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 379 records · Page 21Linked to original sources
PubMed1995

Structured neural network of medical diagnosis for hepatobiliary diseases.

This study aims to apply a structured neural network system for improving diagnostic capabilities of hepatobiliary diseases. Several neural networks were organized according to a priori knowledge. A priori knowledge consists of five pathological states. We compared the diagnostic accuracy of discriminant function, ordinary and structured neural networks. The diagnostic capabilities among testing data were 96% by structured neural network, 70% by ordinary neural network, and 66% by discriminant function. The structured neural network had the significantly higher diagnostic accuracy than the other two methods.

Aged↗
PubMed1995

On the training and performance of high-order neural networks.

An extensive study was undertaken on the architecture, training, and properties of neural networks of order higher than 1. The formulation of the training of high-order neural networks as a nonlinear associative recall problem provides the basis for their optimal least squares training. The simplicity of the outer-product rule motivates the study of the approximation of optimal least squares training by the outer-product rule and the effect of the network order on the efficiency of this approximation. Neural networks with composite key patterns are subsequently proposed as the natural generalization of neural networks of order higher than 1. The properties of this class of neural networks are revealed by studying their optimal least squares training and its relationship with the outer-product rule. The performance of neural networks with composite key patterns is analytically evaluated by studying their capacity. The properties and performance bounds provided by the analytical study are verified through experimental results.

Least-Squares Analysis↗
PubMed1999

Neural networks in the diagnosis of malignant ovarian tumours.

OBJECTIVE: To assess the role of neural networks in predicting the likelihood of malignancy in women presenting with ovarian tumours. DESIGN: Retrospective case study. SETTING: University Department of Obstetrics and Gynaecology, St James's Hospital, Leeds. METHODS: Information from 217 cases with histologically proven benign, borderline or malignant tumours was extracted for study. Four variables (age, ultrasound findings with and without colour Doppler imaging and CA125) were entered in the neural network classifier. The neural network results were compared with logistic regression analysis. RESULTS: When used in the neural network the variables of age, CA125 and ultrasound score produced the best result with a sensitivity of 95% and a corresponding specificity of 78% in predicting malignancy. Logistic regression gave a sensitivity or 82% for a specificity of 51%. CONCLUSION: The neural network is a good method of combining diagnostic variables and may be a useful predictor of malignancy in women presenting with ovarian tumours. A comparison of the performance of the neural network with conventional diagnostic methods would be warranted prior to use in clinical practice.

Adolescent↗
PubMed1997

Artificial neural networks applied to outcome prediction for colorectal cancer patients in separate institutions.

BACKGROUND: Artificial neural networks are computer programs that can be used to discover complex relations within data sets. They permit the recognition of patterns in complex biological data sets that cannot be detected with conventional linear statistical analysis. One such complex problem is the prediction of outcome for individual patients treated for colorectal cancer. Predictions of outcome in such patients have traditionally been based on population statistics. However, these predictions have little meaning for the individual patient. We report the training of neural networks to predict outcome for individual patients from one institution and their predictive performance on data from a different institution in another region. METHODS: 5-year follow-up data from 334 patients treated for colorectal cancer were used to train and validate six neural networks designed for the prediction of death within 9, 12, 15, 18, 21, and 24 months. The previously trained 12-month neural network was then applied to 2-year follow-up data from patients from a second institution; outcome was concealed. No further training of the neural network was undertaken. The network's predictions were compared with those of two consultant colorectal surgeons supplied with the same data. FINDINGS: All six neural networks were able to achieve overall accuracy greater than 80% for the prediction of death for individual patients at institution 1 within 9, 12, 15, 18, 21, and 24 months. The mean sensitivity and specificity were 60% and 88%. When the neural network trained to predict death within 12 months was applied to data from the second institution, overall accuracy of 90% (95% CI 84-96) was achieved, compared with the overall accuracy of the colorectal surgeons of 79% (71-87) and 75% (66-84). INTERPRETATION: The neural networks were able to predict outcome for individual patients with colorectal cancer much more accurately than the currently available clinicopathological methods. Once trained on data from one institution, the neural networks were able to predict outcome for patients from an unrelated institution.

Bias↗
PubMed2002

[Application of resilient backpropagation neural network in predicting hydrophobic parameters of alkylbenzenes].

Artificial neural networks have been applied for predicting the hydrophobic parameters of alkylbenzene. Compared with traditional methods it has the advantages of simple operation and wide applications. Based on error back propagation neural networks the relationship among the molecular connectivity index (chi), van der Waals surface area (Aw) and hydrophobic parameter was studied, meanwhile the mathematical model was established and used to predict the hydrophobic parameters. By comparing the hydrophobic parameters of experimental values with those calculated by neural networks, we found they had good agreement. The average relative deviation was less than 1%. Because traditional back propagation network is generally time consuming, resilient backpropagation (RPROP) algorithm was used to solve this problem. By using RPROP algorithm, the hydrophobic parameters were obtained precisely by fast training and simple parameter's selection. It needed less than 1,000 iterations to reach the goal on the computer operated at 1.4 GHz. The present work shows that the artificial neural network is a new powerful tool to predict the physicochemical parameters.

Algorithms↗
PubMed2002

Distinguishing spurious and nominal attractors applying unlearning to an asymmetric neural network.

We study a neural network with asymmetric connections used as an associative memory. Asymmetry allows the nominal patterns to be stored in cycles. We apply an unlearning procedure, which modifies the synaptic connections. We analyze the global performance, including the network capacity, the attraction basin's size and also the relaxation time distribution. The latter shows a convenient bimodality that is used for discriminating between spurious and stored memory attractors. We show that unlearning in asymmetric networks allows enhancing the global performance of retrieval including retrieval of a sequence of correlated patterns.

Algorithms↗
PubMed2003

Prediction of dihydrofolate reductase inhibition and selectivity using computational neural networks and linear discriminant analysis.

A data set of 345 dihydrofolate reductase inhibitors was used to build QSAR models that correlate chemical structure and inhibition potency for three types of dihydrofolate reductase (DHFR): rat liver (rl), Pneumocystis carinii (pc), and Toxoplasma gondii (tg). Quantitative models were built using subsets of molecular structure descriptors being analyzed by computational neural networks. Neural network models were able to accurately predict log IC(50) values for the three types of DHFR to within +/-0.65 log units (data sets ranged approximately 5.5 log units) of the experimentally determined values. Classification models were also constructed using linear discriminant analysis to identify compounds as selective or nonselective inhibitors of bacterial DHFR (pcDHFR and tgDHFR) relative to mammalian DHFR (rlDHFR). A leave-N-out training procedure was used to add robustness to the models and to prove that consistent results could be obtained using different training and prediction set splits. The best linear discriminant analysis (LDA) models were able to correctly predict DHFR selectivity for approximately 70% of the external prediction set compounds. A set of new nitrogen and oxygen-specific descriptors were developed especially for this data set to better encode structural features, which are believed to directly influence DHFR inhibition and selectivity.

Animals↗
PubMed2000

[Artificial neural network for the identification of infrared spectra].

An Artificial Neural Network(ANN) was used to identify unknown infrared spectra. The Neural Network consisted of three layers was trained by a back-propagation algorithm. In the first step of the experiment, the training set was pure spectra information, the neural network can only identify correctly the spectra without noise or with relatively low noise, in the second step, the training set was spectra information with relatively low noise, the identification results of the test sets was better than that of the first step. The results showed that artificial neural network can be used as a powerful tool in solving classification and identification problems.

Algorithms↗
PubMed1997

Computational neural networks for predictive microbiology: I. Methodology.

Artificial neural networks are mathematical tools inspired by what is known about the physical structure and mechanism of the biological cognition and learning. Neural networks have attracted considerable attention due to their efficacy to model wide spectrum of challenging problems. In this paper, we present one of the most popular networks, the backpropagation, and discuss its learning algorithm and analyze several issues necessary for designating optimal networks that can generalize after being trained on examples. As an application in the area of predictive microbiology, modeling of microorganism growth by neural networks will be presented in a second paper of this series.

Algorithms↗
PubMed2006

A simplified dual neural network for quadratic programming with its KWTA application.

The design, analysis, and application of a new recurrent neural network for quadratic programming, called simplified dual neural network, are discussed. The analysis mainly concentrates on the convergence property and the computational complexity of the neural network. The simplified dual neural network is shown to be globally convergent to the exact optimal solution. The complexity of the neural network architecture is reduced with the number of neurons equal to the number of inequality constraints. Its application to k-winners-take-all (KWTA) operation is discussed to demonstrate how to solve problems with this neural network.

Algorithms↗
PubMed1997

Use of an artificial neural network to analyse an ECG with QS complex in V1-2 leads.

A feed-forward neural network with back-propagation algorithm is used to distinguish anterior wall myocardial infarction (AI) and non-infarction based on analysis of computerised electrocardiograms. Data used in the study are from 132 patients diagnosed as having AI by automated electrocardiograph analysis. Their ECGs show an abnormal Q-wave (or QS complex) or small R progression in leads V1 and V2. However, 66 of them are diagnosed as old AI from the history, physical examination, echocardiogram and other laboratory data, whereas the other 66 are not. The network is trained with the data from half of the AI and non-infarction patients; respectively. The diagnostic accuracy rate is then tested with the remaining 66 patients (33 infarction, 33 non-infarction) who have not been exposed to the network. The neural network correctly identifies 90.2% of the patients with AI and 93.3% of the patients without infarction. The neural network is capable of diagnosing anterior wall myocardial infarction better than a computer electrocardiograph.

Decision Trees↗
PubMed2004

Prediction of mortality in an Indian intensive care unit. Comparison between APACHE II and artificial neural networks.

OBJECTIVE: To compare hospital outcome prediction using an artificial neural network model, built on an Indian data set, with the APACHE II (Acute Physiology and Chronic Health Evaluation II) logistic regression model. DESIGN: Analysis of a database containing prospectively collected data. SETTING: Medical-neurological ICU of a university hospital in Mumbai, India. SUBJECTS: Two thousand sixty-two consecutive admissions between 1996 and 1998. INTERVENTIONS: None. MEASUREMENTS AND RESULTS: The 22 variables used to obtain day-1 APACHE II score and risk of death were recorded. Data from 1,962 patients were used to train the neural network using a back-propagation algorithm. Data from the remaining 1,000 patients were used for testing this model and comparing it with APACHE II. There were 337 deaths in these 1,000 patients; APACHE II predicted 246 deaths while the neural network predicted 336 deaths. Calibration, assessed by the Hosmer-Lemeshow statistic, was better with the neural network (H=22.4) than with APACHE II (H=123.5) and so was discrimination (area under receiver operating characteristic curve =0.87 versus 0.77, p=0.002). Analysis of information gain due to each of the 22 variables revealed that the neural network could predict outcome using only 15 variables. A new model using these 15 variables predicted 335 deaths, had calibration (H=27.7) and discrimination (area under receiver operating characteristic curve =0.88) which was comparable to the 22-variable model (p=0.87) and superior to the APACHE II equation (p<0.001). CONCLUSION: Artificial neural networks, trained on Indian patient data, used fewer variables and yet outperformed the APACHE II system in predicting hospital outcome.

APACHE↗
PubMed1995

Applications of neural networks in medicine.

Artificial Neural Networks (ANNs) are a relatively new approach to computing inspired by the design and operation of the human brain. This paper introduces ANNs and describes some of their applications in the area of medicine, including cancer prognosis, segmentation of magnetic resonance images, and automated analysis of electrocardiograms.

Breast Neoplasms↗
PubMed2001

Improved long-term temperature prediction by chaining of neural networks.

When an artificial neural network (ANN) is trained to predict signals p steps ahead, the quality of the prediction typically decreases for large values of p. In this paper, we compare two methods for prediction with ANNs: the classical recursion of one-step ahead predictors and a new kind of chain structure. When applying both techniques to the prediction of the temperature at the end of a blast furnace, we conclude that the chaining approach leads to an improved prediction of the temperature and avoidance of instabilities, since the chained networks gradually take the prediction of their predecessors in the chain as an extra input. It is observed that instabilities might occur in the iterative case, which does not happen with the chaining approach. To select relevant inputs and decrease the number of weights in this approach, Automatic Relevance Determination (ARD) for multilayer perceptrons is applied.

Bayes Theorem↗
PubMed2000

Linear programming based on neural networks for radiotherapy treatment planning.

In this paper, we propose a neural network model for linear programming that is designed to optimize radiotherapy treatment planning (RTP). This kind of neural network can be easily implemented by using a kind of 'neural' electronic system in order to obtain an optimization solution in real time. We first give an introduction to the RTP problem and construct a non-constraint objective function for the neural network model. We adopt a gradient algorithm to minimize the objective function and design the structure of the neural network for RTP. Compared to traditional linear programming methods, this neural network model can reduce the time needed for convergence, the size of problems (i.e., the number of variables to be searched) and the number of extra slack and surplus variables needed. We obtained a set of optimized beam weights that result in a better dose distribution as compared to that obtained using the simplex algorithm under the same initial condition. The example presented in this paper shows that this model is feasible in three-dimensional RTP.

Algorithms↗
PubMedDate not supplied

Selecting screening candidates for kinase and G protein-coupled receptor targets using neural networks.

A series of neural networks has been trained, using consensus methods, to recognize compounds that act at biological targets belonging to specific gene families. The MDDR database was used to provide compounds targeted against gene families and sets of randomly selected molecules. BCUT parameters were employed as input descriptors that encode structural properties and information relevant to ligand-receptor interactions. In each case, the networks identified over 80% of the compounds targeting a gene family. The technique was applied to purchasing compounds from external suppliers, and results from screening against one gene family demonstrated impressive abilities to predict the activity of the majority of known hit compounds.

Databases, Factual↗
PubMed2000

A local training and pruning approach for neural networks.

The training of neural networks using the extended Kalman filter (EKF) algorithm is plagued by the drawback of high computational complexity and storage requirement that may become prohibitive even for networks of moderate size. In this paper, we present a local EKF training and pruning approach that can solve this problem. In particular, the by-products obtained along with the local EKF training can be utilized to measure the importance of the network weights. Comparing with the original global approach, the proposed local EKF training and pruning approach results in a much lower computational complexity and storage requirement. Hence, it is more practical in solving real world problems. The performance of the proposed algorithm is demonstrated on one medium- and one large-scale problems, namely, sunspot data prediction and handwritten digit recognition.

Algorithms↗
PubMed1994

Detecting dysfunctional behavior in adolescents: the examination of relationships using neural networks.

We describe a neural network that models the effect of personality, social, and environmental variables on hopelessness in adolescents. A sensitivity analysis suggests the effect that variation in each of the input variables will have on the output. Clinical implications are that health professionals can focus their attention on the variables most likely to impact upon the outcome.

Adolescent↗