Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “network analysis”

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 199 records · Page 11Linked to original sources
PubMed1992

A practical application of neural network analysis for predicting outcome of individual breast cancer patients.

It has been previously shown that Neural Networks can be trained to recognize individual breast cancer patients at high and low risk for recurrent disease and death. This paper expands on the initial investigation and shows that by coding time as one of the prognostic variables, a Neural Network can use censored survival data to predict patient outcome over time. In this demonstration a Neural Network was trained, tested, and validated using censored survival data from a group of 1373 patients with node-positive breast cancer. The Neural Network method predicted patient outcome as accurately as Cox Regression modeling. The final Neural Network model can be presented with a patient's prognostic information and make a series of predictions about probability of relapse at different times of follow-up, allowing one to draw survival probability curves for individual patients.

Adult↗
PubMedDate not supplied

A population density approach that facilitates large-scale modeling of neural networks: analysis and an application to orientation tuning.

We explore a computationally efficient method of simulating realistic networks of neurons introduced by Knight, Manin, and Sirovich (1996) in which integrate-and-fire neurons are grouped into large populations of similar neurons. For each population, we form a probability density that represents the distribution of neurons over all possible states. The populations are coupled via stochastic synapses in which the conductance of a neuron is modulated according to the firing rates of its presynaptic populations. The evolution equation for each of these probability densities is a partial differential-integral equation, which we solve numerically. Results obtained for several example networks are tested against conventional computations for groups of individual neurons. We apply this approach to modeling orientation tuning in the visual cortex. Our population density model is based on the recurrent feedback model of a hypercolumn in cat visual cortex of Somers et al. (1995). We simulate the response to oriented flashed bars. As in the Somers model, a weak orientation bias provided by feed-forward lateral geniculate input is transformed by intracortical circuitry into sharper orientation tuning that is independent of stimulus contrast. The population density approach appears to be a viable method for simulating large neural networks. Its computational efficiency overcomes some of the restrictions imposed by computation time in individual neuron simulations, allowing one to build more complex networks and to explore parameter space more easily. The method produces smooth rate functions with one pass of the stimulus and does not require signal averaging. At the same time, this model captures the dynamics of single-neuron activity that are missed in simple firing-rate models.

Action Potentials↗
PubMed2005

Social and geographical boundaries around senior nurse and physician leaders: an application of social network analysis.

The purpose of this study was to describe the social and geographical boundaries around the networks of senior nurse executives and physician leaders and managers in acute-care hospitals in the United Kingdom. A telephone survey was conducted using standard social network methods. A random sample was drawn from a national list and repeatedly sampled until 100 respondents were interviewed. The response rate was 49.5%. Both groups tended to discuss "important professional matters" with others who were similar to themselves in terms of profession, gender, age, and seniority, with physicians being more extreme in this regard. The implication is that gaps in the network of informal ties will impede the dissemination of information and the spread of social influence between these 2 important groups. Managers (non-clinically qualified) appear to occupy a powerful "brokerage" role. Informal networks are mainly composed of local ties. The authors argue that dissemination and influence strategies that take features of the social structure into account are more likely to be successful.

Geography↗
PubMed2006

Wavelet-based neural network analysis of internal carotid arterial Doppler signals.

In this study, internal carotid arterial Doppler signals recorded from 130 subjects, where 45 of them suffered from internal carotid artery stenosis, 44 of them suffered from internal carotid artery occlusion and the rest of them were healthy subjects, were classified using wavelet-based neural network. Wavelet-based neural network model, employing the multilayer perceptron, was used for analysis of the internal carotid arterial Doppler signals. Multi-layer perceptron neural network (MLPNN) trained with the Levenberg-Marquardt algorithm was used to detect stenosis and occlusion in internal carotid arteries. In order to determine the MLPNN inputs, spectral analysis of the internal carotid arterial Doppler signals was performed using wavelet transform (WT). The MLPNN was trained, cross validated, and tested with training, cross validation, and testing sets, respectively. All these data sets were obtained from internal carotid arteries of healthy subjects, subjects suffering from internal carotid artery stenosis and occlusion. The correct classification rate was 96% for healthy subjects, 96.15% for subjects having internal carotid artery stenosis and 96.30% for subjects having internal carotid artery occlusion. The classification results showed that the MLPNN trained with the Levenberg-Marquardt algorithm was effective to detect internal carotid artery stenosis and occlusion.

Adult↗
PubMed2006

Role of transrectal ultrasonography in the prediction of prostate cancer: artificial neural network analysis.

OBJECTIVE: The purpose of this study was to evaluate the diagnostic performance of an artificial neural network (ANN) model with and without transrectal ultrasonographic (TRUS) data. METHODS: Six hundred eighty-four consecutive patients who had undergone TRUS-guided prostate biopsy from May 2003 to January 2005 were enrolled. We constructed 2 ANN models. One (ANN_1) incorporated patient age, digital rectal examination findings, prostate-specific antigen (PSA) level, PSA density, transitional zone volume, and PSA density in the transitional zone as input data, whereas the other (ANN_2) was constructed with the above and TRUS findings as input data. The performances of these 2 ANN models according to PSA levels (group A, 0-4 ng/mL; group B, 4-10 ng/mL; and group C, >10 ng/mL) were evaluated using receiver operating characteristic analysis. RESULTS: Of the 684 patients who underwent prostate biopsy, 214 (31.3%) were confirmed to have prostate cancer; of 137 patients with positive digital rectal examination results, 60 (43.8%) were confirmed to have prostate cancer; and of 131 patients with positive TRUS findings, 93 (71%) were confirmed to have prostate cancer. In groups A, B, and C, the AUCs for ANN_1 were 0.738, 0.753, and 0.774, respectively; the AUCs for ANN_2 were 0.859, 0.797, and 0.894. In all groups, ANN_2 showed better accuracy than ANN_1 (P < .05). CONCLUSIONS: According to receiver operating characteristic analysis, ANN with TRUS findings was found to be more accurate than ANN without. We conclude that TRUS findings should be included as an input data component in ANN models used to diagnose prostate cancer.

Adult↗
PubMed1999

Artificial neural network analysis of common femoral artery Doppler shift signals: classification of proximal disease.

The aim of this study was to apply artificial neural networks (ANNs) to the problem of the diagnosis of aorto-iliac arterial disease on the basis of the profile of the common femoral artery (CFA) Doppler flow velocity waveform. The maximum frequency envelopes obtained from the CFA of 180 subjects were used to create sets of training and testing vectors for a back-propagation ANN. The ANN had three outputs: one representing the absence of significant aorto-iliac disease (i.e., < 50% diameter stenosis), one representing the presence of a hemodynamically significant aorto-iliac stenosis (i.e., 50-99% stenosis), and the other representing the presence of an aorto-iliac occlusion. After training, the ANN correctly classified 80% of "no significant disease" testing data, 45% of "significant stenosis" data and 85% of "occlusion" data. This work, thus, demonstrated the ability of an ANN to identify the severity of aorto-iliac disease from the CFA waveform. Although the ANN outperformed standard univariate methods and visual classification of the data, it would appear that further work is needed to increase the accuracy of the ANN to a clinically acceptable standard.

Adult↗
PubMed2002

Variety identification of wheat using mass spectrometry with neural networks and the influence of mass spectra processing prior to neural network analysis.

The performance of matrix-assisted laser desorption/ionisation time-of-flight mass spectrometry with neural networks in wheat variety classification is further evaluated.1 Two principal issues were studied: (a) the number of varieties that could be classified correctly; and (b) various means of pre-processing mass spectrometric data. The number of wheat varieties tested was increased from 10 to 30. The main pre-processing method investigated was based on Gaussian smoothing of the spectra, but other methods based on normalisation procedures and multiplicative scatter correction of data were also used. With the final method, it was possible to classify 30 wheat varieties with 87% correctly classified mass spectra and a correlation coefficient of 0.90.

Journal Article↗
PubMed2004

Novel naphthylstyryl-pyridium potentiometric dyes offer advantages for neural network analysis.

The submucous plexus of the guinea pig intestine is a quasi-two-dimensional mammalian neural network that is particularly amenable to study using multiple site optical recording of transmembrane voltage (MSORTV) [Biol. Bull. 183 (1992) 344; J. Neurosci. 19 (1999) 3073]. For several years the potentiometric dye of choice for monitoring the electrical activity of its individual neurons has been di-8-ANEPPS [Neuron 9 (1992) 393], a naphthylstyryl-pyridinium dye with a propylsulfonate headgroup that provides relatively large fluorescence changes during action potentials and synaptic potentials. Limitations to the use of this dye, however, have been its phototoxicity and its low water solubility which requires the presence of DMSO and Pluronic F-127 in the staining solution. In searching for less toxic and more soluble dyes exhibiting larger fluorescence signals, we first tried the dienylstyryl-pyridinium dye RH795 [J. Neurosci. 14 (1994) 2545] which is highly soluble in water. This dye yielded relatively large signals, but it was internalized quickly by the submucosal neurons resulting in rapid degradation of the signal-to-noise ratio. We decided to synthesize a series of naphthylstyryl-pyridinium dyes (di-n-ANEPPDHQ) having the same chromophore as di-8-ANEPPS and the quaternary ammonium headgroup (DHQ) of RH795 (resulting in two positive charges versus the neutral propylsulfonate-ring nitrogen combination), and we tested the di-methyl (JPW3039), di-ethyl (JPW2081), di-propyl (JPW3031), di-butyl (JPW5029), and di-octyl (JPW5037) analogues, all of them soluble in ethanol. We found that the di-propyl (di-3-ANEPPDHQ) and the di-butyl (di-4-ANEPPDHQ) forms yielded the best combination of signal-to-noise ratio, moderate phototoxicity and absence of dye internalization.

Animals↗
PubMed2000

Neural network analysis of clinicopathological and molecular markers in bladder cancer.

PURPOSE: To evaluate retrospectively the ability of an artificial neural network (ANN) to predict bladder cancer recurrence within 6 months of diagnosis and stage progression in patients with Ta/T1 bladder cancer, and 12-month cancer-specific survival in patients with T2-T4 bladder cancer. MATERIALS AND METHODS: Data were analyzed using a NeuralWorks Professional II/Plus software package. The input neural data consisted of clinicopathological and molecular characteristics. Distinct patient groups were used for the prediction of stage progression and tumor recurrence in Ta/T1 bladder cancers, and 12-month cancer-specific survival for patients with T2-T4 tumors. ANN predictions were compared with those of four consultant urologists. RESULTS: The accuracy of the neural network in predicting stage progression and recurrence within 6 months for Ta/T1 tumors and 12-month cancer-specific survival for T2-T4 cancers was 80%, 75% and 82% respectively; with corresponding figures for clinicians being 74%, 79% and 65%. On restricting the validation subset to patients with T1G3 tumors in relation to stage progression, the sensitivity of the ANN analysis increased to 100% with a specificity of 78% and an overall accuracy of 82%. The performance of the ANN in predicting stage progression in T1G3 tumors was significantly higher than that of clinicians (p = 0.25 for the ANN and p = 0.008 for clinicians, McNemar test). CONCLUSIONS: Data analysis using an ANN has been shown to be a useful adjunct in predicting outcomes in patients with bladder cancer and out-performs clinicians' predictions of stage progression in the high risk group of patients with T1G3 disease.

Biomarkers, Tumor↗
PubMed2001

Neuronal network analysis based on arrival times of active-sleep specific inhibitory postsynaptic potentials in spinal cord motoneurons of the cat.

The neuronal network responsible for motoneuron inhibition and loss of muscle tone during active (REM) sleep can be activated by the injection of the cholinergic agonist carbachol into a circumscribed region of the brainstem reticular formation. In the present report, we studied the arrival times of inhibitory postsynaptic potentials (IPSPs) observed in intracellular recordings from cat spinal cord motoneurons. These recordings were obtained during episodes of motor inhibition induced by carbachol or during motor inhibition associated with naturally occurring active sleep. When the observed IPSP arrival times were analyzed as a superposition of renewal processes occurring in a pool of pre-motor inhibitory interneurons, it was possible to estimate the following parameters: (1) the number of independent sources of the IPSPs; (2) the rate at which each source was bombarded with excitatory postsynaptic potentials (EPSPs); and (3) the number of EPSPs required to bring each source to threshold. From the data based upon the preceding parameters and the unusually large amplitudes of the active sleep-specific IPSPs, we suggest that each source is a cluster of synchronously discharging pre-motor inhibitory interneurons. The analysis of IPSP arrival times as a superposition of renewal processes, therefore, provides quantitative information regarding neuronal activity that is as far as two synapses upstream from the site of the recording electrode. Consequently, we suggest that a study of the temporal evolution of these parameters could provide a basis for dynamic analyses of this neuronal network and, in the future, for other neuronal networks as well.

Animals↗
PubMedDate not supplied

Neural network analysis of breast cancer from MRI findings.

PURPOSE: To evaluate how much the experience of radiologists affects the performance of an artificial neural network (ANN) trained by two highly experienced radiologists. MATERIALS AND METHODS: Before biopsy two experienced radiologists reviewed the MR images of 100 adult patients with suspicious breast lesions and evaluated their findings based on six features. This database was then used to train a three-layered feed-forward neural network. The network's generalizing ability was then tested to predict the outcome of biopsy in 56 new patients' records which were extracted by 10 participating radiologists. The MRI findings of each reader were presented to the ANN to evaluate the effect of various levels of experience on the output of the ANN. The performance of the ANN was then compared with that of attendant physicians in terms of sensitivity, specificity, and accuracy as well as ROC analysis. RESULTS: The best ANN outcome offered a correct diagnosis in 40 of 41 of the patients with malignant breast cancer and 10 of 15 with benign entity presented in the testing set. The output of the trained ANN outperformed the attendant radiologists with low levels of experience and showed comparable performance with radiologists with higher levels of experience. CONCLUSIONS: The ANN is able to work as a backup system to assist radiologists in the diagnosis of breast cancer.

Adolescent↗
PubMed1998

Neural network analysis of combined conventional and experimental prognostic markers in prostate cancer: a pilot study.

Prostate cancer is the second most common malignancy in men in the UK. The disease is unpredictable in its behaviour and, at present, no single investigative method allows clinicians to differentiate between tumours that will progress and those that will remain quiescent. There is an increasing need for novel means to predict prognosis and outcome of the disease. The aim of this study was to assess the value of artificial neural networks in predicting outcome in prostate cancer in comparison with statistical methods, using a combination of conventional and experimental biological markers. Forty-one patients with different stages and grades of prostate cancer undergoing a variety of treatments were analysed. Artificial neural networks were used as follows: eight input neurons consisting of six conventional factors (age, stage, bone scan findings, grade, serum PSA, treatment) and two experimental markers (immunostaining for bcl-2 and p53, which are both apoptosis-regulating genes). Twenty-one patients were used for training and 20 for testing. A total of 80% of the patients were correctly classified regarding outcome using the combination of factors. When both bcl-2 and p53 immunoreactivity were excluded from the analysis, correct prediction of the outcome was achieved in only 60% of the patients (P = 0.0032). This study was able to demonstrate the value of artificial neural networks in the analysis of prognostic markers in prostate cancer. In addition, the potential for using this technology to evaluate novel markers is highlighted. Further large-scale analyses are required to incorporate this methodology into routine clinical practice.

Aged↗
PubMed2005

Metabolic-flux and network analysis in fourteen hemiascomycetous yeasts.

In a quantitative comparative study, we elucidated the glucose metabolism in fourteen hemiascomycetous yeasts from the Genolevures project. The metabolic networks of these different species were first established by (13)C-labeling data and the inventory of the genomes. This information was subsequently used for metabolic-flux ratio analysis to quantify the intracellular carbon flux distributions in these yeast species. Firstly, we found that compartmentation of amino acid biosynthesis in most species was identical to that in Saccharomyces cerevisiae. Exceptions were the mitochondrial origin of aspartate biosynthesis in Yarrowia lipolytica and the cytosolic origin of alanine biosynthesis in S. kluyveri. Secondly, the control of flux through the TCA cycle was inversely correlated with the ethanol production rate, with S. cerevisiae being the yeast with the highest ethanol production capacity. The classification between respiratory and respiro-fermentative metabolism, however, was not qualitatively exclusive but quantitatively gradual. Thirdly, the flux through the pentose phosphate (PP) pathway was correlated to the yield of biomass, suggesting a balanced production and consumption of NADPH. Generally, this implies the lack of active transhydrogenase-like activities in hemiascomycetous yeasts under the tested growth condition, with Pichia angusta as the sole exception. In the latter case, about 40% of the NADPH was produced in the PP pathway in excess of the requirements for biomass production, which strongly suggests the operation of a yet unidentified mechanism for NADPH reoxidation in this species. In most yeasts, the PP pathway activity appears to be driven exclusively by the demand for NADPH.

Ascomycota↗
PubMed2002

Predicting Type 2 diabetes using an electronic nose-based artificial neural network analysis.

Diabetes is a major health problem in both industrial and developing countries, and its incidence is rising. Although detection of diabetes is improving, about half of the patients with Type 2 diabetes are undiagnosed and the delay from disease onset to diagnosis may exceed 10 yr. Thus, earlier detection of Type 2 diabetes and treatment of hyperglycaemia and related metabolic abnormalities is of vital importance. The objectives of the present study were to examine urine samples from Type 2 diabetic patients and healthy volunteers using the electronic nose technology and to evaluate possible application of data classification methods such as self-learning artificial neural networks (ANN) and logistic regression (LR) in comparison with principal components analysis (PCA). Urine samples from Type 2 diabetic patients and healthy controls were processed randomly using a simple 8-sensors electronic nose and individual electronic nose patterns were qualitatively classified using the "Approximation and Classification of Medical Data" (ACMD) network based on 2 output neurons, binary LR analysis and PCA. Distinct classes were found for Type 2 diabetic subjects and controls using PCA, which had a 96.0% successful classification percentage mean while qualitative ANN analysis and LR analysis had successful classification percentages of 92.0% and 88.0%, respectively. Therefore, the ACMD network is suitable for classifying medical and clinical data.

Aged↗
PubMed2001

Neural network analysis of the prediction of cancer recurrence following debulking laparotomy and chemotherapy in stages III and IV ovarian cancer.

An artificial neural network (ANN) has been developed to predict the presence or absence of cancer following debulking laparotomy and chemotherapy in patients with stages III and IV ovarian cancer. The presence or absence of a residual gross tumor or microscopic disease was determined by a second-look laparotomy. The ANN was trained and tested using detailed operative findings and related surgical procedures associated with the debulking surgery. The ANN predictive results were compared with linear and logistic regression. The ANN significantly outperformed both logistic and linear regression analyses, but additional cases are needed to validate the network.

Female↗
PubMed2006

Prediction of the main cortical areas and connections involved in the tactile function of the visual cortex by network analysis.

We explored the cortical pathways from the primary somatosensory cortex to the primary visual cortex (V1) by analysing connectional data in the macaque monkey using graph-theoretical tools. Cluster analysis revealed the close relationship of the dorsal visual stream and the sensorimotor cortex. It was shown that prefrontal area 46 and parietal areas VIP and 7a occupy a central position between the different clusters in the visuo-tactile network. Among these structures all the shortest paths from primary somatosensory cortex (3a, 1 and 2) to V1 pass through VIP and then reach V1 via MT, V3 and PO. Comparison of the input and output fields suggested a larger specificity for the 3a/1-VIP-MT/V3-V1 pathways among the alternative routes. A reinforcement learning algorithm was used to evaluate the importance of the aforementioned pathways. The results suggest a higher role for V3 in relaying more direct sensorimotor information to V1. Analysing cliques, which identify areas with the strongest coupling in the network, supported the role of VIP, MT and V3 in visuo-tactile integration. These findings indicate that areas 3a, 1, VIP, MT and V3 play a major role in shaping the tactile information reaching V1 in both sighted and blind subjects. Our observations greatly support the findings of the experimental studies and provide a deeper insight into the network architecture underlying visuo-tactile integration in the primate cerebral cortex.

Algorithms↗