Agent Technology and Healthcare: Possibilities, Challenges and Examples of Application - Computational Intelligence in Healthcare: Advanced Methodologies - page 36

see and attend pending actions, look up the electronic health care record of the
patients, fill out documents with results of actions execution, request the updat-
ing and personalization of their profile, work as part of a group, define Individ-
ual Intervention Plans, etc.
5.2 K4Care Multi-agent System
The agents of the K4Care platform embed all the system logic by personifying the
actors involved in HC services ( e.g., administrative procedures, careflows, assess-
ments, follow-ups, etc.). The main goal of the MAS is to coordinate the activities
enclosed in administrative procedures and individual intervention plans (as presented
above) between all involved actors.
Fig. 5. Definition of an Individual Intervention Plan
Agent's execution is guided by the knowledge and data stored in the knowledge
layer at any moment. So a change on that results in immediate changes in the execu-
tion logic. Agents act semi-autonomously, in the sense that several actions, such as
exchange of information, collection of heterogeneous data concerning a patient (re-
sults, current treatment, next recommended step, past history), or the management of
actions to execute, are performed by agents without supervision; others, that may
have some degree of responsibility (such as decisions taken in the process of health-
care), are supervised by users.
Each user (both patients and healthcare professionals) is represented in the system
by a permanent agent (generically represented as Actor Agents in Figure 4). Each one