Health care data transmission and privacy preservation using generalized data transmission with a privacy preservation approach

Internet of Things (IoT) transforms the medical industry by providing the means for patient monitoring in real time and large-scale interaction between patients, physicians, medical equipment, and nursing and clinical personnel. Because of the network’s vastness and diversity, there are opportunities and obstacles in obtaining and sharing information. Medical equipment patients use with sensitive health information needs to be safeguarded to maintain privacy and safety. Specialists exchange private healthcare information to assess patient care and provide prompt treatment. Biometric and cryptographic systems, along with privacy policies, are used to secure medical systems and detect anomalies. Since sensors are energy-constrained, deep learning–based security solutions must balance security and efficiency. The novel framework created in this work, the generalized data transmission with a privacy preservation approach (GDT-PP), lowers the time needed for encryption and decryption while safeguarding data transmission from outside threats. By processing patient data in this way, network traffic is decreased. Moreover, this procedure lowers communication errors and expenses. It is observed that the proposed method outperforms the existing methods. The method also accomplished 59 milliseconds for encryption and 62 milliseconds for decryption in addition to an overhead of 68% along with accuracy of 94%, sensitivity of 93%, and specificity of 93%.