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.

SourceResearch connectionFrom yearThrough year

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

At least 991 records · Page 55Linked to original sources

PubMed1998

Review of neural network applications in sleep research.

To find a better automated sleep-wake staging system for human analyses of numerous polygraphic records is an interesting challenge in sleep research. Over the last few decades, many automated systems have been developed but none are universally applicable. Improvements in computer technology coupled with artificial neural networks based systems (connectionist models) are responsible for new data processing approaches. Despite extensive use of connectionist models in biological data processing, in the past, the field of sleep research appeared to have neglected this approach. Only a few sleep-wake staging systems based on neural network technology have been developed. This paper reviews the current use of artificial neural networks in sleep research. Following a brief presentation of neural network technology, each of the existing system is described and attention drawn to the heterogeneity of the different processing approaches in sleep research. The high performances observed with systems based on neural networks highlight the need to integrate these tools into the field of sleep research.

Animals↗

PubMedDate not supplied

Using a neural network to diagnose the hypertrophic portions of hypertrophic cardiomyopathy.

We studied the ability of a neural network to identify the hypertrophic cardiac regions in hypertrophic cardiomyopathy, with the network using electrocardiographic (ECG) information alone. Computer-based electrocardiography remains a fundamental diagnostic method for analysis of cardiac contour and rhythm. Almost all patients with hypertrophic cardiomyopathy have some abnormal findings on electrocardiography, but it is very difficult, even for an experienced cardiologist, to identify the hypertrophic regions on the basis of electrocardiography alone. Since neural networks are known to be better at pattern recognition than humans are, we tried using a neural network trained with ECG information to identify the hypertrophic regions in hypertrophic cardiomyopathy.

Algorithms↗

PubMed2000

Risk stratification in heart failure using artificial neural networks.

Accurate risk stratification of heart failure patients is critical to improve management and outcomes. Heart failure is a complex multisystem disease in which several predictors are categorical. Neural network models have successfully been applied to several medical classification problems. Using a simple neural network, we assessed one-year prognosis in 132 patients, consecutively admitted with heart failure, by classifying them in 3 groups: death, readmission and one-year event-free survival. Given the small number of cases, the neural network model was trained using a resampling method. We identified relevant predictors using the Automatic Relevance Determination (ARD) method, and estimated their mean effect on the 3 different outcomes. Only 9 individuals were misclassified. Neural networks have the potential to be a useful tool for making prognosis in the domain of heart failure.

Disease-Free Survival↗

PubMed2006

Temporal neural networks for downscaling climate variability and extremes.

This paper presents an application of temporal neural networks for downscaling global climate models (GCMs) output. Because of computational constraints, GCMs are usually run at coarse grid resolution (in the order of 100s of kilometres) and as a result they are inherently unable to present local sub-grid scale features and dynamics. Consequently, outputs from these models cannot be used directly in many climate change impact studies. This research explored the issues of 'downscaling' the outputs of GCMs using a temporal neural network (TNN) approach. The method is proposed for downscaling daily precipitation and temperature series for a region in northern Quebec, Canada. The downscaling models are developed and validated using large-scale predictor variables derived from the National Center for Environmental Prediction (NCEP) reanalysis data set. The performance of the temporal neural network downscaling model is also compared to a regression-based statistical downscaling model with emphasis on their ability in reproducing the observed climate variability and extremes. The downscaling results for the base period (1961-2000) suggest that the TNN is an efficient method for downscaling both daily precipitation as well as daily maximum and minimum temperature series. Furthermore, the different model test results indicate that the TNN model mostly outperforms the statistical models for the downscaling of daily precipitation extremes and variability.

Climate↗

PubMed1998

The use of a neural network to detect upper airway obstruction caused by goiter.

Goiter is a common condition and can cause upper airway obstruction (UAO), which may be difficult to detect. We have studied maximal expiratory and inspiratory flow volume loops using a neural network to see if this offers a better way to identify patients with UAO. The flow-volume loops from 155 patients with goiter were assessed by a human expert and sorted into those with and without UAO. The reliability of this assessment was judged by using two observers who repeated the sorting 8 wk apart. A set of 46 patients with loops suggesting UAO and a set of 51 patients with normal flow loops were taken from these 155, and the loops from a further 50 subjects with airflow limitation caused by chronic obstructive pulmonary disease were used for training and testing the neural network. Novel and standard indices were derived from the loops and used by the neural network. The kappa score for agreement between each of the observers and the original classification were 0.5 and 0.46, respectively, with the agreement between the observers at each reading of 0.58 and 0.68. The neural network found that a combination of four novel scores for flatness of the expiratory loop, the moment ratio, and the FEV1/PEF ratio was best at identifying UAO with a kappa score of 0.81, a sensitivity of 88%, specificity of 94% and an accuracy of 92%. We conclude that a neural network using only six indices taken from the expiratory limb of a flow-volume loop was better than human experts at identifying flow loops with UAO.

Adult↗

PubMedDate not supplied

Predicting physical-chemical properties of compounds from molecular structures by recursive neural networks.

In this paper, we report on the potential of a recently developed neural network for structures applied to the prediction of physical chemical properties of compounds. The proposed recursive neural network (RecNN) model is able to directly take as input a structured representation of the molecule and to model a direct and adaptive relationship between the molecular structure and target property. Therefore, it combines in a learning system the flexibility and general advantages of a neural network model with the representational power of a structured domain. As a result, a completely new approach to quantitative structure-activity relationship/quantitative structure-property relationship (QSPR/QSAR) analysis is obtained. An original representation of the molecular structures has been developed accounting for both the occurrence of specific atoms/groups and the topological relationships among them. Gibbs free energy of solvation in water, Delta(solv)G degrees , has been chosen as a benchmark for the model. The different approaches proposed in the literature for the prediction of this property have been reconsidered from a general perspective. The advantages of RecNN as a suitable tool for the automatization of fundamental parts of the QSPR/QSAR analysis have been highlighted. The RecNN model has been applied to the analysis of the Delta(solv)G degrees in water of 138 monofunctional acyclic organic compounds and tested on an external data set of 33 compounds. As a result of the statistical analysis, we obtained, for the predictive accuracy estimated on the test set, correlation coefficient R = 0.9985, standard deviation S = 0.68 kJ mol(-1), and mean absolute error MAE = 0.46 kJ mol(-1). The inherent ability of RecNN to abstract chemical knowledge through the adaptive learning process has been investigated by principal components analysis of the internal representations computed by the network. It has been found that the model recognizes the chemical compounds on the basis of a nontrivial combination of their chemical structure and target property.

Journal Article↗

PubMed1999

Quantifying complex patterns of bioacoustic variation: use of a neural network to compare killer whale (Orcinus orca) dialects.

A quantitative measure of acoustic similarity is crucial to any study comparing vocalizations of different species, social groups, or individuals. The goal of this study was to develop a method of extracting frequency contours from recordings of pulsed vocalizations and to test a nonlinear index of acoustic similarity based on the error of an artificial neural network at classifying them. Since the performance of neural networks depends on the amount of consistent variation in the training data, this technique can be used to assess such variation from samples of acoustic signals. The frequency contour extraction and the neural network index were tested on samples of one call type shared by nine social groups of killer whales. For comparison, call similarity was judged by three human subjects in pairwise classification tasks. The results showed a significant correlation between the neural network index and the similarity ratings by the subjects. Both measures of acoustic similarity were significantly correlated with the groups' association patterns, indicating that both methods of quantifying acoustic similarity are biologically meaningful. An index based on neural network analysis therefore represents an objective and repeatable means of measuring acoustic similarity, and allows comparison of results across studies, species and time.

Acoustics↗

PubMed1992

Reconstruction of neural networks is organized by co-existence of various signal molecules or input activation in Helix pomatia L.

The overlapping neural networks consisting of multifunctional neurons were shown to take part alternatively in regulation of various visceral functions or behaviour. The reconstruction of the neural networks was shown to be a function of input activation or transmitter cocktail used at the vicinity of the neurons. In rearrangement of neural networks acetylcholine (Ach), serotonin (5HT) and molluscan neuropeptide, FMRFamide were found to be effective. The modulation occurs at the level of ion channels and at least three different types, namely the Ca-, delayed K- and the unspecific cation channels were shown to be responsible for it. The modulatory action of low molecular weight neurotransmitters and peptides was more often directed to the same species of ion channels, but the maximum of channel activation can appear at different voltage ranges. The modulation of afferent and efferent pathways by signal molecules can assure the mosaic-like functioning of the units of neural networks.

Acetylcholine↗

PubMed1997

Prediction of Phase Behavior in Microemulsion Systems Using Artificial Neural Networks

Preliminary investigations have been conducted to assess the potential for using (back-propagation, feed-forward) artificial neural networks to predict the phase behavior of quaternary microemulsion-forming systems, with a view to employing this type of methodology in the evaluation of novel cosurfactants for the formulation of pharmaceutically acceptable drug-delivery systems. The data employed in training the neural networks related to microemulsion systems containing lecithin, isopropyl myristate, and water, together with different types of cosurfactants, including short- and medium-chain alcohols, amines, acids, and ethylene glycol monoalkyl ethers. Previously unpublished phase diagrams are presented for four systems involving the cosurfactants 2-methyl-2-butanol, 2-methyl-1-propanol, 2-methyl-1-butanol, and isopropanol, which, along with eight other published sets of data, are used to test the predictive ability of the trained networks. The pseudo-ternary phase diagrams for these systems are predicted using only four computed physicochemical properties for the cosurfactants involved. The artificial neural networks are shown to be highly successful in predicting phase behavior for these systems, achieving mean success rates of 96.7 and 91.6% for training and test data, respectively. The conclusion is reached that artificial neural networks can provide useful tools for the development of microemulsion-based drug-delivery systems.

Journal Article↗

PubMed1993

Development of predictive models of laboratory animal growth using artificial neural networks.

Traditional regression analysis of body weight growth curves encounters problems when the data are extremely variable. While transformations are often employed to meet the criteria of the analysis, some transformations are inadequate for normalizing the data. Regression analysis also requires presuppositions regarding the model to be fit and the techniques to be used in the analysis. An alternative approach using artificial neural networks is presented which may be suitable for developing predictive models of growth. Neural networks are simulators of the processes that occur in the biological brain during the learning process. They are trained on the data, developing the necessary algorithms within their internal architecture, and produce a predictive model based on the learned facts. A dataset of Sprague-Dawley rat (Rattus norvegicus) weights is analyzed by both traditional regression analysis and neural network training. Predictions of body weight are made from both models. While both methods produce models that adequately predict the body weights, the neural network model is superior in that it combines accuracy and precision, being less influenced by longitudinal variability in the data. Thus, the neural network provides another tool for researchers to analyze growth curve data.

Algorithms↗

PubMed2001

Minimal number of chicken daily growth velocities for artificial neural network detection of pulmonary hypertension syndrome (PHS).

Previously, evaluation of the first 2 wk of daily growth velocity with an artificial neural network (ANN) provided an effective noninvasive approach for predicting the susceptibility of broilers to pulmonary hypertension syndrome (PHS). This study was conducted to define the minimum number of days of growth data and the type of ANN required for the best prediction of PHS susceptibility. Four experiments were conducted in which broilers were weighed daily at 0800 h. In Experiment 1, Hubbard male broilers were reared to 50 d of age, with 13 developing PHS and 33 remaining normal (N), for a PHS:N ratio of 13:33. In Experiment 2, ANAK broilers were exposed to cool temperatures (16 to 17 C) from 17 to 42 d of age, resulting in a PHS:N ratio of 16:46 for males. In Experiments 3 and 4, Hubbard male and female chicks from a base population and a PHS-resistant line were exposed to cool temperatures from 17 to 42 d (Experiment 3) or 49 d of age (Experiment 4). The PHS:N ratios were 40:68 for males and 6:96 for females in Experiment 3 and 26:91 for males and 10:58 for females in Experiment 4. Four ANN, back propagation (BP3), Ward back propagation (WardBP), probabilistic (PNN), and general regression (GRNN), were evaluated for their ability to predict PHS in the shortest number of days based on daily growth velocities (BWd+1-BWd). A 100% prediction of PHS and N birds was considered the criterion of success. Starting with 14 d of data, each ANN was trained on daily growth velocity, and the number of predictive days was reduced with each run of the ANN. The best ANN was a GRNN, which correctly diagnosed PHS and N male broilers on 4 and 6 d of growth velocity data for Experiments 1 and 2, respectively. The results were poorer with the BP3, WardBP, and PNN. The diagnostic ability of the neural network was not consistent over all four experiments. In Experiment 2, a minimum of 6 d was required for 100% PHS detection for males. In Experiment 3, the best diagnostic value for males was 93% PHS detection and 100% N detection at 15 d. For females, the 100% PHS detection occurred at a minimum of 8 d. In Experiment 4, males had 100% PHS and N detection at a minimum of 11 d. Females had a 100% PHS and N detection at a minimum of 10 d. An attempt to build a single neural network that would detect PHS susceptibility in Hubbard (Experiment 1) and ANAK (Experiment 2) broilers was unsuccessful. The application (validation) of neural networks between experiments also was not successful (data not presented). However, these studies demonstrate that within a breed or line reared under similar selection pressures for ascites, a GRNN based on the first 14 d of growth velocity can detect, with at least 93% accuracy, broilers susceptible to PHS.

Age Factors↗

PubMed2003

A novel approach to the recognition of protein architecture from sequence using Fourier analysis and neural networks.

A novel method is presented for the prediction of protein architecture from sequence using neural networks. The method involves the preprocessing of protein sequence data by numerically encoding it and then applying a Fourier transform. The encoded and transformed data are then used to train a neural network to recognize a number of different protein architectures. The method proved significantly better than comparable alternative strategies such as percentage dipeptide frequency, but is still limited by the size of the data set and the input demands of a neural network. Its main potential is as a complement to existing fold recognition techniques, with its ability to identify global symmetries within protein structures its greatest strength.

Algorithms↗

PubMed1997

HAVNET: A New Neural Network Architecture for Pattern Recognition.

A new artificial neural network architecture, specifically designed for two-dimensional binary pattern recognition, is introduced. The network employs a unique similarity metric, based on the Hausdorff distance, to determine the degree of match between an input pattern and a learned representation. Use of this metric in the network leads to behaviour that is more consistent with human performance than that generated by similarity metrics currently in use in other artificial neural networks. A detailed description of the architecture, the learning equations, and the recall equations for the network are presented. An extension of the network is also described in which each class of learned objects is represented by multiple two-dimensional aspects. This extension greatly increases the utility of the network for tasks like character recognition and three-dimensional vision. The network is employed on an example pattern recognition task to demonstrate its application, with very good results. Copyright 1996 Elsevier Science Ltd.

Journal Article↗

PubMedDate not supplied

A spiking neural network architecture for nonlinear function approximation.

Multilayer perceptrons have received much attention in recent years due to their universal approximation capabilities. Normally, such models use real valued continuous signals, although they are loosely based on biological neuronal networks that encode signals using spike trains. Spiking neural networks are of interest both from a biological point of view and in terms of a method of robust signaling in particularly noisy or difficult environments. It is important to consider networks based on spike trains. A basic question that needs to be considered however, is what type of architecture can be used to provide universal function approximation capabilities in spiking networks? In this paper, we propose a spiking neural network architecture using both integrate-and-fire units as well as delays, that is capable of approximating a real valued function mapping to within a specified degree of accuracy.

Action Potentials↗

PubMed1995

An artificial intelligent diagnostic system with neural networks to determine genetical disorders and fetal health by using maternal serum markers.

OBJECTIVE: To develop an artificial intelligent diagnostic system with neural networks to determine genetical disorders and fetal health problems by using maternal serum markers ('Triple Test') and maternal age. STUDY DESIGN: A total of 112 pregnant women were referred to Fetal Medicine Unit of Hacettepe University Hospital for fetal ultrasonography and chromosome analysis with different indications. All patients underwent genetic amniocentesis or fetal blood sampling under ultrasound guidance. Gross malformations and hydrops fetalis were detected in 15 and 5 fetuses, respectively. We have found chromosomal abnormality in 7 cases. 'Triple Test' is offered to all patients and serum levels of alpha-fetoprotein, human chorionic gonadotropin and unconjugated estriol were analyzed by radioimmunoassay. In this study, we have used supervised artificial neural network structure to develop a diagnostic system. Our system's input parameters are maternal age, gestational age and 'Triple Test' results. Our system consists of two different artificial neural network modules whose decision-making logics are different. One of them is designed to search genetical disorders while the other one is for the assessment of fetal well-being. Confusion matrix is used for statistical evaluation. RESULTS: The discriminatory power of the artificial neural network to search genetical disorders and fetal well-being is found to be highly significant (z = 10.583 and z = 10.424, respectively). CONCLUSION: This system brings objectively to the evaluation of 'Triple Test' results and can be used both for the detection of genetical disorders and fetal well-being. Nevertheless, the analysis program's performance is limited to input information and knowledge and medical expert expert can not get more than he or she has donated the system.

Adolescent↗

PubMed2005

Diagnosis of alcoholism based on neural network analysis of phenotypic risk factors.

BACKGROUND: Alcoholism is a serious public health problem. It has both genetic and environmental causes. In an effort to gain understanding of the underlying genetic susceptibility to alcoholism, a long-term study has been undertaken. The Collaborative Study on the Genetics of Alcoholism (COGA) provides a rich source of genetic and phenotypic data. One ongoing problem is the difficulty of reliably diagnosing alcoholism, despite many known risk factors and measurements. We have applied a well known pattern-matching method, neural network analysis, to phenotypic data provided to participants in Genetic Analysis Workshop 14 by COGA. The aim is to train the network to recognize complex phenotypic patterns that are characteristic of those with alcoholism as well as those who are free of symptoms. Our results indicate that this approach may be helpful in the diagnosis of alcoholism. RESULTS: Training and testing of input/output pairs of risk factors by means of a "feed-forward back-propagation" neural network resulted in reliability of about 94% in predicting the presence or absence of alcoholism based on 36 input phenotypic risk factors. Pruning the neural network to remove relatively uninformative factors resulted in a reduced network of 14 input factors that was still 95% reliable. Some of the factors selected by the pruning steps have been identified as traits that show either linkage or association to potential candidate regions. CONCLUSION: The complex, multivariate picture formed by known risk factors for alcoholism can be incorporated into a neural network analysis that reliably predicts the presence or absence of alcoholism about 94-95% of the time. Several characteristics that were identified by a pruned neural network have previously been shown to be important in this disease based on more traditional linkage and association studies. Neural networks therefore provide one less traditional approach to both identifying alcoholic individuals and determining the most informative risk factors.

Alcohol Drinking↗

PubMed1996

Performance of multi-layer feedforward neural networks to predict liver transplantation outcome.

A novel multisolutional clustering and quantization (MCQ) algorithm has been developed that provides a flexible way to preprocess data. It was tested whether it would impact the neural network's performance favorably and whether the employment of the proposed algorithm would enable neural networks to handle missing data. This was assessed by comparing the performance of neural networks using a well-documented data set to predict outcome following liver transplantation. This new approach to data preprocessing leads to a statistically significant improvement in network performance when compared to simple linear scaling. The obtained results also showed that coding missing data as zeroes in combination with the MCQ algorithm, leads to a significant improvement in neural network performance on a data set containing missing values in 59.4% of cases when compared to replacement of missing values with either series means or medians.

Algorithms↗

PubMed1994

A hierarchical neural network assembly for classification of cervical cells in automated screening.

Experiments are described using artificial neural networks to classify cells imaged in cervical smears according to their degree of abnormality. This problem of classification was broken into 3 subtasks, each of which an independent back-propagation neural network was trained to solve. Input patterns were fed to the first network for classification of the cells as essentially normal or abnormal and then, depending on the outcome of the classification, a second stage was invoked for classifying the cell as (i) normal or mildly dysplastic, or (ii) moderately or severely dysplastic. It is shown that the correct choice of normalization of input data, as well as the use of a hierarchy of neural networks, each optimised for a specific subtask of the whole classification process, yields a predictive value hitherto unattained by automated systems.

Algorithms↗