Randomized Trial of Model Predictive Control for Improved Anemia Management

Abstract

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.

Individualized Anemia Management Reduces Hemoglobin Variability in Hemodialysis Patients

“…Individualized dosing in SAM was based on MMPC. MMPC is an extension of the MPC approach 8,9 and uses multiple MPC algorithms designed for patient-specific doseresponse models. Each model corresponds to one of five dose-response classes: extreme hyper-responder, hyper-responder, moderate hyper-responder, intermediate responder, and hyporesponder.…”

“…Given the patient population of our facility and our previous experience, 8 we expected to enroll between 50 and 80 participants for this study. On the basis of our previous simulations, 13,14 we assumed a minimum clinically important difference of 10% in the primary outcome in favor of SAM.…”

“…[8][9][10] We have shown that a population approach to ESA dosing, based on the principles of model predictive control (MPC), is comparable with a standard protocol. 8,9 We now present the results of a randomized clinical trial of an MPC-based individualized approach to ESA dosing.…”

“…[8][9][10] We have shown that a population approach to ESA dosing, based on the principles of model predictive control (MPC), is comparable with a standard protocol. 8,9 We now present the results of a randomized clinical trial of an MPC-based individualized approach to ESA dosing. We tested the hypothesis that individualized ESA dosing improves the total hemoglobin variability defined as the proportion of hemoglobin measurements within a user-specified target (10-12 g/dl) compared with a standard protocol-based population approach.…”

A radial basis function method for solving optimal control problems.

“…In a clinical setting, the prediction of Hb level would be more useful and practical than the prediction of EPO drug dose, since the former has wellestablished protocols and recommended guidelines [104]. A model predictive control (MPC) approach was designed and successfully applied to the anemia management problem as a population-oriented method in [97], [98] and later as an individualized approach [101]. While their recent work for individualized anemia management has shown promising results in declining Hb variability among CKD patients [101], the method is not sufficiently fast for achieving the desired Hb level, especially for poor responder patients.…”