Research On Technologies Of Workflow Monitoring And Automatic Scheduling In Radiology

Introducing workflow management technology in healthcare may control the growing cost and prevent the errors in the complex processes. Thus, workflow has become a problem needed to be addressed urgently for the further development of the healthcare information system. However, the application of workflow technology in medical area is difficult because of the complexity and flexibility of medical workflow and the heterogeneous environment. In the medical field, the radiology process with the characteristics of complexity and flexibility is better structured. Thus radiology domain is the ideal entry point of the application of workflow management technology in healthcare field.However, there are some problems when apply workflow management technology in radiology. First, workflow monitoring is the basic function of workflow management. But monitoring the overall processes in Radiology is difficult because of the heterogeneous environment. Second, radiology roster is very important for the dynamic resource allocation and task distribution when workflow execution. However, radiology rosters are always generated manually by radiology managers. It costs a lot of management time, and it cannot guarantee the quality of the results. In this thesis, we discuss the research on technologies of workflow monitoring and automatic scheduling in radiology.This paper tries to introduce workflow management technology into the healthcare field. Workflow management technology is used to implement the system integration in a heterogeneous environment. First, a workflow model of radiology process was established. Second, based on the model, the legacy systems were corresponded to the tasks and their process were controlled by workflow management system. Finally, a workflow based dashboard was designed and implemented to help the radiology administrators and managers monitor the states of processes in the radiology department.In this paper, we research the radiology scheduling. Firstly, a multi-objective and aperiodic model of radiology scheduling is established based on the requirement in the radiology department. Then, an improved tabu search algorithm is designed to solve problem. Based on the classical algorithm, a two-step pretreatment is used to obtain an initial solution. The solution meets all constraints and some objectives. It limits the subsequent search in an effective and relative optimized range. In addition, the search neighborhood is limited according to the doctors' skill level. It can reduce the invalid search and improve the efficiency of the algorithm. Finally, a radiology automatic scheduling system is designed and developed to help the radiology administrators and managers generate rosters.A use case implementation is carried out in Huzhou Central hospital of China. The results show that the radiology workflow-based monitoring dashboard can help the radiology managers understand the overall radiology processes, discover the errors at an early stage and facilitate process optimization. Traditionally, the radiology managers need to spend 3 to 4 hours to generate a radiology roster each week. After the radiology automatic scheduling system is applied, the radiology rosters are generated by a computer. It significant reduces the time on the scheduling and guarantee the quality of rosters.