Triage
Conditions
Brief summary
Artificial intelligence, and in particular Graph Neural Networks (GNNs), have shown enormous potential in the analysis of complex clinical data. Thanks to their ability to model relationships between variables, GNNs represent a significant evolution compared to traditional models, enabling better interpretation of medical information and supporting data-driven decision-making in complex contexts such as emergency medicine. The application of GNNs to clinical triage and to the prediction of length of stay can improve clinical efficiency by optimizing resource allocation and patient management. This observational study aims to evaluate the accuracy of predictions with respect to real clinical data, contributing to the development of advanced predictive tools to support healthcare decision-making processes.
Interventions
OTHERObservation
there is no intervetiuons
Sponsors
Azienda Ospedaliero Universitaria Renato Dulbecco
University of Catanzaro
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Healthy volunteers
No
Inclusion criteria
* all
Exclusion criteria
* Patients labelled with red codes and serious injuries.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Numbers of Undertriaged | 12 monthds | The investigators will measure the number of misclassifications |
| Undertriaged | 12 months | The investigators will measure the ability to predict undertriage |
Countries
Italy
Outcome results
None listed