Open data and artificial intelligence: a window of opportunity for septic patients in emergency departments

Abstract

Sepsis remains one of the leading causes of mortality in emergency departments (EDs). Despite advances in definitions and management protocols, early identification continues to be a critical challenge due to the nonspecific presentation of the disease. Early management is based on 3 fundamental pillars: source control, antibiotics, and hemodynamic resuscitation, all of which require early intervention. Tools such as the SOFA score, biomarkers (C-reactive protein, procalcitonin, lactate), and protocols like the Sepsis Code have improved detection and management. However, the clinical heterogeneity of sepsis and limitations of current models hinder their universal implementation. Artificial intelligence (AI) is emerging as a key tool to improve early detection of sepsis through the analysis of large volumes of clinical data. Open data, following FAIR principles (Findable, Accessible, Interoperable, Reusable), facilitate the development of robust and personalized algorithms, minimizing bias and enhancing scientific collaboration. Spain generates vast amounts of clinical data in its EDs but lacks a unified database. The creation of an open system with data use agreements would enable the development of predictive models specific to its population. The use of A.I. in combination with specific databases promises to improve treatment personalization, reduce mortality, and optimize resources in sepsis care, changing the current paradigm of clinical management.