Use of artificial intelligence for reverse referral between a hospital emergency department and a primary urgent care center

Yolanda Taules ¹ Silvia Gros ¹ Maria Viladrosa ² Natàlia Llorens ¹ Sílvia Solis ¹ Oriol Yuguero ^2,3*

• ¹ Catalan Health Institute (ICS), Barcelona, Catalonia, Spain
• ² Lleida Institute for Biomedical Research (IRBLleida), Lleida, Spain
• ³ Fundació per a la Universitat Oberta de Catalunya, Barcelona, Catalonia, Spain

The demand for immediate care in emergency departments (EDs) has risen since the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic. Objective Test the ability of AI to promote reverse referral and to provide patient education. Methods Pilot study that included patients presenting to our Hospital Emergency Department (HED) with a non severe disease and who met the inclusion criteria. The participants were asked to answer a series of questions using an electronic device and receive a recommendation for health attention. Then, patients could choose to either remain in the hospital or leave Results 427 patients finally participated in the pilot study. Within this population, 49.5% were women, and the mean patient age was 37.5 years. Mediktor recommended reverse referral to urgent care in 43.6%. Our results demonstrate that the tool is safe and provides accurate patient screening, correctly distinguishing between those who should continue to wait for HED care and those for whom an urgent care center is adequate.