Abstract: FR-PO0046
A Digital Enhanced Patient Journey for IgAN: Feasibility of an Artificial Intelligence (AI)-Supported, Multidisciplinary Care Ecosystem
Session Information
- Artificial Intelligence: Clinical Prediction, Decision Support, and Digital Kidney Care
October 23, 2026 | Location: Exhibit Hall A, Convention Center
Abstract Time: 10:00 AM - 12:00 PM
Category: Artificial Intelligence, Digital Health, and Data Science
- 300 Artificial Intelligence, Digital Health, and Data Science
Authors
- Di Leo, Vincenzo, Universita degli Studi di Bari Aldo Moro, Bari, Apulia, Italy
- Annese, Francesca, Universita degli Studi di Bari Aldo Moro, Bari, Apulia, Italy
- Mastropaolo, Claudio, Italian Federation of Medical-Scientific Societies, Milan, Italy
- Rossini, Michele, Universita degli Studi di Bari Aldo Moro, Bari, Apulia, Italy
- Pontrelli, Paola, Universita degli Studi di Bari Aldo Moro, Bari, Apulia, Italy
- Sallustio, Fabio, Universita degli Studi di Bari Aldo Moro, Bari, Apulia, Italy
- Gesualdo, Loreto, Universita degli Studi di Bari Aldo Moro, Bari, Italy
Background
IgAN is the most common primary glomerulonephritis worldwide and a leading cause of CKD. Care is fragmented: diagnostic delays of 2–3 years, poor coordination between GPs, nephrologists and specialists, limited use of certified digital decision-support tools and low clinical trial enrollment. The expanding therapeutic pipeline makes standardized, technology-supported pathways urgent.
Methods
Under FISM (Italian Federation of Medical-Scientific Societies) coordination, a feasibility study of a Digital Enhanced Patient Journey (PJDE) was conducted with a 12-expert multidisciplinary panel covering nephrology (SIN), cardiology, gastroenterology, gynecology, nutrition, psychology, lab medicine, radiology, primary care, public health, nursing and AINIgA. A modified Delphi methodology was applied across 4 phases: literature/regulatory review (KDIGO 2025, MDR 2017/745, GDPR), journey mapping, co-design of the future journey and SWOT-based feasibility assessment across six axes (clinical, technological, organizational, regulatory, economic, patient participation).
Results
The panel unanimously rated the PJDE feasible across all axes. The redesigned journey integrates 3 macro-phases (intake/diagnosis, stratification, treatment/follow-up) orchestrated by the PJDE platform and supported by Clara (clinical learning and research assistant), an AI clinical DSS aligned with KDIGO 2025. Clara provides Oxford MEST-C–informed risk stratification, prescriptive alerts and algorithmic clinical trial matching. Estimated impact includes a 15–20% reduction in unplanned hospitalizations and improved trial enrollment. Key enablers identified: HL7 FHIR interoperability and nurse case managers in Health Transformation Labs (HTLs). Priority recommendations include selecting 3–5 geographically distributed HTLs and launching a 6-month pilot.
Conclusion
A multidisciplinary, AI-supported PJDE for IgAN is clinically necessary and technically feasible. Implementation through HTLs offers a scalable model to reduce diagnostic delay, harmonize care and accelerate trial recruitment.