An Agent-based Detection Method of Condition Progression Trends on Mobile for Hypertensive Diabetic Patients

Diabetes and hypertension are prevalent chronic conditions on a global scale. There exists a correlation between them, rendering them more prone to transpire concurrently. The proposed mobile application provides users with a proactive self-monitoring capability by detecting tendencies of condition progression. In this study, there exist three distinct categories of condition progression trends that can be identified, namely positive, negative, and neutral condition progression trends. In order to provide a detection mechanism, a collaboration among three distinct types of agents takes place. Content agents are responsible for managing the incoming data, interpreter agents handle the preprocessing of the data, and aggregator agents are tasked with creating the detection rules. More specifically, three types of content agents are used in this study including the personal agent, clinical agent, and behavior agent respectively. The result of the simulation indicates that the proposed detection method achieves an accuracy rate of 93.67%.