Valencia, Oscar A. Garcia

Delayed graft function (DGF) is a frequent complication after deceased donor kidney transplantation, yet its long-term impact remains understudied. Heterogeneous populations, short follow-up, and inadequate control of donor-related factors have limited prior studies. Using the Scientific Registry of Transplant Recipients (2005–2024), we evaluated the association between DGF and long-term graft outcomes, including a mate-kidney (same donor, discordant DGF status) analysis to isolate its independent effect. We identified 103,678 dialysis-dependent deceased donor kidney recipients maintained on tacrolimus and mycophenolate. Mixed-effects Cox models, adjusted for donor, recipient, immunologic, and procurement factors. DGF occurred in 30.1% of recipients and was associated with increased death-censored graft failure (HR 1.40; 95% CI 1.33–1.47) and overall graft failure (HR 1.27; 95% CI 1.23–1.31). DGF recipients had higher rejection rates at 6 (6.0% vs. 4.7%) and 12 months (8.9% vs. 7.3%), longer hospital stay, and higher 1-year rehospitalization. In the mate-kidney analysis (6,818 donors), DGF remained strongly associated with death-censored graft failure (HR 1.58; 95% CI 1.39–1.80) and overall graft failure (HR 1.35; 95% CI 1.25–1.46), confirming the independent effect of DGF. DGF is a strong predictor of adverse long-term outcomes irrespective of rejection and warrants targeted prevention strategies and intensified follow-up.

Background Tacrolimus dosing after kidney transplantation is complex, highly individualized, and prone to variability, which can impact graft outcomes. While machine learning (ML) approaches have been used primarily to predict tacrolimus concentrations, large language models (LLMs) may enable protocol-constrained clinical decision support by generating dosing recommendations aligned with established treatment guidelines. Methods We developed TacroDose AI, a protocol-constrained LLM based on GPT-4, to generate tacrolimus dosing recommendations aligned with institutional guidelines. Using 300 structured simulated clinical scenarios, we evaluated protocol adherence, error patterns, and reproducibility of model-generated dosing recommendations. Following review of initial outputs, a refined prompt ( TacroAI 2.0 ) was implemented to strengthen protocol constraints and structured output verification, and performance was reassessed. Results TacroDose AI achieved 72.9% protocol adherence, with 27.1% protocol deviations, including 13.9% sentinel errors with potential clinical significance. Prompt refinement substantially improved performance: TacroAI 2.0 achieved 91.7% adherence, reduced sentinel errors to 1.0%, and improved reproducibility from 77.3 to 86.7% (all p < 0.01). Although rounding discrepancies increased, these represented minor numerical differences without clinical relevance. Performance improvements were observed across subtherapeutic, therapeutic, and supratherapeutic tacrolimus scenarios. Conclusion Protocol-constrained LLMs can produce guideline-concordant tacrolimus dosing recommendations with high adherence and improved reliability in simulated clinical settings. These findings highlight a potential framework for integrating generative AI with rule-based clinical protocols to support safe medication management. With further validation using real-world data, such systems could be integrated into electronic health records to support clinician-supervised, protocol-based immunosuppressive dosing in transplant care.

Background Effective patient education is critical for informed decision-making and adherence in kidney transplantation. Generative artificial intelligence (AI), particularly large language models (LLMs), has the potential to enhance patient education in kidney transplantation; however, its factual accuracy and readability remain incompletely characterized. Methods We evaluated the performance of the GPT-5.1 (2025) model in generating plain-language explanations for 100 clinically relevant kidney transplantation terms. Explanations were generated using a standardized prompt (first round) and a revised prompt explicitly requesting an eighth-grade reading level or lower (second round). Accuracy was assessed by expert reviewers using a 5-point Likert scale, while readability was evaluated using the Flesch Reading Ease (higher score indicated easier readability of the text) and Flesch–Kincaid Grade Level (higher score indicated higher education level required to understand the text) score. The study was conducted in November 2025. Results All AI-generated explanations demonstrated high accuracy, with no clinically significant errors. In the first round, the mean Flesch Reading Ease score was 23.6 ± 23.4, indicating very difficult readability, and 46% of explanations required a college-level reading ability (mean Flesch–Kincaid Grade Level 13.4 ± 4.8). Following prompt revision, readability improved substantially. The mean Flesch Reading Ease score increased to 62.4 ± 7.5, corresponding to standard readability, and all explanations were written at a middle school level or below (mean Flesch–Kincaid Grade Level 6.3 ± 1.1). Conclusion GPT-5.1 generated highly accurate explanations of kidney transplantation terms across prompting strategies. Explicit readability-focused prompting substantially improved readability without compromising accuracy, underscoring the importance of prompt design when deploying LLMs for patient-centered education in transplantation.