Kidney Week

Abstract: FR-OR012

Real-World Validation and Optimization of CKD Progression Prediction Models Using US Mayo Clinic Data

Session Information

• Artificial Intelligence and Data Science Transforming Kidney Care: From Algorithms to Action
  November 07, 2025 | Location: Room 361A, Convention Center
  Abstract Time: 04:50 PM - 05:00 PM

Category: Artificial Intelligence, Digital Health, and Data Science

• 300 Artificial Intelligence, Digital Health, and Data Science

Authors

• Chang, David R., Division of Nephrology, Department of Internal Medicine, China Medical University Hospital, Taichung, Taiwan

David R. Chang, MD

• Kuo, Chin-Chi, Big Data Center, China Medical University Hospital, Taichung, Taiwan

Chin-Chi Kuo, MD, PhD, MPH

• Lin, Yu-Ting, Big Data Center, China Medical University Hospital, Taichung, Taiwan

Yu-Ting Lin, PhD

• Chen, Yi-Chun, Big Data Center, China Medical University Hospital, Taichung, Taiwan

Yi-Chun Chen, MS

• Arya, Priyanka, Vivance, Singapore, Singapore

Priyanka Arya

• Aguilar, Ricardo, Vivance, Singapore, Singapore

Ricardo Aguilar, PhD

• Jain, Arsh, London Health Sciences Centre, London, Ontario, Canada

Arsh Jain, MD, MS, MSc

Background

Accurate chronic-kidney-disease (CKD) risk prediction tools stall in practice because data elements are often missing. Two deep-learning models, RRT Onset and Rapid Progression (RP), originally developed in Taiwan (China Medical University Hospital, CMUH) and granted FDA Breakthrough Device Designation were tested and optimized using a large, racially diverse U.S. cohort from the Mayo Clinic Platform (MCP).

Methods

We analyzed 232,613 stage 3–5 CKD patients (25,214 under nephrology care) treated at Mayo Clinic sites (AZ, FL, MN) between 2018 and 2024. Outcomes were (1) RRT initiation and (2) eGFR decline (≥40%, slope ≤-5 mL/min/1.73m²/yr, or eGFR <15) within 2 and 5 years. Model variants assessed were: original, fine-tuned, and de novo (trained exclusively on MCP data). Discrimination (AUC), sensitivity, and specificity were compared with 4-variable Kidney Failure Risk Equation (KFRE).

Results

The fine-tuned AI models delivered robust discrimination (RRT-AUC 0.85–0.86; RP-AUC 0.78–0.81). uACR was absent in 46% of records, resulting in an inability to calculate KFRE. Against KFRE (AUC 0.81), fine-tuned RRT predictions improved event reclassification by 12.9–41.4%, while maintaining sensitivity >78% and specificity >75%. Notably, de novo model did not offer significant performance advantages over the fine-tuned model (Table 1). Event rates increased with higher risk scores supporting effective risk stratification (Figure 1).

Conclusion

FDA-designated AI models preserved accuracy despite nearly 50% data missingness and outperformed KFRE across U.S. centers. A rapid fine-tuning step, rather than de novo training, enables seamless local deployment, facilitating prospective trials and accelerating clinical adoption.

Digital Object Identifier (DOI)

• doi: 10.1681/ASN.2025re6x6kqf