Introduction:We explored the organizational and environmental impacts of the management of erythropoiesis-stimulating agents (ESAs) and intravenous iron for the treatment of chronic kidney disease-related anemia in France. Methods:An electronic survey (March-November 2023) was completed by the head of the supplying pharmacy from 12 dialysis organizations. Eligible organizations reserved ESAs or could identify the ESA prescriptions for dialysis-dependent patients. Primary endpoints were time spent on ESA management and frequency of tasks. Secondary endpoints included the environmental impact of ESAs and the organizational impacts of IV iron management. Results:ESA management required 313.9 h/month per dialysis organization, of which 285.3 h were spent on injection, preparation, administration, and post-administration monitoring. Three-quarters (74.2%) of cold storage space was dedicated to ESAs. IV iron management required 779.3 h/month per dialysis organization, of which 664 h were attributable to administration and post-infusion monitoring. Conclusion:Management of ESAs and IV iron required substantial time and resources in French dialysis organizations.
Artificial intelligence (AI) is playing an increasingly prominent role in medicine, and nephrology is no exception. Yet, behind this generic term lie very different realities depending on the type of data being processed. This didactic article offers a structured account of how AI works across three main data families, illustrated with concrete examples drawn from nephrology practice. With tabular data (the kind found in everyday medical records), predictive models can already anticipate acute kidney injury, intradialytic hypotension, or graft loss. With histological images, neural networks learn to detect and quantify glomerular lesions with remarkable precision, without replacing the pathologist. With text, large language models excel at reformulation, summarization, and triage tasks, more so than at diagnostic reasoning in ambiguous settings. The common thread across all three domains is the same: AI learns statistical regularities from data. Understanding this is the prerequisite for informed use: neither reflexive distrust nor uncritical delegation.
