Derrick K. Rollins

Adaptive system identification for estimating future glucose concentrations and hypoglycemia alarms

Many patients with diabetes experience high variability in glucose concentrations that includes prolonged hyperglycemia or hypoglycemia. Models predicting a subjects future glucose concentrations can be used for preventing such conditions by providing early alarms. This paper presents a time-series model that captures dynamical changes in the glucose metabolism. Adaptive system identification is proposed to estimate model parameters which enable the adaptation of the model to inter-/intra-subject variation and glycemic disturbances. It consists of online parameter identification using the weighted recursive least squares method and a change detection strategy that monitors variation in model parameters. Univariate models developed from a subjects continuous glucose measurements are compared to multivariate models that are enhanced with continuous metabolic, physical activity and lifestyle information from a multi-sensor body monitor. A real life application for the proposed algorithm is demonstrated on early (30 min in advance) hypoglycemia detection.

Hypoglycemia Early Alarm Systems Based On Multivariable Models.

Hypoglycemia is a major challenge of artificial pancreas systems and a source of concern for potential users and parents of young children with Type 1 diabetes (T1D). Early alarms to warn the potential of hypoglycemia are essential and should provide enough time to take action to avoid hypoglycemia. Many alarm systems proposed in the literature are based on interpretation of recent trends in glucose values. In the present study, subject-specific recursive linear time series models are introduced as a better alternative to capture glucose variations and predict future blood glucose concentrations. These models are then used in hypoglycemia early alarm systems that notify patients to take action to prevent hypoglycemia before it happens. The models developed and the hypoglycemia alarm system are tested retrospectively using T1D subject data. A Savitzky-Golay filter and a Kalman filter are used to reduce noise in patient data. The hypoglycemia alarm algorithm is developed by using predictions of future glucose concentrations from recursive models. The modeling algorithm enables the dynamic adaptation of models to inter-/intra-subject variation and glycemic disturbances and provides satisfactory glucose concentration prediction with relatively small error. The alarm systems demonstrate good performance in prediction of hypoglycemia and ultimately in prevention of its occurrence.

Issues regarding artificial neural network modeling for reactors and fermenters

Abstract In recent years researchers in many areas have used artificial neural networks (ANNs) to model a variety of physical relationships. While in many cases this selection appears sound and reasonable, one must remember than ANN modeling is an empirical modeling technique (based on data) and is subject to the limitations of such techniques. Poor prediction occurs when the training data set does not contain adequate “information” to model a dynamic process. Using data from a simulated continuous-stirred tank reactor, this paper illustrates four scenarios: (1) steady state, (2) large process time constant, (3) infrequent sampling, and (4) variable sampling rate. The first scenario is typical of simulation studies while the other three incorporate attributes found in real plant data. For the cases in which ANNs predicted well, linear regression (LR), one of the oldest empirical modeling techniques, predicted equally well, and when LR failed to accurately model/predict the data, ANNs predicted poorly. Since real plant data would resemble a combination of situations (2), (3), and (4), it is important to understand that empirical models are not necessarily appropriate for predictively modeling dynamic processes in practice.

Intelligent selection of hypothesis tests to enhance gross error identification

Abstract The objective of this study was to evaluate the ability of a new technique to identify systematic measurement errors (i.e. biases) in process variables. This technique obtains high identification accuracy and computational speed by efficiently selecting a small subset of statistical hypothesis tests from a very large set using new selection criteria developed in this work. In this article the proposed technique is also evaluated and compared to a well known method in a fairly extenisve Monte Carlo simulation study. The proposed technique was found to be computationally faster and, as the variances of measurement errors decreased, significantly more accurate in identifying systematic errors.

A superior approach to indices in determining mixture segregation

Abstract In the forties, the index approach to measure segregation for powder mixtures was introduced. Since that time, several researchers have introduced new indices in an effort to improve this approach continually for the determination of mixture segregation. However, there are two major drawbacks of all current indices that make them unattractive as measures of segregation. First, these indices can vary for reasons other than segregation. The second drawback is the inability to determine if the calculated values of these indices are significant while controlling the probability of making incorrect conclusions. In this article a measure of segregation is proposed that is not subject to these limitations. In addition, a theoretical evaluation is given of current indices and the proposed approach. The conclusions of this evaluation are illustrated and confirmed by a Monte Carlo simulation study.

Hypoglycemia Early Alarm Systems Based on Recursive Autoregressive Partial Least Squares Models

Background: Hypoglycemia caused by intensive insulin therapy is a major challenge for artificial pancreas systems. Early detection and prevention of potential hypoglycemia are essential for the acceptance of fully automated artificial pancreas systems. Many of the proposed alarm systems are based on interpretation of recent values or trends in glucose values. In the present study, subject-specific linear models are introduced to capture glucose variations and predict future blood glucose concentrations. These models can be used in early alarm systems of potential hypoglycemia. Method: A recursive autoregressive partial least squares (RARPLS) algorithm is used to model the continuous glucose monitoring sensor data and predict future glucose concentrations for use in hypoglycemia alarm systems. The partial least squares models constructed are updated recursively at each sampling step with a moving window. An early hypoglycemia alarm algorithm using these models is proposed and evaluated. Results: Glucose prediction models based on real-time filtered data has a root mean squared error of 7.79 and a sum of squares of glucose prediction error of 7.35% for six-step-ahead (30 min) glucose predictions. The early alarm systems based on RARPLS shows good performance. A sensitivity of 86% and a false alarm rate of 0.42 false positive/day are obtained for the early alarm system based on six-step-ahead predicted glucose values with an average early detection time of 25.25 min. Conclusions: The RARPLS models developed provide satisfactory glucose prediction with relatively smaller error than other proposed algorithms and are good candidates to forecast and warn about potential hypoglycemia unless preventive action is taken far in advance.

Continuous-time Hammerstein and Wiener modeling under second-order static nonlinearity for periodic process signals

This article presents continuous-time (CT) analytical solutions to Hammerstein and Wiener systems with second-order plus-lead (SOPL) dynamic behavior for sinusoidal input changes. The proposed solutions depend only on the most recent input change and exact accuracy is demonstrated for cases of varying frequency (ω), amplitude (A), and phase angle (φ). This article demonstrates two critical advancements in the application of these solutions using a multiple input, multiple output (MIMO) mathematically simulated continuous stirred tank reactor (CSTR). The first one is improved accuracy over approximating periodic input changes as piece-wise step changes. The second one is the ability to accurately model process noise in the outputs when the input process noise can be decomposed into a sum of sinusoidal components. Since in many applications inputs are measured at a much higher rate than an output, the CT modeling of periodic process noise provides a means to model periodic output noise despite infrequent sampling of the output. Moreover, this article also presents output correction using measured output to remove prediction bias under white and serially correlated noise of measured outputs.

Critical modeling issues for successful feedforward control of blood glucose in insulin dependent diabetics

Accurate modeling of the effects of nutrient and activity variables on blood glucose can make a major impact in reducing the complications of diabetes for insulin dependent type 1 and 2 diabetics. These models can be used to design feedforward controllers that can revolutionize blood glucose control. However, to achieve this objective, there are several critical issues in measurement, data collection, and modeling that need to be resolved. This work discusses and presents solutions to resolving these issues.

A novel data mining method to identify assay-specific signatures in functional genomic studies.

Background:The highly dimensional data produced by functional genomic (FG) studies makes it difficult to visualize relationships between gene products and experimental conditions (i.e., assays). Although dimensionality reduction methods such as principal component analysis (PCA) have been very useful, their application to identify assay-specific signatures has been limited by the lack of appropriate methodologies. This article proposes a new and powerful PCA-based method for the identification of assay-specific gene signatures in FG studies.Results:The proposed method (PM) is unique for several reasons. First, it is the only one, to our knowledge, that uses gene contribution, a product of the loading and expression level, to obtain assay signatures. The PM develops and exploits two types of assay-specific contribution plots, which are new to the application of PCA in the FG area. The first type plots the assay-specific gene contribution against the given order of the genes and reveals variations in distribution between assay-specific gene signatures as well as outliers within assay groups indicating the degree of importance of the most dominant genes. The second type plots the contribution of each gene in ascending or descending order against a constantly increasing index. This type of plots reveals assay-specific gene signatures defined by the inflection points in the curve. In addition, sharp regions within the signature define the genes that contribute the most to the signature. We proposed and used the curvature as an appropriate metric to characterize these sharp regions, thus identifying the subset of genes contributing the most to the signature. Finally, the PM uses the full dataset to determine the final gene signature, thus eliminating the chance of gene exclusion by poor screening in earlier steps. The strengths of the PM are demonstrated using a simulation study, and two studies of real DNA microarray data – a study of classification of human tissue samples and a study of E. coli cultures with different medium formulations.ConclusionWe have developed a PCA-based method that effectively identifies assay-specific signatures in ranked groups of genes from the full data set in a more efficient and simplistic procedure than current approaches. Although this work demonstrates the ability of the PM to identify assay-specific signatures in DNA microarray experiments, this approach could be useful in areas such as proteomics and metabolomics.

Measurement bias detection in linear dynamic systems

A new method to detect the existence of biased measured variables in dynamic processes is presented. Hence, this work presents a new Dynamic Global Test (DGT) and test procedure for dynamic gross error detection (GED) that brings to light certain of its attributes which have not hitherto (to our knowledge) been presented in GED literature. Recognition of these attributes leads to a scheme that enables identification of the type of biased measurement (e.g. flow or level). This approach is not computationally intensive and is applicable in the case of process leaks and multiple biased variables. Simulation results for the identification of the type of biased measurement (e.g. flow or level) and the estimation of the time of occurrence (ETOC) are given. The performance study in this work specifically varied the size of measurement bias (i), the bias location (i ), the bias true time of occurrence (TTOC), the significance level (), and the sample size (N). This study shows the proposed approach to be accurate in identifying the type of biased variable and its TTOC. The performance of the proposed scheme improves as N and i increase.