CONTEXT-AWARE AI FOR DYNAMIC RISK SCORING OF PATIENT DATA TRANSACTIONS IN IOT-ENABLED CLINICAL ENVIRONMENTS

Abstract

Recent applications of Internet of Things (IoT) technologies have been able to elevate the process of patient monitoring and data acquisition in clinical environments.Still, it is impossible to neglect the aspects of security and privacy, given that fully sensitive patient information is being generated in real time.The traditional risk scoring models for healthcare data are based on static parameters and do not take into consideration the dynamic and context-dependent nature of transaction types involving IoT data.Herein is proposed a new context-aware AI model to dynamically assess the risk of patient data transactions taking place in IoT-enabled clinical environments.The solution allows integrating real-time contextual information such as patient health status, environmental circumstances, and device-related data into the risk scoring process so that the risk assessments are not only more accurate but also timely.The AIbased model has been evaluated on a large dataset of simulated clinical IoT transactions and demonstrated the ability to deliver accurate, real-time predictions of risk, with significant improvement over the traditional static models.Here, we describe the methodology, findings, and implications of employing context-aware AI to fortify healthcare data security, presenting an attractive solution to the problems generated by the growing use of IoT in healthcare.

Ähnliche Arbeiten