Individualized anemia management in a dialysis facility - long-term utility as a single-center quality improvement experience
.

BACKGROUND: Standard protocol-based approaches to erythropoiesis stimulating agent (ESA) dosing in anemia management of end-stage renal disease (ESRD) fail to address the inter-individual variability in patient's response to ESA. We conducted a single-center quality improvement project to investigate the long-term performance of a computer-designed dosing system. MATERIALS AND METHODS: The study was a retrospective case-control study with long-term follow-up. All hemodialysis patients who received treatment at University Kidney Center (Louisville, KY, USA) between September 1, 2009, and March 31, 2017, were included. We implemented an individualized ESA dosing algorithm into an electronic health records database software to provide patient-specific ESA dose recommendations to anemia managers at monthly intervals. The primary outcome was the percentage of hemoglobin (Hb) concentrations between 10 and 12 g/dL during the case-control study and 9 and 11 g/dL during follow-up. Secondary outcomes were intra- and inter-individual Hb variability. For the case-control study, we compared outcomes over 12 months before and after implementation of the algorithm. Subjects served as their own controls. We used the last Hb concentration of the month and ESA dose per week. Long-term follow-up examined trends in proportion within the target range, Hb, and ESA dose. RESULTS: Individualized ESA dosing in 56 subjects was associated with a moderate (6.6%) increase of mean Hb maintenance within target over the 12-month observation period (62.7% before vs. 69.3% after, p = 0.063). Intra-individual mean Hb variability decreased (1.1 g/dL before vs. 0.8 g/dL after, p < 0.001), so did inter-individual mean Hb variability (1.2 g/dL before vs. 1.0 g/dL after, p = 0.010). Long-term follow-up in 233 subjects for 42 months demonstrated stability of the achieved Hb despite an increasing ESA resistance in the patient population. CONCLUSION: Implementation of the individualized ESA dosing algorithm facilitates improvement in Hb maintenance within target, decreases Hb variability and reduces the dose of ESA required to achieve Hb target.
.

Individualized anemia management reduces hemoglobin variability in hemodialysis patients.

One-size-fits-all protocol-based approaches to anemia management with erythropoiesis-stimulating agents (ESAs) may result in undesired patterns of hemoglobin variability. In this single-center, double-blind, randomized controlled trial, we tested the hypothesis that individualized dosing of ESA improves hemoglobin variability over a standard population-based approach. We enrolled 62 hemodialysis patients and followed them over a 12-month period. Patients were randomly assigned to receive ESA doses guided by the Smart Anemia Manager algorithm (treatment) or by a standard protocol (control). Dose recommendations, performed on a monthly basis, were validated by an expert physician anemia manager. The primary outcome was the percentage of hemoglobin concentrations between 10 and 12 g/dl over the follow-up period. A total of 258 of 356 (72.5%) hemoglobin concentrations were between 10 and 12 g/dl in the treatment group, compared with 208 of 336 (61.9%) in the control group; 42 (11.8%) hemoglobin concentrations were <10 g/dl in the treatment group compared with 88 (24.7%) in the control group; and 56 (15.7%) hemoglobin concentrations were >12 g/dl in the treatment group compared with 46 (13.4%) in the control group. The median ESA dosage per patient was 2000 IU/wk in both groups. Five participants received 6 transfusions (21 U) in the treatment group, compared with 8 participants and 13 transfusions (31 U) in the control group. These results suggest that individualized ESA dosing decreases total hemoglobin variability compared with a population protocol-based approach. As hemoglobin levels are declining in hemodialysis patients, decreasing hemoglobin variability may help reduce the risk of transfusions in this population.

Determining optimum hemoglobin sampling for anemia management from every-treatment data.

BACKGROUND AND OBJECTIVES: Anemia management protocols in ESRD call for hemoglobin (Hb) monitoring every 2 to 4 weeks. Short-term Hb variability affects the reliability of Hb measurement and may lead to incorrect dosing of erythropoiesis stimulating agents. We prospectively analyzed short-term Hb variability and quantified the relationship between frequency of Hb monitoring and error in Hb estimation. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: Using the Crit-Line III TQA device, we prospectively observed Hb during each dialysis treatment in 49 ESRD patients and quantified long- and short-term Hb variability. We estimated Hb from data sampled at regular intervals; 8×, 4×, 2×, or 1× per month to establish how well we account for short-term variability at different monitoring intervals. We calculated the Hb estimation error (Hb(err)) as a root mean-squared difference between the observed and estimated Hb and compared it with the measurement error. RESULTS: The most accurate Hb estimation is achieved when monitoring 8× per month (Hb(err) = 0.23 ± 0.05 g/dl), but it exceeds the accuracy of the measurement device. The estimation error increases to 0.34 ± 0.07 g/dl when monitoring 4× per month, 0.39 ± 0.08 g/dl when monitoring 2× a month, and 0.45 ± 0.09 g/dl when monitoring 1× per month. Estimation error comparable to instrument error information is as follows: 8× per month, 15 patients; 4× per month, 22 patients; 2× per month, 6 patients; 1× per a month, 6 patients. CONCLUSIONS: Four times a month is the clinically optimal Hb monitoring frequency for anemia management.

Randomized trial of model predictive control for improved anemia management.

BACKGROUND AND OBJECTIVES: Variable hemoglobin (Hb) response to erythropoiesis stimulating agents may result in adverse outcomes. The utility of model predictive control for drug dosing was previously demonstrated. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: This was a double-blinded, randomized, controlled trial to test model predictive control for dosing erythropoietin in ESRD patients. The trial included 60 hemodialysis patients who were randomized into a treatment arm (30 subjects) that received erythropoietin doses on the basis of the computer recommendations or a control arm (30 subjects) that received erythropoietin doses on the basis of recommendations from a standard anemia management protocol (control). The subjects were followed for 8 months, and the proportions of measured Hb within the target of 11 to 12 g/dl and outside 9 to 13 g/dl were measured. Variability of the Hb level was measured by the absolute difference between the achieved Hb and the target Hb of 11.5 g/dl as well as the area under the Hb curve. RESULTS: Model predictive control resulted in 15 observations >13 or <9 g/dl (outliers), a mean absolute difference between achieved Hb and 11.5 g/dl of 0.98 +/- 0.08 g/dl, and an area under the Hb curve of 2.86 +/- 1.46. The control group algorithm resulted in 30 Hb outliers (P = 0.051), produced a mean absolute difference between achieved Hb and 11.5 g/dl of 1.18 +/- 0.18 g/dl (P < 0.001 difference in variance), and an area under the Hb curve of 3.38 +/- 2.69 (P = 0.025 difference in variance). CONCLUSIONS: Model predictive control of erythropoietin administration improves anemia management.

Model predictive control of erythropoietin administration in the anemia of ESRD.

BACKGROUND: Variable hemoglobin (Hb) response to erythropoiesis-stimulating agents (ESAs) may result in adverse outcomes. New methods are needed to determine the appropriate dose of ESA to maintain the target Hb level. DESIGN: (1) Observational study to develop an algorithm for model predictive control (MPC) by using an artificial neural network model of Hb response to ESA. (2) Computer simulation to test MPC versus a conventional anemia management protocol (AMP). (3) Clinical trial to test MPC. SETTING & PARTICIPANTS: The MPC was developed from historic data from 186 long-term hemodialysis patients at the University of Louisville, KY. Testing by simulation occurred in 60 hypothetical patients generated from random sampling of the 186 patients. The trial included 9 hemodialysis patients who received ESA doses based on MPC recommendations over 6 months. PREDICTOR: Management by means of MPC or AMP. OUTCOME OF INTEREST: Achieved Hb level and variability measured by means of the difference between achieved Hb level and target Hb level of 11.5 g/dL and erythropoietin dose. In the trial, Hb level deviation from target was compared in the same subjects between the study (last 4 of 6 months on MPC) and control (4 months on AMP immediately proceeding the study period) periods. RESULTS: In simulation, achieved Hb levels were 12.3 +/- 0.6 g/dL for AMP and 11.6 +/- 0.4 g/dL for MPC (P < 0.001), mean SDs were 0.75 +/- 0.30 g/dL for AMP and 0.60 +/- 0.21 g/dL for MPC (P < 0.01), and mean absolute differences from target were 0.8 +/- 0.6 g/dL for AMP and 0.3 +/- 0.3 g/dL for MPC (P < 0.001). In the trial, achieved Hb levels were 11.9 +/- 1.1 g/dL for AMP and 11.8 +/- 0.6 g/dL for MPC (P = 0.8), mean SDs were 0.86 +/- 0.60 g/dL for AMP and 0.64 +/- 0.33 g/dL for MPC (P = 0.4), and mean absolute differences from target were 1.19 +/- 0.79 g/dL for AMP and 0.79 +/- 0.50 g/dL for MPC (P = 0.02). CONCLUSION: MPC of ESAs may result in improved anemia management.

Using clinical information in goal-oriented learning.

We have proposed an extension to the Q-learning algorithm that incorporates the existing clinical expertise into the trial-and-error process of acquiring an appropriate administration strategy of rHuEPO to patients with anemia due to ESRD. The specific modification lies in multiple updates of the Q-values for several dose/response combinations during a single learning event. This in turn decreases the risk of administering doses that are inadequate in certain situations and thus increases the speed of the learning process. We have evaluated the proposed method using a simulation test-bed involving an "artificial patient" and compared the outcomes to those obtained by a classical Q-learning and a numerical implementation of a clinically used administration protocol for anemia management. The outcomes of the simulated treatments demonstrate that the proposed method is a more effective tool than the traditional Q-learning. Furthermore, we have observed that it has a potential to provide even more stable anemia management than the AMP.

Model predictive control with reinforcement learning for drug delivery in renal anemia management.

Treatment of chronic conditions often creates the challenge of an adequate drug administration. The intra- and inter-individual variability of drug response requires periodic adjustments of the dosing protocols. We describe a method, combining model predictive control for simulation of patient response and reinforcement learning for estimation of dosing strategy, to facilitate the management of anemia due to kidney failure.

Individualization of pharmacological anemia management using reinforcement learning.

Effective management of anemia due to renal failure poses many challenges to physicians. Individual response to treatment varies across patient populations and, due to the prolonged character of the therapy, changes over time. In this work, a Reinforcement Learning-based approach is proposed as an alternative method for individualization of drug administration in the treatment of renal anemia. Q-learning, an off-policy approximate dynamic programming method, is applied to determine the proper dosing strategy in real time. Simulations compare the proposed methodology with the currently used dosing protocol. Presented results illustrate the ability of the proposed method to achieve the therapeutic goal for individuals with different response characteristics and its potential to become an alternative to currently used techniques.

Pharmacodynamic population analysis in chronic renal failure using artificial neural networks--a comparative study.

This work presents a pharmacodynamic population analysis in chronic renal failure patients using Artificial Neural Networks (ANNs). In pursuit of an effective and cost-efficient strategy for drug delivery in patients with renal failure, two different types of ANN are applied to perform drug dose-effect modeling and their performance compared. Applied in a clinical environment, such models will allow for prediction of patient response to the drug at the effect site and, subsequently, for adjusting the dosing regimen.