Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Networks”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 901 records · Page 50Linked to original sources
PubMed2006

On the sensitive dependence on initial conditions of the dynamics of networks of spiking neurons.

We have previously formulated an abstract dynamical system for networks of spiking neurons and derived a formal result that identifies the criterion for its dynamics, without inputs, to be "sensitive to initial conditions". Since formal results are applicable only to the extent to which their assumptions are valid, we begin this article by demonstrating that the assumptions are indeed reasonable for a wide range of networks, particularly those that lack overarching structure. A notable aspect of the criterion is the finding that sensitivity does not necessarily arise from randomness of connectivity or of connection strengths, in networks. The criterion guides us to cases that decouple these aspects: we present two instructive examples of networks, one with random connectivity and connection strengths, yet whose dynamics is insensitive, and another with structured connectivity and connection strengths, yet whose dynamics is sensitive. We then argue based on the criterion and the gross electrophysiology of the cortex that the dynamics of cortical networks ought to be almost surely sensitive under conditions typically found there. We supplement this with two examples of networks modeling cortical columns with widely differing qualitative dynamics, yet with both exhibiting sensitive dependence. Next, we use the criterion to construct a network that undergoes bifurcation from sensitive dynamics to insensitive dynamics when the value of a control parameter is varied. Finally, we extend the formal result to networks driven by stationary input spike trains, deriving a superior criterion than previously reported.

Action Potentials↗
PubMed2005

A mixture of experts network structure for breast cancer diagnosis.

Mixture of experts (ME) is a modular neural network architecture for supervised learning. This paper illustrates the use of ME network structure to guide diagnosing of breast cancer. Expectation-maximization (EM) algorithm was used for training the ME so that the learning process is decoupled in a manner that fits well with the modular structure. Diagnosis tasks are among the most interesting activities in which to implement intelligent systems. Specifically, diagnosis is an attempt to accurately forecast the outcome of a specific situation, using as input information obtained from a concrete set of variables that potentially describe the situation. The ME network structure was implemented for breast cancer diagnosis using the attributes of each record in the Wisconsin breast cancer database. To improve diagnostic accuracy, the outputs of expert networks were combined by a gating network simultaneously trained in order to stochastically select the expert that is performing the best at solving the problem. For the Wisconsin breast cancer diagnosis problem, the obtained total classification accuracy by the ME network structure was 98.85%. The ME network structure achieved accuracy rates which were higher than that of the stand-alone neural network models.

Algorithms↗
PubMed1993

Remapping of neural activity in the motor colliculus: a neural network study.

Neurophysiological studies have shown that the deeper layers of the superior colliculus (SC) contain a topographical neural map representing the ocular vectorial displacement required for foveation of the target (motor error). It is known that the location of the active area in this neural map can be updated, not only following changes in retinal error, but also by efference-copy signals representing a change in eye position. Since it can be shown that a two-layer feedforward network cannot perform this task, we have simulated this system by training a three-layered neural network with access to retinal error and efference copy information about eye position. The network was taught to code motor error topographically (as in the collicular motor map) by generating population activity at the appropriate location in its output layer for different combinations of visual and efference copy signals. After the network had learned the required remapping transformation with sufficient precision (error of one deg over an 80 x 80 deg working range), the properties of the trained network were analyzed. From an investigation of the activity patterns of the hidden units in the trained network it appeared that information about target location relative to the head, implicitly present at the level of input signals, is no longer available at the level of the hidden layer. More detailed inspection of the properties of these units revealed that they code motor error. Their movement field is a monotonic function of motor error amplitude, and shows broad direction tuning specific for each unit. Finally, simulations were made with a four layered network with an architecture and access to input signals closely mimicking Robinson's model of the saccadic system. Again, the network was trained to represent motor error topographically in its output layer. The model shows, for the first time, how the computation of the topographical motor error map in the SC from retinal and eye position signals may proceed in two steps, involving a stage where target location is coded in a distributed fashion in craniotopic coordinates and a subsequent supracollicular stage, where radial motor error is represented in a firing-rate code in units with broad tuning characteristics. These two stages in the model show interesting similarities with the characteristics of neuron populations shown neurophysiologically in area 7a and parietal region LIP, respectively.

Brain Mapping↗
PubMed1995

Artificial neural network and classical least-squares methods for neurotransmitter mixture analysis.

Identification of individual components in biological mixtures can be a difficult problem regardless of the analytical method employed. In this work, Raman spectroscopy was chosen as a prototype analytical method due to its inherent versatility and applicability to aqueous media, making it useful for the study of biological samples. Artificial neural networks (ANNs) and the classical least-squares (CLS) method were used to identify and quantify the Raman spectra of the small-molecule neurotransmitters and mixtures of such molecules. The transfer functions used by a network, as well as the architecture of a network, played an important role in the ability of the network to identify the Raman spectra of individual neurotransmitters and the Raman spectra of neurotransmitter mixtures. Specifically, networks using sigmoid and hyperbolic tangent transfer functions generalized better from the mixtures in the training data set to those in the testing data sets than networks using sine functions. Networks with connections that permit the local processing of inputs generally performed better than other networks on all the testing data sets. and better than the CLS method of curve fitting, on novel spectra of some neurotransmitters. The CLS method was found to perform well on noisy, shifted, and difference spectra.

Acetylcholine↗
PubMed1994

How to improve a neural network for early detection of hepatic cancer.

Radiologists perform differential diagnoses of hepatic (liver) masses using ultrasonography (US), computed tomography (CT), magnetic resonance imaging (MRI), and laboratory tests, but interpretation is often difficult. In our earlier research, a backpropagation neural network was designed to diagnose five classifications of hepatic masses: metastatic carcinoma, hepatoma, cavernous hemangioma, abscess, and cirrhosis. After being trained using ultrasonographic data and laboratory tests, the network classified hepatic masses correctly in 51 of 72 cases. That accuracy of 71% is higher than the 50% scored by the average radiology resident in training but lower than the 90% scored by the typical board-certified radiologist. What do we need to do to increase that accuracy and make the network friendly enough that radiologists will use it in their diagnoses? We have reviewed the literature, discussed alternatives and developed a plan to improve the diagnostic accuracy of the networks. That plan consists of: (i) get many more patient cases and more data variables, including MRI and CT data, so the network can be more highly trained. A shortage of enough patient cases to properly train the network is the key problem; (ii) use genetic algorithms and other techniques to preprocess the data; (iii) the network should have an optical interface to read images directly; and (iv) build a user-friendly interface using the C programming language on a 486 microcomputer. Continued research along the guidelines in this study should provide a sophisticated neural network for early detection of hepatic cancer that hopefully will exceed the diagnostic abilities of most radiologists.

Carcinoma, Hepatocellular↗
PubMed1995

One-year mortality prognosis in heart failure: a neural network approach based on echocardiographic data.

OBJECTIVES: This study sought to assess the usefulness and accuracy of artificial neural networks in the prognosis of 1-year mortality in patients with heart failure. BACKGROUND: Artificial neural networks is a computational technique used to represent and process information by means of networks of interconnected processing elements, similar to neurons. They have found applications in medical decision support systems, particularly in prognosis. METHODS: Clinical and Doppler-derived echocardiographic data from 95 consecutive patients with diffuse impairment of myocardial contractility were studied. After 1 year, data regarding survival or death were obtained and produced the prognostic variable. The data base was divided randomly into a training data set (47 cases, 8 deaths) and a testing data set (48 cases, 7 deaths). Results of artificial neural network classification were compared with those from linear discriminant analysis, clinical judgment and conventional heuristically based programs. RESULTS: The study group included 57 male (47 survivors) and 38 female patients (33 survivors). Linear discriminant analysis was not efficient for separating survivors from nonsurvivors because the accuracy at the ideal cutoff value was only 67.4%, with a sensitivity of 67.5%, positive predictive value of 27.8% and negative predictive value of 91.5%. In contrast, all artificial neural networks were able to predict outcome with an accuracy of 90%, specificity of 93% and sensitivity of 71.4%, for the best artificial neural network. Both clinical judgment and automatic heuristic methods were also inferior in performance. CONCLUSIONS: The artificial neural network method has proved to be reliable for implementing quantitative prognosis of mortality in patients with heart failure. Additional studies with larger numbers of patients are required to better assess the usefulness of artificial neural networks.

Adolescent↗
PubMed1993

A tutorial introduction to stochastic simulation algorithms for belief networks.

Belief networks combine probabilistic knowledge with explicit information about conditional independence assumptions. A belief network consists of a directed acyclic graph in which the nodes represent variables and the edges express relationships of conditional dependence. When information about one variable's state is given to the network in the form of evidence, an update algorithm computes the posterior marginal probability distributions for the remaining variables in the network. Many algorithms for performing this inference task have been proposed. Exact algorithms report precise results for some classes of networks, but take exponential time (in the number of nodes) both in the worst case and for many interesting networks. Stochastic simulation algorithms estimate the posterior marginal probability distribution for many graph topologies that would require exponential time when using an exact algorithm. Nonetheless, for some belief networks, stochastic simulation algorithms are also known to have exponential worst case performance. This article describes at a tutorial level several stochastic simulation algorithms for belief networks, and illustrates them on some simple examples. In addition, the theoretical and empirical performance of the algorithms is briefly surveyed.

Algorithms↗
PubMed2006

On the potential of personal networks for hospitals.

OBJECTIVE: Today, there are many barriers that prevent seamless electronic voice and data communication with remote content and services that the user wants to access at a certain time and place. This is especially the case in hospitals, where the communication needs are very complex and context dependent, and where strict privacy and safety conditions apply. Personal network (PN) technology is expected to enable the various private networks of a single person to communicate seamlessly with each other, hiding underlying network complexity from the user. We have analyzed the usefulness of PNs in hospitals. METHODS: We studied the use case of a medical emergency surgery, and built a demonstrator by integrating models of the specialists' personal area networks, home networks, office networks, and a hospital network into a single virtual network. We performed user studies in various hospitals, using a combination of individual context interviews, scenario and requirements verification, guided experimenting with the demonstrator and concluding workshops. RESULTS: We show that, in case of medical emergencies, PNs can provide a means to enlist remote assistance from peers wherever they are in the world at a particular moment. It can also ease the communication between the operating theatre and the outside world, e.g. for educational purposes.

Computer Communication Networks↗
PubMed2006

The cognit: a network model of cortical representation.

The prevalent concept in modular models is that there are discrete cortical domains dedicated more or less exclusively to such cognitive functions as visual discrimination, language, spatial attention, face recognition, motor programming, memory retrieval, and working memory. Most of these models have failed or languished for lack of conclusive evidence. In their stead, network models are emerging as more suitable and productive alternatives. Network models are predicated on the basic tenet that cognitive representations consist of widely distributed networks of cortical neurons. Cognitive functions, namely perception, attention, memory, language, and intelligence, consist of neural transactions within and between these networks. The present model postulates that memory and knowledge are represented by distributed, interactive, and overlapping networks of neurons in association cortex. Such networks, named cognits, constitute the basic units of memory or knowledge. The association cortex of posterior-post-rolandic-regions contains perceptual cognits: cognitive networks made of neurons associated by information acquired through the senses. Conversely, frontal association cortex contains executive cognits, made of neurons associated by information related to action. In both posterior and frontal cortex, cognits are hierarchically organized. At the bottom of that organization-that is, in parasensory and premotor cortex-cognits are small and relatively simple, representing simple percepts or motor acts. At the top of the organization-in temporo-parietal and prefrontal cortex-cognits are wider and represent complex and abstract information of perceptual or executive character. Posterior and frontal networks are associated by long reciprocal cortico-cortical connections. These connections support the dynamics of the perception-action cycle in sequential behavior, speech, and reasoning.

Animals↗
PubMedDate not supplied

Social network structure and social support in HIV-positive inner city mothers.

It has been documented that social support influences health outcomes of persons with chronic illnesses. The incidence of HIV and AIDS among minority women is growing at an alarming rate, but little is known about social support in this vulnerable population, and even less is known about the social network conveying that support. Guided by the convoy of social networks model, this study describes the social networks in a sample of HIV-positive, urban-dwelling mothers (N = 147) by stage of disease (i.e., asymptomatic, symptomatic, AIDS) and examines relationships between social network structure and social support. Hierarchical linear modeling showed that women's social networks were disproportionately populated by children, and network members of women with AIDS were significantly older than network members of HIV-positive women with or without symptoms. Profile analyses showed that women's perceptions of the quality of social support differed according to the proportion of family members populating different segments of the social network.

Adaptation, Psychological↗
PubMed2006

Risk factor identification and mortality prediction in cardiac surgery using artificial neural networks.

OBJECTIVE: The artificial neural network model is a nonlinear technology useful for complex pattern recognition problems. This study aimed to develop a method to select risk variables and predict mortality after cardiac surgery by using artificial neural networks. METHODS: Prospectively collected data from 18,362 patients undergoing cardiac surgery at 128 European institutions in 1995 (the European System for Cardiac Operative Risk Evaluation database) were used. Models to predict the operative mortality were constructed using artificial neural networks. For calibration a sixfold cross-validation technique was used, and for testing a fourfold cross-testing was performed. Risk variables were ranked and minimized in number by calibrated artificial neural networks. Mortality prediction with 95% confidence limits for each patient was obtained by the bootstrap technique. The area under the receiver operating characteristics curve was used as a quantitative measure of the ability to distinguish between survivors and nonsurvivors. Subgroup analysis of surgical operation categories was performed. The results were compared with those from logistic European System for Cardiac Operative Risk Evaluation analysis. RESULTS: The operative mortality was 4.9%. Artificial neural networks selected 34 of the total 72 risk variables as relevant for mortality prediction. The receiver operating characteristics area for artificial neural networks (0.81) was larger than the logistic European System for Cardiac Operative Risk Evaluation model (0.79; P = .0001). For different surgical operation categories, there were no differences in the discriminatory power for the artificial neural networks (P = .15) but significant differences were found for the logistic European System for Cardiac Operative Risk Evaluation (P = .0072). CONCLUSIONS: Risk factors in a ranked order contributing to the mortality prediction were identified. A minimal set of risk variables achieving a superior mortality prediction was defined. The artificial neural network model is applicable independent of the cardiac surgical procedure.

Adolescent↗
PubMed2004

Local design principles of mammalian cortical networks.

To understand global and local design principles of mammalian cerebral cortical networks, we applied network-theoretical approaches to connectivity data from macaque and cat cortical networks. We first confirmed "small-world" properties and searched for the evidence of hierarchical modularity. To elucidate their local design principles, we then compared these cortical networks, based on the significance profile (SP) of network motifs in the real network compared to randomized networks. We found that SPs of different mammalian cortical networks are highly conserved and robust, suggesting constraints of neocortical development and evolution.

Animals↗
PubMed1995

Artificial neural networks for recognition of electrocardiographic lead reversal.

Misplacement of electrodes during the recording of an electrocardiogram (ECG) can cause an incorrect interpretation, misdiagnosis, and subsequent lack of proper treatment. The purpose of this study was twofold: (1) to develop artificial neural networks that yield peak sensitivity for the recognition of right/left arm lead reversal at a very high specificity; and (2) to compare the performances of the networks with those of 2 widely used rule-based interpretation programs. The study was based on 11,009 ECGs recorded in patients at an emergency department using computerized electrocardiographs. Each of the ECGs was used to computationally generate an ECG with right/left arm lead reversal. Neural networks were trained to detect ECGs with right/left arm lead reversal. Different networks and rule-based criteria were used depending on the presence or absence of P waves. The networks and the criteria all showed a very high specificity (99.87% to 100%). The neural networks performed better than the rule-based criteria, both when P waves were present (sensitivity 99.1%) or absent (sensitivity 94.5%). The corresponding sensitivities for the best criteria were 93.9% and 39.3%, respectively. An estimated 300 million ECGs are recorded annually in the world. The majority of these recordings are performed using computerized electrocardiographs, which include algorithms for detection of right/left arm lead reversals. In this study, neural networks performed better than conventional algorithms and the differences in sensitivity could result in 100,000 to 400,000 right/left arm lead reversals being detected by networks but not by conventional interpretation programs.

Algorithms↗
PubMed1997

Coronary artery bypass risk prediction using neural networks.

BACKGROUND: Neural networks are nonparametric, robust, pattern recognition techniques that can be used to model complex relationships. METHODS: The applicability of multilayer perceptron neural networks (MLP) to coronary artery bypass grafting risk prediction was assessed using The Society of Thoracic Surgeons database of 80,606 patients who underwent coronary artery bypass grafting in 1993. The results of traditional logistic regression and Bayesian analysis were compared with single-layer (no hidden layer), two-layer (one hidden layer), and three-layer (two hidden layer) MLP neural networks. These networks were trained using stochastic gradient descent with early stopping. All prediction models used the same variables and were evaluated by training on 40,480 patients and cross-validation testing on a separate group of 40,126 patients. Techniques were also developed to calculate effective odds ratios for MLP networks and to generate confidence intervals for MLP risk predictions using an auxiliary "confidence MLP." RESULTS: Receiver operating characteristic curve areas for predicting mortality were approximately 76% for all classifiers, including neural networks. Calibration (accuracy of posterior probability prediction) was slightly better with a two-member committee classifier that averaged the outputs of a MLP network and a logistic regression model. Unlike the individual methods, the committee classifier did not overestimate or underestimate risk for high-risk patients. CONCLUSIONS: A committee classifier combining the best neural network and logistic regression provided the best model calibration, but the receiver operating characteristic curve area was only 76% irrespective of which predictive model was used.

Bayes Theorem↗
PubMed2002

Combining neural network predictions for medical diagnosis.

We present our results from combining the predictions of an ensemble of neural networks for the diagnosis of hepatobiliary disorders. To improve the accuracy of the diagnosis, we train the second level networks using the outputs of the first level networks as input data. The second level networks achieve an accuracy that is higher than that of the individual networks in the first level. Compared to the simple method which averages the outputs of the first level networks, the second level networks are also more accurate. We discuss how the overall predictive accuracy can be improved by introducing bias during the training of the level one networks.

Bias↗
PubMed2000

Pattern classification by a neurofuzzy network: application to vibration monitoring.

An innovative neurofuzzy network is proposed herein for pattern classification applications, specifically for vibration monitoring. A fuzzy set interpretation is incorporated into the network design to handle imprecise information. A neural network architecture is used to automatically deduce fuzzy if-then rules based on a hybrid supervised learning scheme. The neurofuzzy classifier proposed is equipped with a one-pass, on-line, and incremental learning algorithm. This network can be considered a self-organized classifier with the ability to adaptively learn new information without forgetting old knowledge. The classification performance of the proposed neurofuzzy network is validated on the Fisher's Iris data, which is a well-known benchmark data set. For the generalization capability, the neurofuzzy network can achieve 97.33% correct classification. In addition, to demonstrate the efficiency and effectiveness of the proposed neurofuzzy paradigm, numerical simulations have been performed using the Westland data set. The Westland data set consists of vibration data collected from a US Navy CH-46E helicopter test stand. Using a simple fast Fourier transform technique for feature extraction, the proposed neurofuzzy network has shown promising results. Using various torque levels for training and testing, the network achieved 100% correct classification.

Algorithms↗
PubMed1998

Novel staging tool for localized prostate cancer: a pilot study using genetic adaptive neural networks.

PURPOSE: An estimated $1.5 billion is spent annually for direct medical expenses and an additional $2.5 billion for indirect costs for the management of prostate cancer. Today there are several procedures for staging prostate cancer, including lymph node dissection. Despite these procedures, the accuracy of predicting extracapsular disease remains low (range 37 to 63, mean 45%). Use of multiple staging procedures adds significantly to the costs of managing prostate cancer. Recently artificial intelligence based neural networks have become available for medical applications. Unlike traditional statistical methods, these networks do not assume linearity or homogeneity of variance and, thus, they are more accurate for clinical data. We applied this concept to staging localized prostate cancer and devised an algorithm that can be used for prostate cancer staging. MATERIALS AND METHODS: Our study comprised 1,200 men with clinically organ confined prostate cancer who underwent preoperative staging using serum prostate specific antigen, systematic biopsy and Gleason scoring before radical prostatectomy and lymphadenectomy. The performance of the neural network was validated for a subset of patients and network predictions were compared with actual pathological stage. Mean patient age was 62.9 years, mean serum prostate specific antigen 8.1 ng./ml. and mean biopsy Gleason 6. Of the patients 55% had organ confined disease, 27% positive margins, 8% seminal vesicle involvement and 7% lymph node disease. Of margin positive patients 30% also had seminal vesicle involvement, while of seminal vesicle positive patients 50% also had positive margins. RESULTS: The sensitivity of the network was 81 to 100%, and specificity was 72 to 75% for various predictions of margin, seminal vesicle and lymph node involvement. The negative predictive values tended to be relatively high for all 3 features (range 92 to 100%). The neural network missed only 8% of patients with margin positive disease, and 2% with lymph node and 0% with seminal vesicle involvement. CONCLUSIONS: Our study suggests that neural networks may be useful as an initial staging tool for detection of extracapsular extension in patients with clinically organ confined prostate cancer. These networks preclude unnecessary staging tests for 63% of patients with clinically organ confined prostate cancer.

Algorithms↗
PubMed2002

A preliminary evaluation of neural network analysis for pharmacodynamic modeling of the dosing of the hydroxymethylglutaryl coenzyme A-reductase inhibitors simvastatin and atorvastatin.

BACKGROUND: Neural networks have been used in diagnosing and treating many diseases, including the diagnosis of myocardial infarction and insulin dosing in diabetes mellitus. OBJECTIVE: The goal of this study was to develop a preliminary pharmacodynamic model for dosing of the hydroxymethylglutaryl coenzyme A (HMG-CoA)-reductase inhibitors simvastatin and atorvastatin using neural network analysis. METHODS: Using NeuralSIM neural network software (NeuralWare, Carnegie, Pa), lipid panels from patients at a hospital lipid clinic were entered as inputs for the model, and the doses of simvastatin or atorvastatin that achieved those lipid results were used as outputs. The network was trained using 2 different data sets and was run using a subset of the data as inputs. The results of the neural network run (predictions) were compared with the actual doses used as directed by the hospital pharmacist in accordance with the lipid clinic protocol. RESULTS: Complete data sets were available for 17 patients (11 men, 6 women). The mean age of these patients was 56.7 years (range, 40-67 years). The neural network model based on data set 1 predicted a dose that was within 95% of the actual dose 7 of 12 times and predicted use of the drug actually used 13 of 19 (68.4%) times. The neural network based on data set 2 predicted use of the drug actually used 10 of 17 (58.8%) times, but the predicted doses never approximated the actual doses by > or = 90%. CONCLUSIONS: A neural network model for the dosing of the HMG-CoA-reductase inhibitors simvastatin and atorvastatin demonstrated an ability to predict appropriate dosing, but inclusion of other factors (eg, age, body weight, sex) and a larger sample size may be necessary for development of a more accurate model.

Adult↗