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 1,333 records · Page 74Linked to original sources
PubMed1992

Application of artificial neural network to computer-aided diagnosis of coronary artery disease in myocardial SPECT bull's-eye images.

We have developed a computerized system that can aid in the radiologist's diagnosis in the detection and classification of coronary artery diseases. The technique employs a neural network to analyze 201Tl myocardial SPECT bull's-eye images. This multi-layer feed-forward neural network with a backpropagation algorithm has 256 input units (pattern: compressed 16 x 16-matrix images), 5-140 units in a single hidden layer, and eight output units (diagnosis: one normal and seven different types of abnormalities). The neural network was taught using pairs of training (learning) input data (bull's-eye "EXTENT" image) and desired output data ("correct" diagnosis). The effects of the numbers of hidden units and learning iterations in the network on the recognition performance were examined. In our initial stage, the results show that the recognition performance of the neural network is better than that of the radiology resident but worse than that of the experienced radiologist. Our study also demonstrates that the result produced in the neural network depends on the variety of the training examples used. The preliminary study suggests that the neural network approach is useful for the computer-aided diagnosis of coronary artery diseases in myocardial SPECT bull's-eye images.

Coronary Disease↗
PubMed1995

GENESIS as a neural network modeling tool for saccadic eye movements.

Interest in exploring the computational properties of networks of parallel distributed processing elements has increased due to studies of the structure and function of biological neural networks. Much of the current research involves numerical simulations of these types of networks. GENESIS (GEneral NEtwork SImulation System) and XODUS (X-based Ouput and Display Utility for Simulators) are a result of that interest. The two systems combined provides a standardized and flexible means of constructing neural networks. The structure of GENESIS follows the actual biological network much more closely than artificial neural networks. This paper presents a simple simulation of the cable properties of a dendritic cable consisting of twenty compartments and one soma. The results of the simulation are then compared to actual cable metrics.

Animals↗
PubMed1994

A high-speed network for cardiac image review.

A high-speed fiber-based network for the transmission and display of digitized full-motion cardiac images has been developed. Based on Asynchronous Transfer Mode (ATM), the network is scaleable, meaning that the same software and hardware is used for a small local area network or for a large multi-institutional network. The system can handle uncompressed digital angiographic images, considered to be at the "high-end" of the bandwidth requirements. Along with the networking, a general-purpose multi-modality review station has been implemented without specialized hardware. This station can store a full injection sequence in "loop RAM" in a 512 x 512 format, then interpolate to 1024 x 1024 while displaying at 30 frames per second. The network and review stations connect to a central file server that uses a virtual file system to make a large high-speed RAID storage disk and associated off-line storage tapes and cartridges all appear as a single large file system to the software. In addition to supporting archival storage and review, the system can also digitize live video using high-speed Direct Memory Access (DMA) from the frame grabber to present uncompressed data to the network. Fully functional prototypes have provided the proof of concept, with full deployment in the institution planned as the next stage.

Cardiology↗
PubMed1994

Neural network-based detection of esophageal intubation.

To improve the accuracy of early detection of inadvertent esophageal intubation, we designed, trained, and tested a neural network-based computer system to detect the mechanical differences between lung and esophagogastric ventilation. Ten 25 to 30-kg anesthetized swine were sequentially ventilated with tidal volumes of 9, 12, and 15 mL/kg, using tubes placed in the trachea and in the esophagus, while flow and pressure waveforms were collected for 9-10 breaths. Gas remaining in the stomach was aspirated after each period of gastric ventilation. A computer program identified each mechanical inspiration, extracted the first 37 flow and pressure data points from each record, and normalized them to an equal amplitude. A back-propagation single-hidden-layer neural network was trained to identify the origin of flow and pressure waveforms as tracheal or esophageal. Ten different training and testing groups were assembled. In each group, data from nine subjects were used for training and data from the remaining subjects were used for testing. A total of 291 esophageal and 300 tracheal flow and pressure waveforms were analyzed by the network. The network identified esophageal intubation correctly during the first five breaths of all esophageal recordings. In one subject, the network identified the eighth esophageal breath as tracheal and could not identify three breaths. All tracheal intubations were identified correctly. Flow and pressure "signatures" of pulmonary and gastric ventilation are easily learned by a neural network. Therefore, neural-network recognition of esophageal intubation from flow and pressure signals is possible, and the development of an on-line detector for tracheal tube misplacement seems feasible.

Animals↗
PubMed1993

Overtraining in neural networks that interpret clinical data.

Backpropagation neural networks are a computer-based pattern-recognition method that has been applied to the interpretation of clinical data. Unlike rule-based pattern recognition, backpropagation networks learn by being repetitively trained with examples of the patterns to be differentiated. We describe and analyze the phenomenon of overtraining in backpropagation networks. Overtraining refers to the reduction in generalization ability that can occur as networks are trained. The clinical application we used was the differentiation of giant cell arteritis (GCA) from other forms of vasculitis (OTH) based on results for 807 patients (593 OTH, 214 GCA) and eight clinical predictor variables. The 807 cases were randomly assigned to either a training set with 404 cases or to a cross-validation set with the remaining 403 cases. The cross-validation set was used to monitor generalization during training. Results were obtained for eight networks, each derived from a different random assignment of the 807 cases. Training error monotonically decreased during training. In contrast, the cross-validation error usually reached a minimum early in training while the training error was still decreasing. Training beyond the minimum cross-validation error was associated with an increased cross-validation error. The shape of the cross-validation error curve and the point during training corresponding to the minimum cross-validation error varied with the composition of the data sets and the training conditions. The study indicates that training error is not a reliable indicator of a network's ability to generalize. To find the point during training when a network generalizes best, one must monitor cross-validation error separately.

Bias↗
PubMed1995

Management of uncertainty in breast cancer grading with Bayesian belief networks.

OBJECTIVE: To examine the potential of different constructs of Bayesian belief networks (BBN) to manage uncertainty in breast cancer grading. STUDY DESIGN: We developed four networks, two based on Bloom-Richardson's and two on Helpap's grading systems. The function of the networks was based either on an expert's experience or frequency counts derived from subjective grading of a large number of samples. The four BBNs were tested on 20 specimens, and the resulting final beliefs were compared with the subjective gradings. RESULTS: The BBNs showed agreement with the subjective gradings in 60-85% of cases. Different constructs of BBNs, however, differed in their performance. The mean beliefs in frequency-based networks were slightly higher than in experience-based networks. In addition, as compared with the Bloom-Richardson-based networks, the Helpap-based BBNs resulted in higher maximum beliefs but produced a larger fraction of discrepancies with the subjectively graded cases. Depending on the type of network, 65-90% of the BBN grades were associated with high beliefs. CONCLUSION: The results suggest that for reliable results, grading systems with more than three or four variables may be necessary. When based on relevant information, BBNs seem to have the potential to become a valuable method of assisting the pathologist in breast cancer grading.

Breast Neoplasms↗
PubMed1996

A network approach to outpatient service delivery systems: resources flow and system influence.

OBJECTIVE: The study tests a path model for the effects on organizational influence of an organization's centrality in four resource exchange networks in order to gain insight into the network relations that may affect coordination and effectiveness of outpatient health and mental health service systems. DATA SOURCES: Primary data are used from face-to-face interviews with the directors of every organization in the predefined service systems in three urbanized counties in Oregon. Each system consisted of 19 to 20 organizations. Data were collected during 1986 and 1987. STUDY DESIGN: The path model contains five variables: the major dependent variable is attributed organizational influence; the independent variables are three sets of primary resource exchanges: funds allocation, client referrals, and client inflow. An intervening variable of general network contacts, as an informational resource, is modeled as an outcome of the three primary resource exchanges, as well as one of the predictors of influence. DATA COLLECTION: Organizations were identified as system members through a modified snowball sampling procedure. Measures of organizational influence and centrality in each of the exchange networks were derived from interviews with all directors about their interactions with each organization in the system. Multiple regression analysis was used to test the path model. PRINCIPAL FINDINGS: The most important resource in predicting centrality in a general contact network is centrality in a client referral network, while contacts and funds allocation centrality are significant predictors of organizational influence. CONCLUSIONS: The organization with the greatest influence within the system (because of its ability to allocate funds) may not be the organization that takes the largest role in terms of coordinating routine contacts (because of its ability to refer clients). This disjuncture may signal a weakness in the coordination network and system effectiveness, since the more influential organization may not be the most knowledgeable one in terms of the needs of the system.

Ambulatory Care↗
PubMed1995

Social and sexual networks: their role in the spread of HIV/AIDS among young gay men.

This article examines how networks of social and sexual relations affect risky sexual behavior and HIV seroprevalence among young gay men. Social networks can transmit information and cultural norms regarding safer sex, while networks of sexual partners channel the risk of exposure to HIV infection. These two network effects may help to explain some of the behavior and seroconversion differentials in the gay community. A number of recent studies have shown higher rates of unsafe sex among younger gay men. In the Longitudinal AIDS Impact Project, for example, younger gay men (18-24) report unsafe receptive anal sex at rates double that for any other age group (30% vs. 14-16%). One possible explanation is that younger men have watched fewer friends and colleagues contract HIV or AIDS, and are correspondingly less cautious. We test this hypothesis by comparing the personal networks of younger and older gay men to see whether those who practice safer sex have more exposure to persons with HIV or AIDS. The results give only weak support for the hypothesis that personal exposure to the effects of HIV and AIDS increases adherence to safer sex practices. Seroprevalence patterns among young men may be the result of their sexual networks, with those choosing older partners more likely to be exposed to HIV infection. We examine this hypothesis by comparing the age composition of the unsafe sexual partner network for seropositive and seronegative young men. The results strongly support the hypothesis that younger gay men with older partners are the leading edge of the epidemic in their cohort.

Acquired Immunodeficiency Syndrome↗
PubMed1996

Gamma oscillation by synaptic inhibition in a hippocampal interneuronal network model.

Fast neuronal oscillations (gamma, 20-80 Hz) have been observed in the neocortex and hippocampus during behavioral arousal. Using computer simulations, we investigated the hypothesis that such rhythmic activity can emerge in a random network of interconnected GABAergic fast-spiking interneurons. Specific conditions for the population synchronization, on properties of single cells and the circuit, were identified. These include the following: (1) that the amplitude of spike afterhyperpolarization be above the GABAA synaptic reversal potential; (2) that the ratio between the synaptic decay time constant and the oscillation period be sufficiently large; (3) that the effects of heterogeneities be modest because of a steep frequency-current relationship of fast-spiking neurons. Furthermore, using a population coherence measure, based on coincident firings of neural pairs, it is demonstrated that large-scale network synchronization requires a critical (minimal) average number of synaptic contacts per cell, which is not sensitive to the network size. By changing the GABAA synaptic maximal conductance, synaptic decay time constant, or the mean external excitatory drive to the network, the neuronal firing frequencies were gradually and monotonically varied. By contrast, the network synchronization was found to be high only within a frequency band coinciding with the gamma (20-80 Hz) range. We conclude that the GABAA synaptic transmission provides a suitable mechanism for synchronized gamma oscillations in a sparsely connected network of fast-spiking interneurons. In turn, the interneuronal network can presumably maintain subthreshold oscillations in principal cell populations and serve to synchronize discharges of spatially distributed neurons.

Animals↗
PubMed1996

Application of artificial neural networks to clinical pharmacology.

Drug dosages and drug choices are determined by a knowledge of the drug's pharmacokinetics and pharmacodynamics. Often, insufficient information is available to determine the pharmacokinetics of a drug or which drug will have a desired effect for an individual patient. We propose that a form of nonlinear regression, an artificial neural network, can be used. We have demonstrated this use with 2 examples. In the first example we use a neural network to predict gentamicin peak and trough concentrations from routine therapeutic drug monitoring. In the second example we predict delayed renal allograft function as a guide for induction of immunosuppression therapy. Predictions were made using a multilayer feedforward perceptron and compared to nonlinear mixed effect modeling (NONMEM) and logistic regression. Neural network peak and trough gentamicin predictions were more precise and less biased than control predictions made using NONMEM. Prediction error for peak serum concentrations averaged 16.5% for the neural networks and 18.6% for NONMEM. Prediction error for trough concentrations were 48.3% for neural networks and 59.0% for NONMEM. When used for the prediction of delayed graft function, the neural network correctly predicted immediate graft function 73% of the time and delayed graft function 65% of the time. For those patients predicted to develop delayed graft function, alternate induction using anti-lymphocyte globulin may be indicated. These 2 examples demonstrate how an artificial neural network may be applied to predictions in clinical pharmacology.

Anti-Bacterial Agents↗
PubMed1997

Prediction of trauma mortality using a neural network.

A neural network is a computerized construct consisting of input neurons (which process input data) connected to hidden neurons (to mathematically manipulate values they receive from all the input neurons) connected to output neurons (to output a prediction). Neural networks are created and trained via multiple iterations over data with known results. In 1993, 897 trauma patients were either declared dead in the emergency room (ER; 76 cases), admitted to the intensive care unit (427 cases, 36 deaths), or taken directly to the operating room (394 cases, 29 deaths). Using only data available from the ER, a neural network was created, and 628 cases were randomly selected for training. After 268 iterations, the network was trained to correctly predict death or survival in all 628 cases. This trained network was then tested on the other 269 cases without our providing the death or survival result. Its overall accuracy was 91 per cent (244 of 269 cases). It was able to predict correctly 60 per cent (12 of 20 cases) of the postoperative or post-intensive care unit admission deaths and 90 per cent (26 of 29 cases) of the deaths in the ER. Computerized neural networks can accurately predict a trauma patient's fate based on inital ER presentation. The theory and use of neural networks in predicting clinical outcome will be presented.

Age Factors↗
PubMed1997

Toward implementation of artificial neural networks that "really work".

Artificial neural networks are established analytical methods in bio-medical research. They have repeatedly outperformed traditional tools for pattern recognition and clinical outcome prediction while assuring continued adaptation and learning. However, successful experimental neural networks systems seldom reach a production state. That is, they are not incorporated into clinical information systems. It could be speculated that neural networks simply must undergo a lengthy acceptance process before they become part of the day to day operations of health care systems. However, our experience trying to incorporate experimental neural networks into information systems lead us to believe that there are technical and operational barriers that greatly difficult neural network implementation. A solution for these problems may be the delineation of policies and procedures for neural network implementation and the development a new class of neural network client/server applications that fit the needs of current clinical information systems.

Hospital Information Systems↗
PubMed1998

Artificial neural networks in pediatric urology: prediction of sonographic outcome following pyeloplasty.

PURPOSE: Computerized artificial neural networks are analogous to biological neuronal systems. Since they may be trained to recognize the relevance of complex patterns in data, neural networks may be useful for decision making in the multifactorial management of ureteropelvic junction obstruction. We determine the ability of a customized neural network to predict sonographic outcome after pyeloplasty in children with ureteropelvic junction obstruction. MATERIALS AND METHODS: A data set was constructed with 242 demographic, clinical, radiological and surgical elements. We analyzed the available retrospective data in 100 consecutive children who underwent unilateral pyeloplasty for ureteropelvic junction obstruction chosen from all 144 surgically treated for ureteropelvic junction obstruction between 1993 and 1995. One radiologist reviewed all film data and provided a final sonographic outcome designation in each case. We wrote a set of computer programs to construct a neural network. A composite 4-layer network was built with output nodes representing 4 possible sonographic outcomes. The 100 patient data set was randomly divided into 84 training and 16 testing examples. RESULTS: The neural network correctly predicted all 5 of 5 significantly improved, 7 of 7 improved, 2 of 2 same and 2 of 2 worse sonogram results after pyeloplasty. Therefore, sensitivity and specificity were 100% for all 4 outcomes. Linear regression analysis of the data yielded inferior sensitivity and specificity values (52 to 94%), confirming that ureteropelvic junction obstruction is a nonlinear data analysis problem. CONCLUSIONS: The 100% accuracy, sensitivity and specificity of our neural network in this pilot study provide evidence of the value of the neural computational approach for the modern exploration and modeling of the clinical problem of pediatric ureteropelvic junction obstruction.

Child↗
PubMed1998

Medical reduction of stone risk in a network of treatment centers compared to a research clinic.

PURPOSE: We determined whether a network of 7 comprehensive kidney stone treatment centers supported by specialized stone management software and laboratory resources could achieve reductions in urine supersaturation comparable to those in a single research clinic devoted to metabolic stone prevention. MATERIALS AND METHODS: Supersaturation values for calcium oxalate, calcium phosphate and uric acid in 24-hour urine samples were calculated from a set of kidney stone risk factor measurements made at a central laboratory site for the network and research laboratory for the clinic. Individual results and group outcomes were presented to each center in time sequential table graphics. The decrease in supersaturation with treatment was compared in the network and clinic using analysis of variance. RESULTS: Supersaturation was effectively reduced in the network and clinic, and the reduction was proportional to the initial supersaturation value and increase in urine volume. The clinic achieved a greater supersaturation reduction, higher fraction of patient followup and greater increase in urine volume but the treatment effects in the network were, nevertheless, substantial and significant. CONCLUSIONS: Given proper software and laboratory support, a network of treatment centers can rival but not quite match results in a dedicated metabolic stone research and prevention clinic. Therefore, large scale stone prevention in a network system appears feasible and effective.

Adult↗
PubMed1998

Organizational characteristics associated with agency position in community care networks.

This study examines how organizational characteristics affect agency participation and centrality in community service networks. We find that the network structure of agency relations varies for administrative and client-related activities among the 69 agencies studied, which include all but the most isolated agencies serving people with physical disabilities in a single community. In identifying structurally equivalent groups using network analysis, we find that all types of agencies except HMOs are found throughout community service networks. Analyses show that among the five types of relations, minimal intergroup activity occurs within funding and planning networks and that organizational size and ownership are the best organizational predictors of network location and centrality. Non-profits are the most central for planning and client referrals, and large agencies are the most central for funding. We explore the implications of these findings, particularly for sustaining cooperation within the service networks and for the role of non-profits and medical providers in the community.

Community Networks↗
PubMed2003

Self-similar community structure in a network of human interactions.

We propose a procedure for analyzing and characterizing complex networks. We apply this to the social network as constructed from email communications within a medium sized university with about 1700 employees. Email networks provide an accurate and nonintrusive description of the flow of information within human organizations. Our results reveal the self-organization of the network into a state where the distribution of community sizes is self-similar. This suggests that a universal mechanism, responsible for emergence of scaling in other self-organized complex systems, as, for instance, river networks, could also be the underlying driving force in the formation and evolution of social networks.

Algorithms↗
PubMed1999

Synthesis, physical characterization, and biological performance of sequential homointerpenetrating polymer network sponges based on poly(2-hydroxyethyl methacrylate).

A limitation in the use of hydrophilic poly(2-hydroxyethyl methacrylate) (PHEMA) sponges as implantable devices is their inherently poor mechanical strength. This precludes proper surgical manipulation, especially in the eye where the size of the implant is usually small. In this study a new method was developed to produce mechanically stronger PHEMA sponges. Sequential homointerpenetrating polymer network (homo-IPN) sponges were made by using HEMA as the precursor for generating both the first network and the successive interpenetrated networks. Following the formation of network I, the sponge was squeezed to remove the interstitial water, soaked in the second monomer (also HEMA), and squeezed again to remove the excess monomer from the pores before being subjected to the second polymerization leading to the formation of network II. Two two-component IPN sponges (K2 and K4) with increasing HEMA content in the network II and a three-component IPN sponge (K3) were produced, and their properties were compared to those of a homopolymer PHEMA sponge (control). Apart from elongation, the tensile properties were all significantly enhanced in the IPN sponges; the water content was the same as in the control sponge, except for sponge K4, which was lower. Light microscopy revealed similar pore morphologies of the control and IPN sponges K2 and K3, and the majority of the pores were around 25 microm. Sponge K4 displayed smaller pores of around 10 microm. Cellular invasion into the sponges was examined in vitro (incubation with 3T3 fibroblasts) and in vivo (implantation in rabbit corneas). Although the in vitro assay detected a change in the cell behavior in the early stage of invasion, which was probably due to the formation of IPNs, such changes were not reflected in the longer term in vivo experiment. There was a proper integration of sponges K2 and K3 with the corneal stroma, but much less cellular invasion and no neovascularization in sponge K4. We concluded that IPN formation is a valid method to enhance the strength of PHEMA sponges, provided that the content of HEMA in the successive networks is not too high.

Animals↗
PubMed1999

Establishing homology criteria for regulatory gene networks: prospects and challenges.

One of the most remarkable discoveries to emerge from the field of developmental genetics is the observation that many regulatory genes and segments of their interactive networks (pathways) appear to have been conserved in several metazoan phyla. Determining whether these conserved regulatory networks are homologous, i.e. derived from an equivalent network in the most recent common ancestor, is critical to understanding comparisons between model system studies, and the evolution of metazoan body plans. To this end, I outline some of the evolutionary properties of regulatory networks, and propose both similarity and phylogenetic criteria that can be used to test the hypothesis that two regulatory networks are homologous. Furthermore, I propose that genetic networks can be treated as a distinct level of biological organization, and can be analysed together with other hierarchical levels, such as genes, embryonic origins and morphological structures, in a comparative framework. Examples from the literature, particularly the genetic regulatory networks involved in patterning arthropod and vertebrate limbs, are examined using the proposed criteria and hierarchical approach.

Animals↗