Background: Emergency Medical Services (EMS) plays a fundamental role in providing good quality healthcare services to citizens, as they are the first responders in distressing situations. Few studies have used available EMS data to investigate EMS call characteristics and subsequent responses. Methods: Data were extracted from the emergency registry for the period 2013–2017. This included call and rescue vehicle dispatch information. All relationships in analyses and differences in events proportion between 2013 and 2017 were tested against the Pearson’s Chi-Square with a 99% level of confidence. Results: Among the 2,120,838 emergency calls, operators dispatched at least one rescue vehicle for 1,494,855. There was an estimated overall incidence of 96 emergency calls and 75 rescue vehicles dispatched per 1000 inhabitants per year. Most calls were made by private citizens, during the daytime, and were made from home (63.8%); 31% of rescue vehicle dispatches were advanced emergency medical vehicles. The highest number of rescue vehicle dispatches ended at the emergency department (74.7%). Conclusions: Our data showed that, with some exception due to environmental differences, the highest proportion of incoming emergency calls is not acute or urgent and could be more effectively managed in other settings than in an Emergency Departments (ED). Better management of dispatch can reduce crowding and save hospital emergency departments time, personnel, and health system costs.

Background: Emergency room reports pose specific challenges to natural language processing techniques. In this setting, violence episodes on women, elderly and children are often under-reported. Categorizing textual descriptions as containing violence-related injuries (V)vs. non-violence-related injuries (NV) is thus a relevant task to the ends of devising alerting mechanisms to track (and prevent) violence episodes.Methods: We presentViDeS(so dubbed afterViolence Detection System), a system to detect episodes of violence from narrative texts in emergency room reports. It employs a deep neural network for categorizing textual ER reports data, and complements such output by making explicit which elements corroborate the interpretation of the record as reporting about violence-related injuries. To these ends we designed a novel hybrid technique for filling semantic frames that employs distributed representations of terms herein, along with syntactic and semantic information. The system has been validated on real data annotated with two sorts of information: about the presence vs. absence of violence-related injuries, and about some semantic roles that can be interpreted as major cues for violent episodes, such as the agent that committed violence, the victim, the body district involved, etc.. The employed dataset contains over 150K records annotated with class (V,NV) information, and 200 records with finer-grained information on the aforementioned semantic roles.Results: We used data coming from an Italian branch of the EU-Injury Database (EU-IDB) project, compiled by hospital staff. Categorization figures approach full precision and recall for negative cases and.97 precision and.94 recall on positive cases. As regards as the recognition of semantic roles, we recorded an accuracy varying from.28 to.90 according to the semantic roles involved. Moreover, the system allowed unveiling annotation errors committed by hospital staff.Conclusions: Explaining systems’ results, so to make their output more comprehensible and convincing, is today necessary for AI systems. Our proposal is to combine distributed and symbolic (frame-like) representations as a possible answer to such pressing request for interpretability. Although presently focused on the medical domain, the proposed methodology is general and, in principle, it can be extended to further application areas and categorization tasks.