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.
Study Type
OBSERVATIONAL
Enrollment
1,500
there is no intervetiuons
University of Catanzaro
Catanzaro, Italy
Numbers of Undertriaged
The investigators will measure the number of misclassifications
Time frame: 12 monthds
Undertriaged
The investigators will measure the ability to predict undertriage
Time frame: 12 months
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.