Testmed. Process management in Emergency Medicine

Background: The main problem in emergency medicine is that clinical assessment and treatment decisions are complex activities. Moreover, clinicians operate in a culture of personal responsibility for decisions, by making it difficult to accept automated systems as the primary decision route. In this paper we present the initial outcomes of the TESTMED project, which aims at developing a process-aware system where the emphasis relies on assisting the clinicians through the availability of recommended healthcare pathways, together with the provision of relevant information that reduce the risk arising from a personal decision The TESTMED project aims at finding an effective way for the clinicians to exploit the guidelines and to acquire, by reading or listening, the guideline itself and to make effective use of it. Moreover TESTMED prototype is able to trace and monitor every choice originated during the guideline execution. Methods: The doctor in charge of handling an incoming patient is equipped with a tablet PC. According to a patient-centered clinical approach, the care pathway is selected on a per-case basis from a dedicated repository and loaded into the back-end management system to be executed. The user interface relies on an integrated multitouch and speech recognition/generation framework, able to handle both touch and vocal inputs, and to support device-to-human interaction via text-to-speech capabilities. The first tests have concerned the guideline enacted for patients suffering from chest pain. Leveraging the encouraging results of our initial tests, we plan to perform in the next months an extensive system evaluation and validation. This will require the enactment of additional guidelines, as well as the collection of both quantitative and qualitative data for assessing the real impact on clinical work practices. Results: We produced two mockups of the system (in the months of April and September 2011) and a working prototype in late November 2011. Each mockup/prototype has been evaluated throughout a wide range of usability tests made with real clinicians, and the outcomes have been used for an incremental improvement of the system. Concerning the current version of the TESTMED prototype, we performed a test in the ward of DEA with 7 different users and with the Chest Pain procedure loaded into the system. Discussion and Conclusions: We can argue that so far main research activities have focused on supporting guidelines modeling and process management in static and well defined clinical contexts. Specific research activities have been carr