Adam E. Gaweda

Data-driven linguistic modeling using relational fuzzy rules

This paper presents a new approach to fuzzy rule-based modeling of nonlinear systems from numerical data. The novelty of the approach lies in the way of input partitioning and in the syntax of the rules. This paper introduces interpretable relational antecedents that incorporate local linear interactions between the input variables into the inference process. This modification improves the approximation quality and allows for limiting the number of rules. Additionally, the resulting linguistic description better captures the system characteristics by exposing the interactions between the input variables.

Iron, Inflammation, Dialysis Adequacy, Nutritional Status, and Hyperparathyroidism Modify Erythropoietic Response

BACKGROUND AND OBJECTIVES The erythropoietic response in hemodialysis patients depends on several physiologic factors. Most epidemiologic studies include the effect of these factors by representing them as confounders. This study tested the hypothesis that iron stores, inflammation, dialysis adequacy, nutritional status, and hyperparathyroidism act as nonlinear effect modifiers of the erythropoietic response and quantified the magnitude of those effects over clinically relevant ranges. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS The following retrospective data from 209 hemodialysis patients receiving Epoetin alfa (Epo) were collected: monthly: predialysis hemoglobin (Hgb), transferrin saturation, serum albumin, dialysis adequacy (Kt/V); quarterly: predialysis serum ferritin and intact parathyroid hormone over a period of 13 to 69 months. The study analyzed the dynamic relationship between hemoglobin and Epo, considering nonlinear effect modification by ferritin, transferrin saturation, Kt/V, albumin, and parathyroid hormone individually. RESULTS Maximum Hgb response to Epo was achieved for serum ferritin between 350 and 500 ng/ml, transferrin saturation greater than 30%, Kt/V greater than 1.4, and albumin greater than 3.8 g/dl. Hgb sensitivity to Epo decreases by about 30% as parathyroid hormone increases from 0 through 1000 pg/ml. CONCLUSIONS Serum ferritin, transferrin saturation, Kt/V, serum albumin, and intact parathyroid hormone are markers of nonlinear effect modification of the erythropoietic response in hemodialysis patients.

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.

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.

Input selection in data-driven fuzzy modeling

An iterative backward selection method for determination of relevant input variables in data-driven fuzzy modeling is presented. The method utilizes parameters of the Takagi-Sugeno model as a factor to determine the significance of input variables. As a result, it is less computationally intensive than most of the existing methods for input variable selection.

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.

Iron dosing in kidney disease: inconsistency of evidence and clinical practice

The management of anemia in patients with chronic kidney disease (CKD) is difficult. The availability of erythropoiesis-stimulating agents (ESAs) has increased treatment options for previously transfusion-requiring patients, but the recent evidence of ESA side effects has prompted the search for complementary or alternative approaches. Next to ESA, parenteral iron supplementation is the second main form of anemia treatment. However, as of now, no systematic approach has been proposed to balance the concurrent administration of both agents according to individual patients needs. Furthermore, the potential risks of excessive iron dosing remain a topic of controversy. How, when and whether to monitor CKD patients for potential iron overload remain to be elucidated. This review addresses the question of risk and benefit of iron administration in CKD, highlights the evidence supporting current practice, provides an overview of standard and potential new markers of iron status and outlines a new pharmacometric approach to physiologically compatible individualized dosing of ESA and iron in CKD patients.

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.

Fuzzy neural network with relational fuzzy rules

The paper presents a fuzzy neural network whose structure accounts for relations between input variables of the system under consideration. This modification results in a simple fuzzy model with improved approximation accuracy. An example of nonlinear time series prediction using the proposed fuzzy neural network is also included.

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