Ongoing Critiquing During Trauma Management
نویسنده
چکیده
A major challenge facing the developers of intelligent decision-support systems is how to present pertinent information to physicians in such a way that it will be effective in influencing their behavior. The successful integration of medical decision-support systems into clinical environments has been a widely reported problem ever since such systems began to appear. While recognizing these systems’ potential for improving the quality of patient care and for controlling costs, physicians have tended to reject new technologies which they see as intrusive, time-consuming, or a challenge to their judgment or autonomy as clinical decision-makers [1]. At the same time, the information processing demands on physicians have been increasing dramatically. Utilizing available clinical data to make appropriate decisions about patient care can be challenging to physicians, who are susceptible to information overload which can lead to biases in data acquisition and processing [8]. To counteract the limitations of human information processing, computer-based decision-support systems have been developed to monitor clinical data as they become available and make physicians aware of pertinent events by means of reminders [4] or alerts [2]. Other systems follow the critiquing approach, providing a more extensive off-line discussion of the risks and benefits of alternative management plans [5, 9].
منابع مشابه
Critiquing: Effective Decision Support In Time-Critical Domains
Critiquing Effective Decision Support in Time Critical Domains Abigail S Gertner Bonnie L Webber Supervisor The TraumAID system is a tool for assisting physicians during the initial de nitive management phase of patients with severe injuries Originally TraumAID was conceived as a rule based expert system combined with a planner After this architecture had been implemented and evaluated we began...
متن کاملOn-line decision support for emergency trauma management.
The overall goal of the TraumAID project is to improve the delivery of quality trauma care during the initial definitive phase of patient management. To this end, we are applying artificial intelligence techniques such as rule-based reasoning, planning, and plan inference. The current system, TraumAID 2.0, consists of (1) an electronic version of the standard trauma flow sheet implemented in Hy...
متن کاملA Bias towards Relevance : Recognizing plans where goalminimization
Domains such as multiple trauma management, in which there are multiple interacting goals that change over time, are ones in which plan recog-nition's standard inductive bias towards a single explanatory goal is inappropriate. In this paper we deene and argue for an alternative bias based on identifying contextually \relevant" goals. We support this claim by showing how a complementary planning...
متن کاملCritiquing: Effective Decision Support in Time-Critical Domains (Dissertation Proposal)
The e ective communication of information is an important concern in the design of an expert consultation system. Several researchers have chosen to adopt a critiquing mode, in which the system evaluates and reacts to a solution proposed by the user rather than presenting its own solution. In this proposal, I present an architecture for a critiquing system that functions in real-time, during th...
متن کاملias towards izing plans where goal minimization fails
Domains such as multiple trauma management, in which there are multiple interacting goals that change over time, are ones in which plan recognition’s standard inductive bias towards a single explanatory goal is inappropriate. In this paper we define and argue for an alternative bias based on identifying contextually “relevant” goals. We support this claim by showing how a complementary planning...
متن کامل