Breast Cancer Detection in the IOT Health Environment Using Modified Recursive Feature Selection

Abstract

The accurate and efficient diagnosis of breast cancer is extremely necessary for recovery and treatment in early stages in IoT healthcare environment. Internet of Things has witnessed the transition in life for the last few years which provides a way to analyze both the real-time data and past data by the emerging role of artificial intelligence and data mining techniques. The current state-of-the-art method does not effectively diagnose the breast cancer in the early stages, and most of the ladies suffered from this dangerous disease. Thus, the early detection of breast cancer significantly poses a great challenge for medical experts and researchers. To solve the problem of early-stage detection of breast cancer, we proposed machine learning-based diagnostic system which effectively classifies the malignant and benign people in the environment of IoT. In the development of our proposed system, a machine learning classifier support vector machine is used to classify the malignant and benign people. To improve the classification performance of the classification system, we used a recursive feature selection algorithm to select more suitable features from the breast cancer dataset. The training/testing splits method is applied for training and testing of the classifier for the best predictive model. Additionally, the classifier performance has been checked on by using performance evaluation metrics such as classification, specificity, sensitivity, Matthews’s correlation coefficient, F1-score, and execution time. To test the proposed method, the dataset “Wisconsin Diagnostic Breast Cancer” has been used in this research study. The experimental results demonstrate that the recursive feature selection algorithm selects the best subset of features, and the classifier SVM achieved optimal classification performance on this best subset of features. The SVM kernel linear achieved high classification accuracy (99%), specificity (99%), and sensitivity (98%), and the Matthews’s correlation coefficient is 99%. From these experimental results, we concluded that the proposed system performance is excellent due to the selection of more appropriate features that are selected by the recursive feature selection algorithm. Furthermore, we suggest this proposed system for effective and efficient early stages diagnosis of breast cancer. Thus, through this system, the recovery and treatment will be more effective for breast cancer. Lastly, the implementation of the proposed system is very reliable in all aspects of IoT healthcare for breast cancer.

Cloud Computing-Based Framework for Breast Cancer Diagnosis Using Extreme Learning Machine

“…McKinney et al [ 38 ] proposed an AI system that outperformed human experts in breast cancer prediction on mammogram images. Memon et al [ 39 ] suggested using a modified recursive feature selection algorithm that achieved 99% accuracy with an SVM classifier on the WDBC dataset. Ronoud and Asadi [ 40 ] suggested using the genetic algorithm (GA) to evolve the number of hidden layers and neurons and to finetune the network weights and biases of the deep belief network (DBN).…”

Detection of Breast Cancer Through Clinical Data Using Supervised and Unsupervised Feature Selection Techniques

“…The performance evaluation metrics [25], [39], [40] are use for performance evaluation of the model such as accuracy, specificity, sensitivity, F1-score, MCC, ROC and AUC. These metrics are described mathematically in equation 5-10 respectively.…”

Recent Advances in Computer-Aided Medical Diagnosis Using Machine Learning Algorithms With Optimization Techniques

“…Sangaiah and Kumar [16] have suggested an algorithm which is a hybrid-type detection system for the breast cancer diagnosis. For the early detection of breast cancer, the suggested algorithm utilized a ReliefF quality reduction with entropy based genetic algorithm.…”