Preserving Patient Privacy in IoT Based Breast Cancer Monitoring System

Disease detection plays a crucial role in providing right treatment to the patients. Currently, the lack of information on cancer prevention and awareness results in high fatality. Breast cancer is the second most deadliest disease across the globe. This type of cancer affects women than men. The proposed model employs an Internet of Things (IoT) based hand held device to predict breast cancer and transmit the heathcare data over the cloud for further medical analysis. The confidentiality of the patient's information is likely to be compromised during transmission. The patient's personal information might be intercepted by an outside party. Hence, the proposed model encrypts sensitive information using a mix of the Triple DES and AES method before sending it to the cloud. To improve the classification performance of MLP and SVM, Particle Swarm Optimization (PSO) is used, and a grid-based search was also used to determine the optimal settings of CNN and ANN models. To put the strategy to test, researchers used the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. The proposed model has achieved 98.5% accuracy in CNN classification and 99.2 % accuracy in ANN classification.