An Early-Warning System for Hypo-/Hyperglycemic Events Based on Fusion of Adaptive Prediction Models

Introduction: Early warning of future hypoglycemic and hyperglycemic events can improve the safety of type 1 diabetes mellitus (T1DM) patients. The aim of this study is to design and evaluate a hypoglycemia / hyperglycemia early warning system (EWS) for T1DM patients under sensor-augmented pump (SAP) therapy. Methods: The EWS is based on the combination of data-driven online adaptive prediction models and a warning algorithm. Three modeling approaches have been investigated: (i) autoregressive (ARX) models, (ii) auto-regressive with an output correction module (cARX) models, and (iii) recurrent neural network (RNN) models. The warning algorithm performs postprocessing of the models′ outputs and issues alerts if upcoming hypoglycemic/hyperglycemic events are detected. Fusion of the cARX and RNN models, due to their complementary prediction performances, resulted in the hybrid autoregressive with an output correction module/recurrent neural network (cARN)-based EWS. Results: The EWS was evaluated on 23 T1DM patients under SAP therapy. The ARX-based system achieved hypoglycemic (hyperglycemic) event prediction with median values of accuracy of 100.0% (100.0%), detection time of 10.0 (8.0) min, and daily false alarms of 0.7 (0.5). The respective values for the cARX-based system were 100.0% (100.0%), 17.5 (14.8) min, and 1.5 (1.3) and, for the RNN-based system, were 100.0% (92.0%), 8.4 (7.0) min, and 0.1 (0.2). The hybrid cARN-based EWS presented outperforming results with 100.0% (100.0%) prediction accuracy, detection 16.7 (14.7) min in advance, and 0.8 (0.8) daily false alarms. Conclusion: Combined use of cARX and RNN models for the development of an EWS outperformed the single use of each model, achieving accurate and prompt event prediction with few false alarms, thus providing increased safety and comfort.

Multi-Model Data Fusion to Improve an Early Warning System for Hypo-/Hyperglycemic Events

Correct predictions of future blood glucose levels in individuals with Type 1 Diabetes (T1D) can be used to provide early warning of upcoming hypo-/hyperglycemic events and thus to improve the patient's safety. To increase prediction accuracy and efficiency, various approaches have been proposed which combine multiple predictors to produce superior results compared to single predictors. Three methods for model fusion are presented and comparatively assessed. Data from 23 T1D subjects under sensor-augmented pump (SAP) therapy were used in two adaptive data-driven models (an autoregressive model with output correction - cARX, and a recurrent neural network - RNN). Data fusion techniques based on i) Dempster-Shafer Evidential Theory (DST), ii) Genetic Algorithms (GA), and iii) Genetic Programming (GP) were used to merge the complimentary performances of the prediction models. The fused output is used in a warning algorithm to issue alarms of upcoming hypo-/hyperglycemic events. The fusion schemes showed improved performance with lower root mean square errors, lower time lags, and higher correlation. In the warning algorithm, median daily false alarms (DFA) of 0.25%, and 100% correct alarms (CA) were obtained for both event types. The detection times (DT) before occurrence of events were 13.0 and 12.1 min respectively for hypo-/hyperglycemic events. Compared to the cARX and RNN models, and a linear fusion of the two, the proposed fusion schemes represents a significant improvement.

Serum tests, liver stiffness and artificial neural networks for diagnosing cirrhosis and portal hypertension

BACKGROUND The diagnostic performance of biochemical scores and artificial neural network models for portal hypertension and cirrhosis is not well established. AIMS To assess diagnostic accuracy of six serum scores, artificial neural networks and liver stiffness measured by transient elastography, for diagnosing cirrhosis, clinically significant portal hypertension and oesophageal varices. METHODS 202 consecutive compensated patients requiring liver biopsy and hepatic venous pressure gradient measurement were included. Several serum tests (alone and combined into scores) and liver stiffness were measured. Artificial neural networks containing or not liver stiffness as input variable were also created. RESULTS The best non-invasive method for diagnosing cirrhosis, portal hypertension and oesophageal varices was liver stiffness (C-statistics=0.93, 0.94, and 0.90, respectively). Among serum tests/scores the best for diagnosing cirrhosis and portal hypertension and oesophageal varices were, respectively, Fibrosis-4, and Lok score. Artificial neural networks including liver stiffness had high diagnostic performance for cirrhosis, portal hypertension and oesophageal varices (accuracy>80%), but were not statistically superior to liver stiffness alone. CONCLUSIONS Liver stiffness was the best non-invasive method to assess the presence of cirrhosis, portal hypertension and oesophageal varices. The use of artificial neural networks integrating different non-invasive tests did not increase the diagnostic accuracy of liver stiffness alone.

Food Recognition for Dietary Assessment Using Deep Convolutional Neural Networks

Diet management is a key factor for the prevention and treatment of diet-related chronic diseases. Computer vision systems aim to provide automated food intake assessment using meal images. We propose a method for the recognition of already segmented food items in meal images. The method uses a 6-layer deep convolutional neural network to classify food image patches. For each food item, overlapping patches are extracted and classified and the class with the majority of votes is assigned to it. Experiments on a manually annotated dataset with 573 food items justified the choice of the involved components and proved the effectiveness of the proposed system yielding an overall accuracy of 84.9%.

Spatial and temporal aspects of synaptic plasticity

The notion that changes in synaptic efficacy underlie learning and memory processes is now widely accepted even if definitive proof of the synaptic plasticity and memory hypothesis is still lacking. When learning occurs, patterns of neural activity representing the occurrence of events cause changes in the strength of synaptic connections within the brain. Reactivation of these altered connections constitutes the experience of memory for these events and for other events with which they may be associated. These statements summarize a long-standing theory of memory formation that we refer to as the synaptic plasticity and memory hypothesis. Since activity-dependent synaptic plasticity is induced at appropriate synapses during memory formation, and is both necessary and sufficient for the information storage, we can speculate that a methodological study of the synapse will help us understand the mechanism of learning. Random events underlie a wide range of biological processes as diverse as genetic drift and molecular diffusion, regulation of gene expression and neural network function. Additionally spatial variability may be important especially in systems with nonlinear behavior. Since synapse is a complex biological system we expect that stochasticity as well as spatial gradients of different enzymes may be significant for induction of plasticity. ^ In that study we address the question "how important spatial and temporal aspects of synaptic plasticity may be". We developed methods to justify our basic assumptions and examined the main sources of variability of calcium dynamics. Among them, a physiological method to estimate the number of postsynaptic receptors as well as a hybrid algorithm for simulating postsynaptic calcium dynamics. Additionally we studied how synaptic geometry may enhance any possible spatial gradient of calcium dynamics and how that spatial variability affect plasticity curves. Finally, we explored the potential of structural synaptic plasticity to provide a metaplasticity mechanism specific for the synapse. ^

A combined measure for quantifying and qualifying the topology preservation of growing self-organizing maps

The Self-OrganizingMap (SOM) is a neural network model that performs an ordered projection of a high dimensional input space in a low-dimensional topological structure. The process in which such mapping is formed is defined by the SOM algorithm, which is a competitive, unsupervised and nonparametric method, since it does not make any assumption about the input data distribution. The feature maps provided by this algorithm have been successfully applied for vector quantization, clustering and high dimensional data visualization processes. However, the initialization of the network topology and the selection of the SOM training parameters are two difficult tasks caused by the unknown distribution of the input signals. A misconfiguration of these parameters can generate a feature map of low-quality, so it is necessary to have some measure of the degree of adaptation of the SOM network to the input data model. The topologypreservation is the most common concept used to implement this measure. Several qualitative and quantitative methods have been proposed for measuring the degree of SOM topologypreservation, particularly using Kohonen's model. In this work, two methods for measuring the topologypreservation of the Growing Cell Structures (GCSs) model are proposed: the topographic function and the topology preserving map

Fuzzy min-max neural networks for categorical data: application to missing data imputation

The fuzzy min–max neural network classifier is a supervised learning method. This classifier takes the hybrid neural networks and fuzzy systems approach. All input variables in the network are required to correspond to continuously valued variables, and this can be a significant constraint in many real-world situations where there are not only quantitative but also categorical data. The usual way of dealing with this type of variables is to replace the categorical by numerical values and treat them as if they were continuously valued. But this method, implicitly defines a possibly unsuitable metric for the categories. A number of different procedures have been proposed to tackle the problem. In this article, we present a new method. The procedure extends the fuzzy min–max neural network input to categorical variables by introducing new fuzzy sets, a new operation, and a new architecture. This provides for greater flexibility and wider application. The proposed method is then applied to missing data imputation in voting intention polls. The micro data—the set of the respondents’ individual answers to the questions—of this type of poll are especially suited for evaluating the method since they include a large number of numerical and categorical attributes.

Evaluation of a PET Prototype Using LYSO:Ce Monolithic Detector Block

We have analyzed the performance of a PET demonstrator formed by two sectors of four monolithic detector blocks placed face-to-face. Both front-end and read-out electronics have been evaluated by means of coincidence measurements using a rotating 22Na source placed at the center of the sectors in order to emulate the behavior of a complete full ring. A continuous training method based on neural network (NN) algorithms has been carried out to determine the entrance points over the surface of the detectors. Reconstructed images from 1 MBq 22Na point source and 22Na Derenzo phantom have been obtained using both filtered back projection (FBP) analytic methods and the OSEM 3D iterative algorithm available in the STIR software package [1]. Preliminary data on image reconstruction from a 22Na point source with Ø = 0.25 mm show spatial resolutions from 1.7 to 2.1 mm FWHM in the transverse plane. The results confirm the viability of this design for the development of a full-ring brain PET scanner compatible with magnetic resonance imaging for human studies.

Prediction of PM10 concentrations using Fuzzy c-Means and ANN

Salamanca has been considered among the most polluted cities in Mexico. The vehicular park, the industry and the emissions produced by agriculture, as well as orography and climatic characteristics have propitiated the increment in pollutant concentration of Particulate Matter less than 10 μg/m3 in diameter (PM10). In this work, a Multilayer Perceptron Neural Network has been used to make the prediction of an hour ahead of pollutant concentration. A database used to train the Neural Network corresponds to historical time series of meteorological variables (wind speed, wind direction, temperature and relative humidity) and air pollutant concentrations of PM10. Before the prediction, Fuzzy c-Means clustering algorithm have been implemented in order to find relationship among pollutant and meteorological variables. These relationship help us to get additional information that will be used for predicting. Our experiments with the proposed system show the importance of this set of meteorological variables on the prediction of PM10 pollutant concentrations and the neural network efficiency. The performance estimation is determined using the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). The results shown that the information obtained in the clustering step allows a prediction of an hour ahead, with data from past 2 hours

On the Biological Plausibility of Artificial Metaplasticity

The training algorithm studied in this paper is inspired by the biological metaplasticity property of neurons. Tested on different multidisciplinary applications, it achieves a more efficient training and improves Artificial Neural Network Performance. The algorithm has been recently proposed for Artificial Neural Networks in general, although for the purpose of discussing its biological plausibility, a Multilayer Perceptron has been used. During the training phase, the artificial metaplasticity multilayer perceptron could be considered a new probabilistic version of the presynaptic rule, as during the training phase the algorithm assigns higher values for updating the weights in the less probable activations than in the ones with higher probability

Microcalcifications Detection using PFCM and ANN

This work presents a method to detect Microcalcifications in Regions of Interest from digitized mammograms. The method is based mainly on the combination of Image Processing, Pattern Recognition and Artificial Intelligence. The Top-Hat transform is a technique based on mathematical morphology operations that, in this work is used to perform contrast enhancement of microcalcifications in the region of interest. In order to find more or less homogeneous regions in the image, we apply a novel image sub-segmentation technique based on Possibilistic Fuzzy c-Means clustering algorithm. From the original region of interest we extract two window-based features, Mean and Deviation Standard, which will be used in a classifier based on a Artificial Neural Network in order to identify microcalcifications. Our results show that the proposed method is a good alternative in the stage of microcalcifications detection, because this stage is an important part of the early Breast Cancer detection

Reduced synchronization persistence in neural networks derived from atm-deficient mice

Many neurodegenerative diseases are characterized by malfunction of the DNA damage response. Therefore, it is important to understand the connection between system level neural network behavior and DNA. Neural networks drawn from genetically engineered animals, interfaced with micro-electrode arrays allowed us to unveil connections between networks’ system level activity properties and such genome instability. We discovered that Atm protein deficiency, which in humans leads to progressive motor impairment, leads to a reduced synchronization persistence compared to wild type synchronization, after chemically imposed DNA damage. Not only do these results suggest a role for DNA stability in neural network activity, they also establish an experimental paradigm for empirically determining the role a gene plays on the behavior of a neural network.

Computational Fluid Dynamics Expert System using Artificial Neural Networks

The design of a modern aircraft is based on three pillars: theoretical results, experimental test and computational simulations. As a results of this, Computational Fluid Dynamic (CFD) solvers are widely used in the aeronautical field. These solvers require the correct selection of many parameters in order to obtain successful results. Besides, the computational time spent in the simulation depends on the proper choice of these parameters. In this paper we create an expert system capable of making an accurate prediction of the number of iterations and time required for the convergence of a computational fluid dynamic (CFD) solver. Artificial neural network (ANN) has been used to design the expert system. It is shown that the developed expert system is capable of making an accurate prediction the number of iterations and time required for the convergence of a CFD solver.

Suitability of artificial neural networks for designing LoC circuits

he simulation of complex LoC (Lab-on-a-Chip) devices is a process that requires solving computationally expensive partial differential equations. An interesting alternative uses artificial neural networks for creating computationally feasible models based on MOR techniques. This paper proposes an approach that uses artificial neural networks for designing LoC components considering the artificial neural network topology as an isomorphism of the LoC device topology. The parameters of the trained neural networks are based on equations for modeling microfluidic circuits, analogous to electronic circuits. The neural networks have been trained to behave like AND, OR, Inverter gates. The parameters of the trained neural networks represent the features of LoC devices that behave as the aforementioned gates. This would mean that LoC devices universally compute.

Pollutant concentrations and Meteorological data classification by Neural Networks

This paper present an environmental contingency forecasting tool based on Neural Networks (NN). Forecasting tool analyzes every hour and daily Sulphur Dioxide (SO2) concentrations and Meteorological data time series. Pollutant concentrations and meteorological variables are self-organized applying a Self-organizing Map (SOM) NN in different classes. Classes are used in training phase of a General Regression Neural Network (GRNN) classifier to provide an air quality forecast. In this case a time series set obtained from Environmental Monitoring Network (EMN) of the city of Salamanca, Guanajuato, México is used. Results verify the potential of this method versus other statistical classification methods and also variables correlation is solved.