Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Neural network”

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 1,801 records · Page 100Linked to original sources
PubMed2001

A sequential neural network model for diabetes prediction.

This paper presents a neural network (NN) model to evaluate an existing Health Risk Appraisal (HRA) for diabetes prediction over 3 years (1996-1998) based on a simulated learning algorithm on individual prognostic process, using the repeatedly measured HRAs of 6142 participants. The approach uses a sequential multi-layered perceptron (SMLP) with backpropagation learning, and an explicit model of time-varying inputs along with the sequentially obtained prediction probability, which was obtained by embedding a multivariate logistic function for consecutive years. The study captures the time-sensitive feature of associating risk factors as predictors to the occurrence of diabetes in the corresponding period. This approach outperforms the baseline classification and regression models in terms of gains (average profit: 0.18) and sensitivity (86.04%) for a test data. The result enables a time-sensitive disease prevention and management program as a prospective effort.

Diabetes Mellitus↗
PubMed1994

Classification of impulse radar waveforms using neural networks.

In this paper, it is demonstrated that multilayer neural networks, trained with the backpropagation algorithm and radial basis functions, can classify impulse radar waveforms from three different asphalt-covered bridge decks, each with its own structure. It might be thought that the thickness of asphalt and the depth of concrete over the reinforcing bars would be nearly constant for any one bridge deck; however in practice this is not the case. There are often significant changes in the thickness of the asphalt and the cover over reinforcement. Furthermore, a certain amount of damage to the concrete caused by severe winter climate often produces a random variation in the reflected waveforms obtained from different locations. These factors lead to a significant number of combinations of waveforms that can be obtained from any given structural type of deck. The classification accuracies achieved ranged between 89.9% and 100%. The accuracies achieved after using principal components analysis to reduce the dimensionality of the input data ranged between 95.6% and 100%.

Algorithms↗
PubMedDate not supplied

A molecular approach to retinal neural networks.

Our understanding of the computations carried out by neural networks in the central nervous system is limited by our incomplete knowledge of the diversity of cell types and the multiplicity of their functions. In the retina, over fifty cell types encode the spatial, temporal, and chromatic parameters of the incoming light stimuli to generate the messages of action potentials that travel to the brain along the fibers of the optic nerve. We have combined molecular techniques with microscopy and electrophysiology to study a rare cell type in the retina, the dopaminergic amacrine (interplexiform cells). These neurons were labeled in transgenic mice with human placental alkaline phosphatase so that they could be identified in vitro for patch-clamping and analysis of gene expression by single-cell RT-PCR and cDNA array profiling. We have thus demonstrated that the retinal dopaminergic neurons spontaneously generate action potentials in a rhythmic fashion, release dopamine over their entire surface, establish GABAergic synapses and contain proteins whose existence went undetected with more conventional techniques.

Amacrine Cells↗
PubMed2006

Tracking the states of a nonlinear and nonstationary system in the weight-space of artificial neural networks.

We propose a novel interpretation and usage of Neural Network (NN) in modeling physiological signals, which are allowed to be nonlinear and/or nonstationary. The method consists of training a NN for the k-step prediction of a physiological signal, and then examining the connection-weight-space (CWS) of the NN to extract information about the signal generator mechanism. We define a novel feature, Normalized Vector Separation (gamma(ij)), to measure the separation of two arbitrary states "i" and "j" in the CWS and use it to track the state changes of the generating system. The performance of the method is examined via synthetic signals and clinical EEG. Synthetic data indicates that gamma(ij) can track the system down to a SNR of 3.5 dB. Clinical data obtained from three patients undergoing carotid endarterectomy of the brain showed that EEG could be modeled (within a root-means-squared-error of 0.01) by the proposed method, and the blood perfusion state of the brain could be monitored via gamma(ij), with small NNs having no more than 21 connection weight altogether.

Brain Ischemia↗
PubMed2001

Modelling and prediction for chaotic fir laser attractor using rational function neural network.

Many real-world systems such as irregular ECG signal, volatility of currency exchange rate and heated fluid reaction exhibit highly complex nonlinear characteristic known as chaos. These chaotic systems cannot be retreated satisfactorily using linear system theory due to its high dimensionality and irregularity. This research focuses on prediction and modelling of chaotic FIR (Far InfraRed) laser system for which the underlying equations are not given. This paper proposed a method for prediction and modelling a chaotic FIR laser time series using rational function neural network. Three network architectures, TDNN (Time Delayed Neural Network), RBF (radial basis function) network and the RF (rational function) network, are also presented. Comparisons between these networks performance show the improvements introduced by the RF network in terms of a decrement in network complexity and better ability of predictability.

Infrared Rays↗
PubMed2005

Optimisation of high performance liquid chromatography separation of neuroprotective peptides. Fractional experimental designs combined with artificial neural networks.

The study of experimental design conjunction with artificial neural networks for optimisation of isocratic ion-pair reverse phase HPLC separation of neuroprotective peptides is reported. Different types of experimental designs (full-factorial, fractional) were studied as suitable input and output data sources for ANN training and examined on mixtures of humanin derivatives. The independent input variables were: composition of mobile phase, including its pH, and column temperature. In case of a simple mixture of two peptides, the retention time of the most retentive component and resolution were used as the dependent variables (outputs). In case of a complex mixture with unknown number of components, number of peaks, sum of resolutions and retention time of ultimate peak were considered as output variables. Fractional factorial experimental design has been proved to produce sufficient input data for ANN approximation and thus further allowed decreasing the number of experiments necessary for optimisation. After the optimal separation conditions were found, fractions with peptides were collected and their analysis using off-line matrix assisted laser desorption/ionisation time of flight mass spectrometry (MALDI-TOF-MS) was performed.

Amino Acid Substitution↗
PubMed2002

Evaluation of an artificial neural network rainfall disaggregation model.

Previous research produced an artificial neural network (ANN) temporal rainfall disaggregation model. After proper training the model can disaggregate hourly rainfall records into sub-hourly time increments. In this paper we present results from continued evaluations of the performance of the ANN model specifically examining how the errors in the disaggregated rainfall hyetograph translate to errors in the prediction of the runoff hydrograph. Using a rainfall-runoff model of a hypothetical watershed we compare the runoff hydrographs produced by the ANN-predicted 15-minute increment rainfall pattern to runoff hydrographs produced by (1) the observed 15-minute increment rainfall pattern, (2) the observed hourly-increment rainfall pattern, and (3) the 15-minute increment rainfall pattern produced by a disaggregation model based on geometric similarity. For 98 test storms the peak discharges produced by the ANN model rainfall pattern had a median under-prediction of 16.6%. This relative error was less than the median under-prediction in peak discharge when using the observed 15-minute rainfall patterns aggregated to hourly increments (40.8%), and when using rainfall patterns produced by the geometric similarity rainfall disaggregation model (21.9%).

Environmental Monitoring↗
PubMedDate not supplied

A neural network model for predicting aquifer water level elevations.

Artificial neural networks (ANNs) were developed for accurately predicting potentiometric surface elevations (monitoring well water level elevations) in a semiconfined glacial sand and gravel aquifer under variable state, pumping extraction, and climate conditions. ANNs "learn" the system behavior of interest by processing representative data patterns through a mathematical structure analogous to the human brain. In this study, the ANNs used the initial water level measurements, production well extractions, and climate conditions to predict the final water level elevations 30 d into the future at two monitoring wells. A sensitivity analysis was conducted with the ANNs that quantified the importance of the various input predictor variables on final water level elevations. Unlike traditional physical-based models, ANNs do not require explicit characterization of the physical system and related physical data. Accordingly, ANN predictions were made on the basis of more easily quantifiable, measured variables, rather than physical model input parameters and conditions. This study demonstrates that ANNs can provide both excellent prediction capability and valuable sensitivity analyses, which can result in more appropriate ground water management strategies.

Climate↗
PubMed2004

Database search post-processing by neural network: Advanced facilities for identification of components in protein mixtures using mass spectrometric peptide mapping.

Database search post-processing by neural network was employed in peptide mapping experiments. The database search was performed using both the known algorithms and score functions, such as Bayesian, MOWSE, Z-score, correlations between calculated and actual peptide length fractional abundance, and, in addition, the probability of protein digest pattern in peptide fingerprint, all embedded in locally developed program. The new signal-processing algorithm based on neural network improves signal-noise separation and is acceptable for automatic protein identification in mixtures. Its power was tested on Helicobacter pylori protein inventory after preceding protein separation by sodium dodecyl sulfate-polyacrylamide gel electrophoresis (SDS-PAGE). Increase in protein identification success rate was observed, and about 100 proteins were identified with no need of human participation in database search estimation.

Algorithms↗
PubMed2002

[Blood gases values forecasting by artificial neural network in prematurely born infants with respiratory distress].

Artificial Neural Networks (ANN) are modern tools for data analysis. They can compete with commonly used statistical methods. Till the date they were not used for modeling continuous parameters in medicine. The aim of this paper is to assess accuracy of ANN in forecasting blood gases values in preterm infants with respiratory distress. The study was conducted with the use of the data from Neonatal Information System (NIS) describing first 30 days of the hospital stay of 19 newborns with birthweight < or = 1500 g admitted to the unit before second day of life in 1997. Separate ANN was created for prognosis of 4 parameters of arterial blood gases (pH, pCO2, pO2, HCO3) and oxygenation index (pO2/FiO2) for 1 hour in advance. For each forecasted parameter input set of parameters was established. The ANN was taught with back propagation algorithm using data of 18 patients, the accuracy of prognosis was tested on the data of the remaining patient. This procedure was repeated 19 times. The error of prognosis was assessed in comparison to predefined curves of the maximal error. The accuracy of achieved prognoses was respectively for pH, pCO2, pO2, HCO3, pO2/FiO2 98.9, 99.7, 97.1, 98.3, 95%.

Blood Gas Analysis↗
PubMed2007

Identification of human term and preterm labor using artificial neural networks on uterine electromyography data.

OBJECTIVE: To use artificial neural networks (ANNs) on uterine electromyography (EMG) data to classify term/preterm labor/non-labor pregnant patients. MATERIALS AND METHODS: A total of 134 term and 51 preterm women (all ultimately delivered spontaneously) were included. Uterine EMG was measured trans-abdominally using surface electrodes. "Bursts" of elevated uterine EMG, corresponding to uterine contractions, were quantified by finding the means and/or standard deviations of the power spectrum (PS) peak frequency, burst duration, number of bursts per unit time, and total burst activity. Measurement-to-delivery (MTD) time was noted for each patient. Term and preterm patient groups were sub-divided, resulting in the following categories: [term-laboring (TL): n = 75; preterm-laboring (PTL): n = 13] and [term-non-laboring (TN): n = 59; preterm-non-laboring (PTN): n = 38], with labor assessed using clinical determinations. ANN was then used on the calculated uterine EMG data to algorithmically and objectively classify patients into labor and non-labor. The percent of correctly categorized patients was found. Comparison between ANN-sorted groups was then performed using Student's t test (with p < 0.05 significant). RESULTS: In total, 59/75 (79%) of TL patients, 12/13 (92%) of PTL patients, 51/59 (86%) of TN patients, and 27/38 (71%) of PTN patients were correctly classified. CONCLUSION: ANNs, used with uterine EMG data, can effectively classify term/preterm labor/non-labor patients.

Adolescent↗
PubMed2001

Discrimination of anesthetic states using mid-latency auditory evoked potential and artificial neural networks.

This study was undertaken to determine whether artificial neural network (ANN) processing of mid-latency auditory evoked potentials (MLAEPs) can identify different anesthetic states during propofol anesthesia, and to determine those parameters that are most useful in the identification process. Twenty-one patients undergoing elective abdominal surgery were studied. To maintain general anesthesia, the patients received propofol (3-5 mgkg(-1) h(-1) intravenously). Epidural analgesia at the level of T4-5 blocked painful stimuli. MLAEP was recorded continuously with patients awake, during induction, during maintenance of general anesthesia, and during emergence until the patients were recovered from anesthesia. Latencies of the 5 MLAEP peaks and three peak to peak amplitudes were measured, along with hemodynamic parameters (heart rate, systolic, and diastolic arterial blood pressure). Four-layer ANNs were used to model the relationship between the parameters of the MLAEP and the four different states (awake, adequate anesthesia, during/before intraoperative movement, and emergence from anesthesia). The best identification accuracy was obtained using only the five latencies. The combination of five latencies and three amplitudes did not improve the identification accuracy. Use of the only the three hemodynamic parameters produced a much poorer identification. This study suggests that the MLAEP has useful information for identifying different anesthetic states, especially in its latencies. A nonlinear discrimination approach, such as the ANN, can effectively capture the relation between the MLAEP patterns and the different states of anesthesia.

Anesthesia↗
PubMed2004

Counter-propagation artificial neural network as a tool for the independent variable selection: structure-mutagenicity study on aromatic amines.

The counter-propagation artificial neural network (CP ANN) technique was applied for the independent variable selection and for structure-mutagenic potency modeling on a set of 95 aromatic and heteroaromatic amines with biological activity investigated experimentally by an in vitro assay. The molecular structures were represented by 275 independent variables classified as topostructural, topochemical, geometrical and quantum-chemical descriptors. As a result of the neural network modeling, the following descriptors were found to be the most important for structure-activity relationship: 5 chi -path connectivity index of order h = 5, 3chibC-bond cluster connectivity index of order h = 3, J(B)-Balaban's J index based on bond types, SHSNH2-electrotopological state index values for atoms, phia-flexibility index (kappa p1 x kappa p2/nvx), IC0-mean information content or complexity of a graph based on the 0 order neighborhood of vertices in a hydrogen-filled graph and ELUMO. The leave one out (LOO) method was used in order to test and select the models for mutagenicity prediction. The statistical parameters for the 7-descriptors model are R(Model) = 0.96 and Rcv = 0.85, respectively. In the next step, the number of variables was reduced and the 4-descriptors model was found (R(Model) = 0.95 and Rcv = 0.85) and classified as the best one.

Algorithms↗
PubMed1999

Prediction of tacrolimus blood levels by using the neural network with genetic algorithm in liver transplantation patients.

The neural network (NN) is a technique using an artificial intelligent concept in predicting outcomes by using various input variables. Tacrolimus pharmacokinetics has wide inter- and intra-subject variability and it is often difficult to predict its blood concentrations by dose alone. The objectives of this study are to select the clinically significant variables and to predict the blood concentration of tacrolimus in liver transplant patients by NN combined with genetic algorithm (GA). A total of thirty-two adult liver transplant patients from the University of Iowa Hospitals and Clinics were selected and the patients' data were retrospectively collected. These patient were randomly assigned into two groups: either the training group (n = 10), or testing group (n = 22). A back propagation (BP) NN was developed which contained two hidden layers. A dynamic BP NN based on the time series concept was trained by using the current and previous data sets to predict the trough levels of tacrolimus. The mean of the NN prediction for tacrolimus blood levels was not significantly different from the observed value by a paired t-test comparison (12.05+/-2.67 ng/ml vs. 12.14+/-2.64 ng/ml, p = 0.80). The average difference of the testing sets between the observed and predicted levels was 1.74 ng/ml with a range from 0.08 to 5.26 ng/ml which is clinically acceptable range. Thirty-seven out of 44 data sets (84%) in the testing group were within 3.0 ng/ml of the observed values. This study demonstrated that tacrolimus blood concentrations are precisely predictable in liver transplant patients using patients variables by NN.

Adult↗
PubMed1992

Computer-assisted image interpretation: use of a neural network to differentiate tubular carcinoma from sclerosing adenosis.

Measurement of nuclear and glandular size and shape features was carried out on 18 cases of sclerosing adenosis and 18 cases of tubular carcinoma. Modified Bonferroni analysis showed that glandular surface density and the coefficient of variation of luminal form factor were significant in discriminating between these two lesions. These two histologic features, together with the diagnosis, were used to train a neural network implementing a backpropagation algorithm. Following training, the network correctly classified 33 of the 36 cases in the training set (92%). Furthermore, the network correctly classified 19 of 19 cases in a test set consisting of cases that were not used to train the network. These results suggest that neural networks may be useful to assist in the differential diagnosis of histologically similar lesions.

Adenocarcinoma↗
PubMed1997

Neural networks as a prognostic tool for patients with non-small cell carcinoma of the lung.

Patients with non-small cell carcinoma of the lung (NSCLC) have a poor prognosis (64 and 41% survival rates in Stages I and II). It is currently not possible to predict which patients with Stage I or II NSCLC will survive the disease. Sixty-seven patients with NSCLC, including 49 patients with Stage I NSCLC and 18 with Stage II disease (11 with squamous cell carcinomas, 35 with adenocarcinomas, and 21 with large cell carcinomas) were treated with lobectomy and followed for a minimum of 5 years. The tumors were studied with DNA flow cytometry and quantitative immunocytochemical studies for proliferation cell nuclear antigen, p53 protein, and MIB-1. The data were analyzed with backpropagation neural networks, univariate analysis of variance, the Kaplan-Meier survival method, and Cox proportional hazards model. The dependent variables were "free of disease" and "recurrence or dead from disease." Twenty neural network models were trained, using all cases but one, after 1883 to 2000 training cycles. At 5 years, 30 patients were free of disease and 37 were dead or had recurrence. Proliferating cell nuclear antigen was the only statistically significant prognostic factor by univariate analysis of variance and Cox proportional hazards analysis. The S phase was statistically significant by univariate analysis of variance (P <.05). All of the 20 models classified the test cases correctly. Study with backpropagation neural networks using multiple prognostic features from patients with NSCLC suggests that this technology might be useful for prediction of survival. This preliminary study must be validated with data from a larger group of patients with NSCLC before its clinical adequacy is established.

Adenocarcinoma↗
PubMed2005

Integrating regression formulas and kernel functions into locally adaptive knowledge-based neural networks: a case study on renal function evaluation.

OBJECTIVE: In many medical areas, there exist different regression formulas to predict/evaluate a medical outcome on the same problem, each of them being efficient only in a particular sub-space of the problem space. The paper aims at the development of a generic, incremental learning model that includes all available regression formulas for a particular prediction problem to define local areas of the problem space with their best performing formula along with useful explanation rules. Another objective of the paper is to develop a specific model for renal function evaluation using nine existing formulas. METHODS AND MATERIALS: We have used a connectionist neuro-fuzzy approach and have developed a knowledge-based neural network model (KBNN) which incorporates and adapts incrementally several existing regression formulas and kernel functions. The model incorporates different non-linear regression functions as neurons in its hidden layer and adapts these functions through incremental learning from data in particular local areas of the space. More specifically, each hidden neural node has a pair of functions associated with it--one regression formula, that represents existing knowledge and one Gaussian kernel function, that defines the sub-space of the whole problem space, in which the formula is locally adapted to new data. All these functions are aggregated and changed through incremental learning. The proposed KBNN model is illustrated using a medical dataset of observed patient glomerular filtration rate (GFR) measurements for renal function evaluation. In this case study, the regression function for each cluster is selected by the model from nine formulas commonly used by medical practitioners to predict GFR. 441 GFR data vectors from 141 patients taken from 12 sites in Australia and New Zealand have been used as a case study experimental data set. RESULTS: The proposed GFR prediction model, based on the proposed generic KBNN model, outperforms at least by 10% accuracy any of the individual regression formulas or a standard neural network model. Furthermore, we have derived locally adapted regression formulas to perform best on local clusters of data along with useful explanatory rules. CONCLUSION: The proposed KBNN model manifests better accuracy then existing regression formulas or neural network models for renal function evaluation and extracts modified formulas that perform well in local areas of the problem space.

Algorithms↗

Refine your search to explore more results.