Background: In private healthcare systems, patients often bypass primary care and access specialists directly. In rheumatology, this practice may lead to inefficiencies due to the broad range of conditions and limited patient knowledge about the specialty. Initial consultations often fail to yield definitive diagnoses or treatment plans, resulting in additional diagnostic tests, follow-up visits, prolonged wait times, and overall system inefficiencies for patients, insurers, and providers.

Objectives: This study aimed to evaluate the effectiveness of ReumAI, an artificial intelligence (AI)-based triage tool, in streamlining rheumatology consultations within a private hospital setting.

Methods: A pilot study was conducted at the Rheumatology Department of Hospital Quirón Barcelona, where all new patient requests were triaged using ReumAI. The system, managed by non-physician staff, utilized AI-guided telephone interviews to generate syndromic diagnostic orientations and identify necessary pre-visit tests. The first 300 cases were assessed for diagnostic concordance between ReumAI and rheumatologists, as well as the utility of requested tests.

Results: The mean age of patients was 52 years (SD 14), with 72% being female. Primary reasons for consultation included hand pain (28%), nonspecific pain (25%), and foot pain (11%). ReumAI’s differential diagnosis aligned with the final syndromic diagnosis in 85% of cases, demonstrating moderate diagnostic concordance (53%) with rheumatologists. Pre-visit tests suggested by ReumAI were deemed useful in 95% of cases.

Conclusion: ReumAI demonstrated significant potential in optimizing rheumatology triage, improving diagnostic efficiency, and reducing wait times. Future larger-scale studies are warranted to validate these findings and evaluate the long-term impact on patient outcomes and healthcare resource utilization.

REFERENCES: NIL.

Acknowledgements: NIL.

Disclosure of Interests: None declared.

© The Authors 2025. This abstract is an open access article published in Annals of Rheumatic Diseases under the CC BY-NC-ND license ( http://creativecommons.org/licenses/by-nc-nd/4.0/ ). Neither EULAR nor the publisher make any representation as to the accuracy of the content. The authors are solely responsible for the content in their abstract including accuracy of the facts, statements, results, conclusion, citing resources etc.