Search results

This paper aims to investigate the process performances in Emergency Departments (EDs) with a novel data-driven approach, permitting to discover the entire patient-flow, deploy the performances in term of time and resources on the activities and flows and identify process deviations and critical bottlenecks. Moreover, the use of this methodology in real time might dynamically provide a picture of the current situation inside the ED in term of waiting times, crowding, resources, etc., supporting the management of patient demand and resources in real time.

The proposed methodology exploits the process-mining techniques. Starting from the event data inside the hospital information systems, it permits automatically to extract the patient-flows, to evaluate the process performances, to detect process exceptions and to identify the deviations between the expected and the actual results.

The application of the proposed method to a real ED revealed being valuable to discover the actual patient-flow, measure the performances of each activity with respect to the predefined targets and compare different operating situations.

Starting from the results provided by this system, hospital managers may explore the root causes of deviations, identify areas for improvements and hypothesize improvement actions. Finally, process-mining outputs may provide useful information for creating simulation models to test and compare alternative ED operational scenarios.

This study responds to the need of novel approaches for monitoring and evaluating processes performances in the EDs. The novelty of this data-driven approach is the opportunity to timely connect performances, patient-flows and activities.

The purpose of this study is twofold: exploring new queue-based variables enabled by process mining and evaluating their impact on the accuracy of waiting time prediction. Such queue-based predictors that capture the current state of the emergency department (ED) may lead to a significant improvement in the accuracy of the prediction models.

Alongside the traditional variables influencing ED waiting time, the authors developed new queue-based predictors exploiting process mining. Process mining techniques allowed the authors to discover the actual patient-flow and derive information about the crowding level of the activities. The proposed predictors were evaluated using linear and nonlinear learning techniques. The authors used real data from an ED.

As expected, the main results show that integrating the set of predictors with queue-based variables significantly improves the accuracy of waiting time prediction. Specifically, mean square error values were reduced by about 22 and 23 per cent by applying linear and nonlinear learning techniques, respectively.

Accurate estimates of waiting time can enable the ED systems to prevent overcrowding e.g. improving the routing of patients in EDs and managing more efficiently the resources. Providing accurate waiting time information also can lead to decreased patients’ dissatisfaction and elopement.

The novelty of the study relies on the attempt to derive queue-based variables reporting the crowding level of the activities within the ED through process mining techniques. Such information is often unavailable or particularly difficult to extract automatically, due to the characteristics of ED processes.