Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Aug 28;26(1):496.
doi: 10.1186/s12882-025-04298-7.

Health-economic evaluation of an AI-powered decision support system for anemia management in in-center hemodialysis patients

Afschin Gandjour  1 , Christian Apel  2 , Dana Kendzia  2 , Luca Neri  3 , Francesco Bellocchio  3 , Len Usvyat  4 , John Larkin  4 , Jovana Petrovic Vorkapic  2
Affiliations

Health-economic evaluation of an AI-powered decision support system for anemia management in in-center hemodialysis patients

Afschin Gandjour et al. BMC Nephrol. .

Abstract

Background: The Anemia Control Model (ACM) is a decision support system powered by an artificial intelligence core designed to assist nephrologists in managing anemia therapy for in-center hemodialysis (HD) patients. This study aims to evaluate the cost-effectiveness of the ACM compared to standard of care in Germany, defined as the absence of ACM and a hemoglobin (Hb) target achievement rate of less than 70% among in-center HD patients, based on results from matched observational studies.

Methods: This simulation study adopted the perspective of the German statutory health insurance. A Markov (cohort) state-transition model was used to project the effects of the ACM over the remaining lifetime of patients. All costs were expressed in 2024 euros, and both costs and quality-adjusted life years (QALYs) were discounted at a rate of 3% per year. To test the sensitivity of the results, one-way sensitivity analyses and a probabilistic sensitivity analysis were performed.

Results: This study finds that ACM provides more QALYs and incurs lower costs compared to standard of care. The net monetary value of ACM is €38,423 per patient in the base case scenario. In the sensitivity analysis, the annual cost of erythropoiesis-stimulating agents emerged as the variable with the largest impact on the value of ACM. The probabilistic sensitivity analysis shows that 100% of cost-effect pairs fall within the dominant southeast quadrant, indicating cost-effectiveness.

Conclusions: This modelling study demonstrates that ACM is cost-effective for managing anemia in German in-center HD patients.

Keywords: Anemia management; Artificial intelligence (AI); Cost-effectiveness analysis; Economic evaluation; End-stage kidney disease (ESKD); Erythropoiesis stimulating agent (ESA); Personalized medicine.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: Ethical approval was not required for this study, as it utilized publicly available data and did not involve direct patient or human subject participation. Informed consent was not applicable for the same reason. The study was conducted in accordance with the principles of the Declaration of Helsinki and followed established methodological guidelines for economic evaluations, including the Consolidated Health Economic Evaluation Reporting Standards (CHEERS) 2022. Competing interests: Christian Apel, Dana Kendzia, Luca Neri, Francesco Bellocchio, Len Usvyat, John Larkin, and Jovana Petrovic are full time employees at Fresenius Medical Care.

Figures

Fig. 1
Fig. 1
Markov model structure for evaluating the cost-effectiveness of the Anemia Control Model in in-center hemodialysis patients. Note: ESA: erythropoiesis-stimulating agent
Fig. 2
Fig. 2
Tornado diagram demonstrating the results of the one-way sensitivity analysis. Notes: Variables are ordered by impact on the net monetary benefit of the Anemia Control Model (ACM). ESA: erythropoiesis-stimulating agent; ARR: absolute risk reduction
Fig. 3
Fig. 3
Scatter plot of results from the Monte Carlo simulation
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Kalis B, Collier M, Fu R. 10 Promising AI Applications in Health Care. May 10. 2018. https://hbr.org/2018/05/10-promising-ai-applications-in-health-care
    1. Chaudhuri S, Long A, Zhang H, Monaghan C, Larkin JW, Kotanko P, Kalaskar S, Kooman JP, van der Sande FM, Maddux FW, Usvyat LA. Artificial intelligence enabled applications in kidney disease. Semin Dial. 2021;34(1):5–16. - PMC - PubMed
    1. Liu Y, Zhang Y, Liu D, Tan X, Tang X, Zhang F, Xia M, Chen G, He L, Zhou L, Zhu X, Liu H. Prediction of ESRD in IgA nephropathy patients from an Asian cohort: a random forest model. Kidney Blood Press Res. 2018;43(6):1852–64. - PubMed
    1. KDIGO CKD Work Group. KDIGO 2012 clinical practice guideline for the evaluation and management of chronic kidney disease. Kidney Int Suppl. 2013;3:1–150. - PubMed
    1. Macdougall IC, Eckardt KU. Anemia in chronic kidney disease. In: Johnson RJ, Feehally J, Floege J, editors. Comprehensive Clinical Nephrology e-Book. Elsevier Health Sciences; 2014.

LinkOut - more resources