Usage of the Anemia Control Model Is Associated with Reduced Hospitalization Risk in Hemodialysis

Abstract

Introduction: The management of anemia in chronic kidney disease (CKD-An) presents significant challenges for nephrologists due to variable responsiveness to erythropoietin-stimulating agents (ESAs), hemoglobin (Hb) cycling, and multiple clinical factors affecting erythropoiesis. The Anemia Control Model (ACM) is a decision support system designed to personalize anemia treatment, which has shown improvements in achieving Hb targets, reducing ESA doses, and maintaining Hb stability. This study aimed to evaluate the association between ACM-guided anemia management with hospitalizations and survival in a large cohort of hemodialysis patients.

Methods: This multi-center, retrospective cohort study evaluated adult hemodialysis patients within the European Fresenius Medical Care NephroCare network from 2014 to 2019. Patients treated according to ACM recommendations were compared to those from centers without ACM. Data on demographics, comorbidities, and dialysis treatment were used to compute a propensity score estimating the likelihood of receiving ACM-guided care. The primary endpoint was hospitalizations during follow-up; the secondary endpoint was survival. A 1:1 propensity score-matched design was used to minimize confounding bias.

Results: A total of 20,209 eligible patients were considered (reference group: 17,101; ACM adherent group: 3108). Before matching, the mean age was 65.3 ± 14.5 years, with 59.2% men. Propensity score matching resulted in two groups of 1950 patients each. Matched ACM adherent and non-ACM patients showed negligible differences in baseline characteristics. Hospitalization rates were lower in the ACM group both before matching (71.3 vs. 82.6 per 100 person-years, p < 0.001) and after matching (74.3 vs. 86.7 per 100 person-years, p < 0.001). During follow-up, 385 patients died, showing no significant survival benefit for ACM-guided care (hazard ratio = 0.93; p = 0.51).

Conclusions: ACM-guided anemia management was associated with a significant reduction in hospitalization risk among hemodialysis patients. These results further support the utility of ACM as a decision-support tool enhancing anemia management in clinical practice.

Keywords: Artificial Intelligence (AI); End Stage Renal Disease (ESRD); anemia management; erythropoiesis-stimulating agent (ESA); personalized medicine.

Figure 1

Study design diagram. This diagram illustrates the timeline and structure of the study, detailing the ascertainment period, follow-up period, exposure groups (ACM users and standard of care), potential confounders, and primary study endpoints (hospital admissions and mortality).

Figure 2

Study flowchart diagram. Flowchart depicting the selection process for the ACM and reference groups from the initial sample (N = 37,009). The ACM group (N = 5273) was refined through multiple exclusion criteria, resulting in a final sample size of N = 3108. The reference group (N = 31,736) was similarly refined to a final sample size of N = 17,101.

Figure 3

Distribution of propensity scores in the ACM and reference groups before matching. Distribution of propensity scores for the ACM group (red) and the reference group (black). The histogram demonstrates the overlap and divergence in propensity scores between the two groups, indicating the relative frequency of individuals across the range of propensity scores.