Healthcare Data Encryption Based on Secure AI Model with Computational Analysis Using Machine Learning Algorithms

As mobile health care grows quickly, medical facilities must also consider the unspoken risk of privacy breaches when exchanging patient health information. Increased accessibility, early disease diagnosis, and widespread therapeutic outreach have all been made possible by digital healthcare. The confidentiality and privacy of the healthcare data have grown to be a top concern for all parties involved, notwithstanding this extraordinary accomplishment. According to data breach reports, one of the main targets for cybercriminals is the healthcare data sector. Indeed, there has been an unparalleled surge in healthcare data breaches during the past few years. Therefore, the focus of this study is on developing an efficient healthcare data encryption based on secure model in machine learning analysis. The proposed technique makes use of Temporal Aggregation Neural Network (TANN) for load reduction by offering a special training strategy that captures the temporal correlation of successive frames in video. A straightforward motion search method combines similar patches from neighbouring frames. Additionally, the Elliptic Curve Menezes-Qu-Vanstone technique is used to encrypt the data securely and confidentially. A number of factors are used to analyse the proposed Load reduction network. The parameters analysed are accuracy, precision, recall, F-1 score, AUC, MAP, RMSE, throughput and network security.