Back

A User-Centered, SMART-on-FHIR-Based Dashboard Prototype for Diabetic Macular Edema

Hoffmann, K.; Grummt, S.; Mishian, H.; Nussbaumer, M.; Wolfien, M.; Stolze, G.; Engelmann, K.; Sedlmayr, M.

2026-09-21 ophthalmology
10.64898/2026.09.15.26362892 medRxiv
Show abstract

Introduction: Diabetic macular edema (DME) management requires integration of ophthalmic and systemic data, yet clinical decision-making remains limited by fragmented information systems and insufficient interoperability. This study aims to design a user-centered, interoperable dashboard prototype to support integrated clinical decision-making in DME care. Methods: The prototype was developed using an agile, user-centered approach and implemented within a SMART-on-FHIR-compatible layered architecture. FHIR-based data standardization, including ophthalmology-specific profiling, enabled interoperable integration and visualization of structured clinical and imaging data within a modular web-based dashboard prototype. Results: The resulting prototype provides a patient-centered dashboard integrating ophthalmic imaging findings and systemic risk factors, such as long-term glycemic markers, inflammatory markers, and blood pressure, within a unified interface. Built on standardized FHIR resources and SMART-on-FHIR authorization, the system demonstrates how user-centered dashboards can be implemented within interoperable, vendor-neutral healthcare IT infrastructures. Conclusion: The presented design case illustrates how user-centered interface design and standards-based interoperability can jointly support the translation of clinical decision support tools into routine care environments. Establishing such interoperable infrastructures represents a key prerequisite for the sustainable deployment of future model-based clinical decision support systems.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.