Current emphasis on protocol-based care has stirred interest:in planni
ng researchas applied to clinical medicine. However, many assumptions
made in designing traditional planners and plan-execution algorithms d
o not hold in medical domains. The problems include the unpredictable
nature of the domain, uncertainty and the variability in the utility o
f available actions, and the need for parallel and continuous executio
n of treatment plans. In the context of our research on intelligent mo
nitoring and control, we developed an approach for plan instantiation
and execution which takes advantage of readily available treatment pro
tocols. The system, named SPIN, instantiates treatment protocols based
on current context, executes plans and closed-loop control actions, m
onitors the execution of plans and actions, and modifies plan executio
n as necessitated by patient response. The system is incorporated in t
he Guardian system for intensive-care patient monitoring and control.
We address the strengths and limitations of the representation and the
execution framework and discuss how the methodology may be improved a
nd used in clinical practice.