Citations

Artificial intelligence (AI), including machine learning, deep learning, reinforcement learning, and generative AI, has the potential to advance critical care nephrology (CCN) by enhancing prediction accuracy, improving diagnostic capabilities, supporting clinical decision making, and streamlining workflow processes. Current applications in CCN include AKI prediction, nephrotoxin surveillance, intradialytic hypotension forecasting, and AI-guided dialysis and continuous KRT management, with performance often exceeding traditional models. However, the effect on patient-centered outcomes such as mortality, dialysis dependence, and cost-effectiveness remains uncertain. Emerging techniques, such as conformal prediction for calibrated risk estimates, causal inference for intervention modeling, and reinforcement learning for adaptive ultrafiltration, show promise in enhancing reliability, interpretability, and individualized care. Generative AI and large language models extend these applications to clinical documentation, reasoning, and patient education, while raising new challenges, including hallucinations, regulatory oversight, and clinician trust. Persistent barriers such as data heterogeneity, limited external validation, alert fatigue, and economic constraints hinder broad adoption. This review synthesizes the current evidence and outlines four priorities for advancing AI in CCN: ( 1 ) rigorous multicenter validation focused on clinical outcomes, ( 2 ) integration of uncertainty quantification and causal modeling into AI tools, ( 3 ) development of clinician-centered interfaces that minimize cognitive load, and ( 4 ) establishment of transparent, adaptive regulatory and governance frameworks. Realizing the promise of AI in CCN will require multidisciplinary collaboration, fairness and generalizability testing, and sustainable implementation strategies that align technologic innovation with measurable improvements in patient care.

We appreciate Dr Akcay's insightful comments. His observations provide valuable context and highlight important considerations for future research. We hope our work will serve as a foundation for further investigation into sex-associated risks in peritoneal dialysis and contribute to optimizing high-quality patient care for all individuals. Looking ahead, future studies should integrate dialysis-specific measures, explore mechanistic pathways, and incorporate patient-centered outcomes to better characterize sex-associated differences in peritoneal dialysis.

Abstract Background and Aims Sodium-glucose cotransporter-2 inhibitors (SGLT2i) are emerging as an essential part of the new standard of care for proteinuria, alongside renin-angiotensin system (RAS) inhibitors in patients with proteinuric chronic kidney disease (CKD). Subgroup analysis of EMPA-KIDNEY and DAPA-CKD trials done in patients with glomerular diseases [IgA Nephropathy (IgAN) and focal and segmental glomerulosclerosis (FSGS)] showed these agents are less effective in reducing proteinuria compared to other agents like Sparsentan, or Double RAS Blockade. Also, the antiproteinuric effects of SGLT2i in patients with glomerular diseases is not well understood. To date, no study has specifically evaluated the effects of body mass index (BMI) on the antiproteinuric efficacy of SGLT2. Here we report the impact of BMI on the antiproteinuric efficacy of SGLT2i in non-diabetic patients with glomerular diseases. Method Single-center retrospective cohort study. Inclusion criteria (1) adult patients with a biopsy-proven glomerular disease or genetic diagnosis [i.e., Collagen IV mutations] from January 1st, 2019, to December 31st, 2023, (2) no Diabetes Mellitus, (3) proteinuria more than 0.75 g/24 h at the time of initiation of treatment despite optimized blood pressure control with renin-angiotensin system (RAS) inhibition at maximum tolerated dose (5) no concomitant use of induction immunosuppression therapy—stable maintenance immunosuppression was allowed. Patients with active neoplasia, no follow-up available after initiation of therapy or kidney transplant were excluded. Baseline was defined as the time of the initiation of SGLT2i. Laboratory values, including proteinuria, serum creatinine, and estimated glomerular filtration rate (eGFR), were obtained at baseline and 6 months. Changes in laboratory values over time were analyzed using the paired t-test and the signed-rank test, depending on the distribution. Weight status was classified based on BMI in three categories: regular (BMI < 25 kg/m2), overweight (25–29.9 kg/m2), and obese (>30 kg/m2). Results We identified 115 non-diabetic patients with glomerular diseases. Median age [IQR] at the time of SGLT2i initiation was 49.1 [35.4, 61.5] years; 74 (64.3%) patients were male, and 96 (83.5%) patients were white, with the second most common ethnicity being Asian with 10 (8.7%) patients. Median BMI for the entire cohort was 28.2 [26.0, 33.1] Kg/m2. Fifty-three (46.1%) patients had IgAN, 22 (19.1%) had secondary FSGS (sFSGS), 3 (2.6%) primary FSGS (pFSGS), and 12 (10.4%) genetic FSGS (gFSGS), with collagen IV mutations as the most common cause of gFSGS. Kidney function and proteinuria over time are presented in Table 1. Significant declines in eGFR [−1.77 ml/min/1.73m2 95% CI: (−4.2, −1.19)] and proteinuria [−0.58 g/24h 95% CI (−0.91, −0.44)] were observed at 6 months in the entire cohort compared to baseline. However, in the subgroup analysis by BMI strata, i.e., <25, 25-29.9, ≥30, the reduction in proteinuria was statistically significant only in overweight and obese patients. The expected early drop in eGFR was not observed in patients with a normal BMI. However, the decline in eGFR progressively increased and was statistically significant in the obese group (Fig. 1). Conclusion The principal finding of the present study is the lack of significant proteinuria reduction in patients with BMI<25 kg/m², which contrasts with the significant reductions observed in overweight and obese patients. SGLT2i's main antiproteinuric mechanism of action involves reducing glomerular hyperfiltration, which is commonly seen in patients with diabetes and obesity. In non-diabetic patients with glomerulopathies, proteinuria may be sustained by mechanisms not dependent on glomerular hyperfiltration, especially in those patients with normal BMI. These findings are crucial to advocate a personalized approach to treatment, challenging the “one-size-fits-all” strategy.