Performance of a Predictive Model for Long-Term Hemoglobin Response to Darbepoetin and Iron Administration in a Large Cohort of Hemodialysis Patients

Abstract

Anemia management, based on erythropoiesis stimulating agents (ESA) and iron supplementation, has become an increasingly challenging problem in hemodialysis patients. Maintaining hemodialysis patients within narrow hemoglobin targets, preventing cycling outside target, and reducing ESA dosing to prevent adverse outcomes requires considerable attention from caregivers. Anticipation of the long-term response (i.e. at 3 months) to the ESA/iron therapy would be of fundamental importance for planning a successful treatment strategy. To this end, we developed a predictive model designed to support decision-making regarding anemia management in hemodialysis (HD) patients treated in center. An Artificial Neural Network (ANN) algorithm for predicting hemoglobin concentrations three months into the future was developed and evaluated in a retrospective study on a sample population of 1558 HD patients treated with intravenous (IV) darbepoetin alfa, and IV iron (sucrose or gluconate). Model inputs were the last 90 days of patients’ medical history and the subsequent 90 days of darbepoetin/iron prescription. Our model was able to predict individual variation of hemoglobin concentration 3 months in the future with a Mean Absolute Error (MAE) of 0.75 g/dL. Error analysis showed a narrow Gaussian distribution centered in 0 g/dL; a root cause analysis identified intercurrent and/or unpredictable events associated with hospitalization, blood transfusion, and laboratory error or misreported hemoglobin values as the main reasons for large discrepancy between predicted versus observed hemoglobin values. Our ANN predictive model offers a simple and reliable tool applicable in daily clinical practice for predicting the long-term response to ESA/iron therapy of HD patients.

Switching from Epoetin Alfa (Epogen®) to Epoetin Alfa-Epbx (Retacrit^TM) Using a Specified Dosing Algorithm: A Randomized, Non-Inferiority Study in Adults on Hemodialysis

“…The primary efficacy endpoint was the proportion of time patients' hemoglobin levels were 9-11 g/dL during the final 8 weeks of the study (weeks [17][18][19][20][21][22][23][24]. This endpoint was introduced in a protocol amendment in December 2015, after the commencement of the study; the original primary endpoint was the proportion of patients who maintained a mean hemoglobin level within the target range during the final 8 weeks of the study.…”

“…Patients with anemia and chronic kidney disease undergoing maintenance hemodialysis and receiving routine intravenous (IV) Epogen ® were randomized 1: 1 to switch to IV Retacrit TM or continue standard-of-care (Epogen ® ) for 24 weeks, using analogous versions of the FMCNA ESA-dosing algorithm. The primary endpoint was the proportion of time patients' hemoglobin was 9-11 g/dL during weeks [17][18][19][20][21][22][23][24]. Results: Of 432 randomized patients, 418 received treatment (Retacrit TM , n = 212; standard-of-care, n = 206) and comprised the full analysis set.…”

“…However, in clinical practice, owing to the complexities of maintaining hemoglobin levels within a narrow target range and the desire to use ESAs judiciously, many dialysis centers utilize algorithms to adjust ESA doses in a precise manner [18][19][20][21]. Therefore, studies examining the dosing of biosimilar epoetins according to such algorithms will be of clear relevance to dialysis providers.…”

Developing a classification system for haemoglobin management in patients with end-stage renal disease on haemodialysis: a secondary data analysis

“…In the past, several approaches have been developed that take a further step and propose specific ESA dosing in individual patients. 23 24 Despite promising results none of them has yet reached the status of a standard tool and further research is necessary to identify the best option. Our classification system can deliver valuable information on the performance of such a tool to optimise anaemia management.…”

“…We chose a period of time of 120 days mainly because this is within the range of the usually reported survival time of an erythrocyte and at least 3 months are considered to be a necessary time frame to evaluate the treatment success. 23 25 However, red blood cell survival is reported to be reduced in patients with CKD, thus contributing to anaemia problems. 26 We suppose those differences in erythrocyte survival time are based on individual cases and in order to cover the entire possible life span, we applied a period of 120 days to all patient data.…”