Waterman, Amy D

Artificial intelligence (AI) is rapidly transforming the delivery of kidney care through predictive analytics, machine learning, deep learning, and generative AI technologies. To meet this challenge, the American Society of Nephrology convened an AI Workgroup to provide a framework for the responsible use of AI in nephrology. The group outlines foundational principles to guide AI development: prioritizing patient benefit, ensuring clinician oversight, and advancing innovation in high-burden disease areas. Its set of foundational assumptions are grounded in the physician always being in the loop and an overarching goal to benefit patients with kidney diseases. This review provides an overview of the clinical uses of AI in nephrology and offers practical guidance for nephrologists seeking to incorporate AI into CKD and AKI management, dialysis, and transplantation care. It also highlights key challenges—such as data quality, equity, transparency, and clinical integration—that must be addressed to ensure the responsible and effective implementation of AI in kidney care.

Background. Chronic systemic inflammation is associated with mortality in patients with chronic kidney disease, cardiovascular disease, and diabetes. The goal of this study was to examine the relationship between pretransplant inflammatory biomarkers (growth differentiation factor-15 [GDF-15], interleukin-6 [IL-6], soluble tumor necrosis factor receptor-1, monokine induced by gamma interferon/chemokine [C-X-C motif] ligand 9 [MIG/CXCL9], monocyte chemoattractant protein-1, soluble FAS, tumor necrosis factor-α, interleukin-15, and interleukin-1β) and death with function (DWF) after kidney transplantation (KT). Methods. We retrospectively measured inflammatory biomarker levels in serum collected up to 1 y before KT (time from blood draw to KT was 130 ± 110 d) in recipients transplanted between January 2006 and December 2018. Kaplan-Meier estimation, Cox regression, and Gradient Boosting Machine modeling were used to examine the relationship between inflammatory biomarkers and DWF. Results. Our cohort consisted of 1595 KT recipients, of whom 62.9% were male and 83.2% were non-Hispanic White. Over a mean follow-up of 7.4 ± 3.9 y, 21.2% of patients (n = 338) experienced DWF. Patients with the highest quartile levels of GDF-15 (>4766 pg/mL), IL-6 (>6.11 pg/mL), and MIG/CXCL9 (> 5835 pg/mL) had increased rates of DWF, and each predicted mortality independently of the others. When adjusted for clinical factors (age, diabetes, etc), the highest quartile levels of GDF-15 and IL-6 remained independently associated with DWF. Adding inflammatory markers to a clinical Cox model improved the C-statistic for DWF from 0.727 to 0.762 using a Gradient Boosting Machine modeling approach. Conclusions. These findings suggest that pre-KT serum concentrations of GDF-15, IL-6, and MIG/CXCL9 may help to risk stratify and manage patients undergoing KT and suggests that chronic inflammation may play a role in mortality in KT recipients.

Background. Gaps in our knowledge of long-term outcomes affect decision making for potential living kidney donors. Methods. The Scientific Registry of Transplant Recipients was asked to determine the feasibility of a candidate registry. Results. Ten living kidney donor programs evaluated 2107 consecutive kidney donor candidates; 2099 of 2107 (99.6%) completed evaluations, 1578 of 2099 (75.2%) had a decision, and 790 of 1578 (50.1%) were approved to donate as of March 12, 2020. By logistic regression, candidates most likely to be approved were married or had attended college or technical school; those least likely to be approved had ≥1 of the following characteristics: Black race, history of cigarette smoking, and higher blood pressure, higher triglycerides, or higher urine albumin-to-creatinine ratios. Reasons for 617 candidates not being approved included medical issues other than chronic kidney disease risk (25.3%), chronic kidney disease risk (18.5%), candidate withdrawal (15.2%), recipient reason (13.6%), anatomical risk to the recipient (10.3%), noneconomic psychosocial (10.3%), economic (0.5%), and other reasons (6.4%). Conclusions. These results suggest that a comprehensive living donor registry is both feasible and necessary to assess long-term outcomes that may inform decision making for future living donor candidates. There may be socioeconomic barriers to donation that require more granular identification so that active measures can address inequities. Some candidates who did not donate may be suitable controls for discerning the appropriateness of acceptance decisions and the long-term outcomes attributable to donation. We anticipate that these issues will be better identified with modifications to the data collection and expansion of the registry to all centers over the next several years.