Wolfgang Wehmeyer

An international observational study suggests that artificial intelligence for clinical decision support optimizes anemia management in hemodialysis patients

Managing anemia in hemodialysis patients can be challenging because of competing therapeutic targets and individual variability. Because therapy recommendations provided by a decision support system can benefit both patients and doctors, we evaluated the impact of an artificial intelligence decision support system, the Anemia Control Model (ACM), on anemia outcomes. Based on patient profiles, the ACM was built to recommend suitable erythropoietic-stimulating agent doses. Our retrospective study consisted of a 12-month control phase (standard anemia care), followed by a 12-month observation phase (ACM-guided care) encompassing 752 patients undergoing hemodialysis therapy in 3 NephroCare clinics located in separate countries. The percentage of hemoglobin values on target, the median darbepoetin dose, and individual hemoglobin fluctuation (estimated from the intrapatient hemoglobin standard deviation) were deemed primary outcomes. In the observation phase, median darbepoetin consumption significantly decreased from 0.63 to 0.46 μg/kg/month, whereas on-target hemoglobin values significantly increased from 70.6% to 76.6%, reaching 83.2% when the ACM suggestions were implemented. Moreover, ACM introduction led to a significant decrease in hemoglobin fluctuation (intrapatient standard deviation decreased from 0.95 g/dl to 0.83 g/dl). Thus, ACM support helped improve anemia outcomes of hemodialysis patients, minimizing erythropoietic-stimulating agent use with the potential to reduce the cost of treatment.

Does the extracorporeal blood flow affect survival of the arteriovenous vascular access

Hemodiafiltration with high‐convective volumes is associated with improved patient survival, whereby practical realization is contingent on high extracorporeal blood flow (Qb) and dialysis treatment time. However, Qb is restricted by vascular access (VA) quality and/or concerns that high Qb could damage the VA. Taking VA quality into consideration, one can investigate the relationship between Qb and VA survival. We analyzed data from 1039 patients treated by hemodiafiltration over a 21‐month period where access blood flow (Qa) measurements were also available at baseline. VA failure was defined as a surgical intervention resulting in the generation of a new VA. Qa was included as a stratification variable within a Cox regression model. A second Cox proportional hazard model with a penalized spline was used to describe the association between Qb and VA survival. Compared with Qb in the 350–357 mL/min range, a significantly higher hazard ratio (HR) for VA failure was detected for fistula only, and then only for Qb < 312 mL/min (HR: 2.361, 95% confidence interval [CI]: 1.251–4.453), Qb = 387–397 mL/min (HR: 1.920, 95% CI: 1.007–3.660) and Qb >414 mL/min (HR: 2.207, 95% CI: 1.101–4.424). Age, gender, diabetes, VA vintage, position of the VA, and arterial pressure were not significantly associated with outcome. The form of the penalized spline confirmed higher risk for VA failure for the lowest and the highest values of Qb. Taking Qa into consideration, no association was found between VA failure and Qb up to flows as high as approximately 390 mL/min.