing techniques were tested on three combinations of two datasets). • This work adds to scientific research by suggesting a unique classifier strategy that achieves astonishing results, up to 98.95% accuracy in detecting glaucoma illness in the binary class. The suggested system's categorization accuracy is evaluated against two widely used and publicly accessible datasets. • This work provides an automated primary glaucoma screening system based on quantitative analysis of fundus pictures to aid ophthalmologists in detecting glaucoma disease more quickly and affordably. It could also be used as a second opinion. With this system, human race has been equipped with a low-cost, rapid, robust, readily implementable, and reliable intelligence system for screening this infection. As a result, the pace of eyesight loss may be minimized. Glaucoma is the second most common cause of vision loss. Manual screening of a patient's eye or screening through a fundus image of the patient's eye requires expert ophthalmologists. This screening analysis is time-consuming, requires expert human involvement, and is subject to human intra-observer variability. Thus, medical imaging professionals are working to solve these issues by investigating retinal images for glaucoma detection using artificial intelligence-based computer-aided diagnosis systems (CAD). Machine learning algorithms (for classification) and nature-inspired computing (for feature selection/reduction) embedded CAD systems can successfully identify retinal pictures and can be employed to overcome these challenges. This proposed work is a productive attempt in which we have proposed two novel two-layered approaches (BA-BCS, BCS-PSO) which are based on Particle Swarm Optimization (PSO), Binary Cuckoo Search (BCS), and Bat Algorithm (BA). We have also analyzed the performances of BA, BCS, and PSO separately. These five (single and two-layered) approaches are used to compose subsets of reduced features that can generate the maximum accuracy when forwarded to three machine learning classifiers. Benchmark publicly available datasets, ORIGA and REFUGE, and their combinations are used to validate the proposed methodology. A maximum accuracy of up to 98.95% is achieved using these approaches. Apart from this, many other trade-off solutions are also suggested for the researcher's community. This study therefore presents novel efforts with new and efficient results that are beneficial to ophthalmologists, researchers, and humanity. [ABSTRACT FROM AUTHOR]