Dialog-Based Intelligent Operation Theatre Scheduler

Medical treatments planning and surgical operations scheduling are substantial elements of hospital management. Operations theatre scheduling deals with assignment of limited hospital resources (rooms, doctors, nurses, etc.) to jobs (patient treatments, surgery, etc.) over the time in order to perform tasks according to their needs and priorities, and to optimize usage of hospital resources [7]. The whole process is restricted by lots of constraints, limitations and preferences [2]. It is characterized by high complexity, which is caused by the uncertainty between the offered capacity and the true demand. As emergency cases occur the planning requirements will change. Existing industrial schedulers usually assume a predefined workflow. Furthermore, they do not take actors’ preferences into account and are therefore suffer from levels of non-acceptance of their resulting schedules [2]. State of the art in this domain are the following methods: no planning, pen and paper, non-intelligent tool-based. Therefore, typically scheduling is done manually and involves specialized persons to facilitate the process. An example of an optimization that can be achieved using process automization for nurses rostering is discussed in [4]. In the considered hospital one person spends 3-5 full-time working days on producing a nurses’ schedule for the period of one month (only shift assignment). A use of a dialog-based semi-automated system is preferred against fully manual or fully automated systems. This is because of the inability of the later to recognize the changes in a high dynamic environment and to take the responsibility for decisions made. As it has to be possible to add new tasks in the planning process “on the fly” and to adequately plan new situations, we involve a human planner in the scheduling activity. The planner acts as a “sensor” to identify changes as they occur and integrates his knowledge as well as decision-making competence into the planning process. The proposals for the schedules are made with the help of heuristics. Actual problem solving mechanisms of the system and their evaluation are presented