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 847 records · Page 47Linked to original sources
PubMed2003

Prediction of delayed renal allograft function using an artificial neural network.

BACKGROUND: Delayed graft function (DGF) is one of the most important complications in the post-transplant period, having an adverse effect on both the immediate and long-term graft survival. In this study, an artificial neural network was used to predict the occurrence of DGF and compared with traditional logistical regression models for prediction of DGF. METHODS: A total of 304 cadaveric renal transplants performed at the Jewish Hospital, Louisville were included in the study. Covariate analysis by artificial neural networks and traditional logistical regression were done to predict the occurrence of DGF. RESULTS: The incidence of DGF in this study was 38%. Logistic regression analysis was more sensitive to prediction of no DGF (91 vs 70%), while the neural network was more sensitive to prediction of yes for DGF (56 vs 37%). Overall prediction accuracy for both logistic regression and the neural network was 64 and 63%, respectively. Logistic regression was 36.5% sensitive and 90.7% specific. The neural network was 63.5% sensitive and 64.8% specific. The only covariate with a P < 0.001 was the transplant of a white donor kidney to a black recipient. Cox proportional hazard regression was used to test for the negative effect of DGF on long-term graft survival. One year graft survival in patients without DGF was 92 +/- 2% vs 81 +/- 3% in patients with DGF. The 5-year graft survival was not affected by DGF in this study. CONCLUSION: Artificial neural networks may be used for prediction of DGF in cadaveric renal transplants. This method is more sensitive but less specific than logistic regression methods.

Adult↗
PubMed2007

[Predictive role of diagnostic information in treatment efficacy of rheumatoid arthritis based on neural network model analysis].

OBJECTIVE: To analyze the indications of the therapies for rheumatoid arthritis (RA) with neural network model analysis. METHODS: Three hundred and ninety-seven patients were included in the clinical trial from 9 clinical centers. They were randomly divided into Western medicine (WM) treated group, 194 cases; and traditional Chinese herbal medicine (CM) treated group, 203 cases. A complete physical examination and 18 common clinical manifestations were prepared before the randomization and after the treatment. The WM therapy included voltaren extended action tablet, methotrexate and sulfasalazine. The CM therapy included Glucosidorum Tripterygii Totorum Tablet and syndrome differentiation treatment. The American College of Rheumatology 20 (ACR20) was taken as efficacy evaluation. All data were analyzed on SAS 8.2 statistical package. The relationships between each variable and efficacy were analyzed, and the variables with P<0.2 were included for the data mining analysis with neural network model. All data were classified into training set (75%) and verification set (25%) for further verification on the data-mining model. RESULTS: Eighteen variables in CM and 24 variables in WM were included in the data-mining model. In CM, morning stiffness, swollen joint number, peripheral immunoglobulin M (IgM) level, tenderness joint number, tenderness, rheumatoid factor (RF), C-reactive protein (CRP) and joint pain were positively related to the efficacy, and disease duration and more urination at night negatively related to the efficacy. In WM, erythrocyte sedimentation rate (ESR), weak waist, white fur in tongue, joint pain, joint stiffness and swollen joint were positively related to the efficacy, and yellow fur in tongue, red tongue, white blood negatively related to the efficacy. In the analysis with the neural network model in the patients of verification set, the predictive response rates of 20% patients would be 100% and 90% in the treatment with CM and WM, respectively. CONCLUSION: Neural network model analysis, based on the full clinical trial data with collection of both traditional Chinese medicine and modern medicine diagnostic information, shows a good predictive role for the information in the efficacy in rheumatoid arthritis.

Adult↗
PubMed1999

Applications of neural networks to recovery of biological products.

Artificial neural networks (ANN) are being applied to recovery of products from fermentation broths. Recovery methods for which mathematical models are complex or non-existent are particularly suitable for control and analysis by ANNs. Use and potential of artificial neural networks for product recovery applications are reviewed.

Journal Article↗
PubMed2006

Detection of pseudosinusoidal epileptic seizure segments in the neonatal EEG by cascading a rule-based algorithm with a neural network.

This paper presents an approach to detect epileptic seizure segments in the neonatal electroencephalogram (EEG) by characterizing the spectral features of the EEG waveform using a rule-based algorithm cascaded with a neural network. A rule-based algorithm screens out short segments of pseudosinusoidal EEG patterns as epileptic based on features in the power spectrum. The output of the rule-based algorithm is used to train and compare the performance of conventional feedforward neural networks and quantum neural networks. The results indicate that the trained neural networks, cascaded with the rule-based algorithm, improved the performance of the rule-based algorithm acting by itself. The evaluation of the proposed cascaded scheme for the detection of pseudosinusoidal seizure segments reveals its potential as a building block of the automated seizure detection system under development.

Algorithms↗
PubMed2002

An approach to the interpretation of backpropagation neural network models in QSAR studies.

An approach to the interpretation of backpropagation neural network models for quantitative structure-activity and structure-property relationships (QSAR/QSPR) studies is proposed. The method is based on analyzing the first and second moments of distribution of the values of the first and the second partial derivatives of neural network outputs with respect to inputs calculated at data points. The use of such statistics makes it possible not only to obtain actually the same characteristics as for the case of traditional "interpretable" statistical methods, such as the linear regression analysis, but also to reveal important additional information regarding the non-linear character of QSAR/QSPR relationships. The approach is illustrated by an example of interpreting a backpropagation neural network model for predicting position of the long-wave absorption band of cyane dyes.

Adsorption↗
PubMed1994

Neural network analysis of the P300 event-related potential in multiple sclerosis.

Neural network analysis is sensitive to subtle changes in patterns of data. We hypothesized that a disease process which can cause impairment of cortical function such as multiple sclerosis (MS) would affect the P300 cognitive evoked potential (P300) in a manner detectable by a feedforward backpropagation neural network. Such a network was trained using a learning data set consisting of 101 P300 wave forms (from 26 MS patients and 26 normal controls). The network was then used to classify a randomly selected test data set of 20 studies (2 studies each of 5 MS patients and 5 controls) to which it had not been previously exposed, with an average accuracy (MS = abnormal, control = normal) of 81% for a single midline electrode, increasing to 90% using 3 midline electrodes in a jury system. Neural network analysis can be of help in distinguishing normal (control) P300 from abnormal (MS) P300.

Acoustic Stimulation↗
PubMed2004

Comparison of logistic regression and neural network analysis applied to predicting living setting after hip fracture.

PURPOSE: Describe and compare the characteristics of artificial neural networks and logistic regression to develop prediction models in epidemiological research. METHODS: The sample included 3708 persons with hip fracture from 46 different states included in the Uniform Data System for Medical Rehabilitation. Mean age was 75.5 years (sd=14.2), 73.7% of patients were female, and 82% were non-Hispanic white. Average length of stay was 17.0 days (sd=10.6). The primary outcome measure was living setting (at home vs. not at home) at 80 to 180 days after discharge. RESULTS: Statistically significant variables (p <.05) in the logistic model included follow-up therapy, sphincter control, self-care ability, marital status, age, and length of stay. Areas under the receiver operating characteristic curves were 0.67 for logistic regression and 0.73 for neural network analysis. Calibration curves indicated a slightly better fit for the neural network model. CONCLUSIONS: Follow-up therapy and independent bowel and/or bladder function were strong predictors of living at home up to 6 months after hospitalization for hip fracture. No practical differences were found between the predictive ability of logistic regression and neural network analysis in this sample.

Aged↗
PubMed1990

Evolutionary optimization and neural network models of behavior.

One of the main challenges to the adaptionist program in general and the use of optimization models in behavioral and evolutionary ecology, in particular, is that organisms are so constrained by ontogeny and phylogeny that they may not be able to attain optimal solutions, however those are defined. This paper responds to the challenge through the comparison of optimality and neural network models for the behavior of an individual polychaete worm. The evolutionary optimization model is used to compute behaviors (movement in and out of a tube) that maximize a measure of Darwinian fitness based on individual survival and reproduction. The neural network involves motor, sensory, energetic reserve and clock neuronal groups. Ontogeny of the neural network is the change of connections of a single individual in response to its experiences in the environment. Evolution of the neural network is the natural selection of initial values of connections between groups and learning rules for changing connections. Taken together, these can be viewed as "design parameters". The best neural networks have fitnesses between 85% and 99% of the fitness of the evolutionary optimization model. More complicated models for polychaete worms are discussed. Formulation of a neural network model for host acceptance decisions by tephritid fruit flies leads to predictions about the neurobiology of the flies. The general conclusion is that neural networks appear to be sufficiently rich and plastic that even weak evolution of design parameters may be sufficient for organisms to achieve behaviors that give fitnesses close to the evolutionary optimal fitness, particularly if the behaviors are relatively simple.

Animals↗
PubMed2005

Multi/infinite dimensional neural networks, multi/infinite dimensional logic theory.

A mathematical model of an arbitrary multi-dimensional neural network is developed and a convergence theorem for an arbitrary multi-dimensional neural network represented by a fully symmetric tensor is stated and proved. The input and output signal states of a multi-dimensional neural network/logic gate are related through an energy function, defined over the fully symmetric tensor (representing the connection structure of a multi-dimensional neural network). The inputs and outputs are related such that the minimum/maximum energy states correspond to the output states of the logic gate/neural network realizing a logic function. Similarly, a logic circuit consisting of the interconnection of logic gates, represented by a block symmetric tensor, is associated with a quadratic/higher degree energy function. Infinite dimensional logic theory is discussed through the utilization of infinite dimension/order tensors.

Algorithms↗
PubMed1997

Characteristic Functions and Process Identification by Neural Networks.

Principal component analysis (PCA) algorithms use neural networks to extract the eigenvectors of the correlation matrix from the data. However, if the process is non-Gaussian, PCA algorithms or their higher order generalisations provide only incomplete or misleading information on the statistical properties of the data. To handle such situations we propose neural network algorithms, with an hybrid (supervised and unsupervised) learning scheme, which constructs the characteristic function of the probability distribution and the transition functions of the stochastic process. Illustrative examples are presented, which include Cauchy and Lévy-type processes.

Journal Article↗
PubMed1995

Experiments in dysarthric speech recognition using artificial neural networks.

In this study, we investigated the use of artificial neural networks (ANNs) to recognize dysarthric speech. Two multilayer neural networks were developed, trained, and tested using isolated words spoken by a dysarthric speaker. One network had the fast Fourier transform (FFT) coefficients as inputs, while the other network had the formant frequencies as inputs. The effect of additional features in the input vector on the recognition rate was also observed. The recognition rate was evaluated against the intelligibility rating obtained by five human listeners and also against the recognition rate of the Introvoice commercial speech-recognition system. Preliminary results demonstrated the ability of the developed networks to successfully recognize dysarthric speech despite its large variability. These networks clearly outperformed both the human listeners and the Introvoice commercial system.

Adult↗
PubMed2004

A neural network model with feature selection for Korean speech act classification.

A speech act is a linguistic action intended by a speaker. Speech act classification is an essential part of a dialogue understanding system because the speech act of an utterance is closely tied with the user's intention in the utterance. We propose a neural network model for Korean speech act classification. In addition, we propose a method that extracts morphological features from surface utterances and selects effective ones among the morphological features. Using the feature selection method, the proposed neural network can partially increase precision and decrease training time. In the experiment, the proposed neural network showed better results than other models using comparatively high-level linguistic features. Based on the experimental result, we believe that the proposed neural network model is suitable for real field applications because it is easy to expand the neural network model into other domains. Moreover, we found that neural networks can be useful in speech act classification if we can convert surface sentences into vectors with fixed dimensions by using an effective feature selection method.

Asian People↗
PubMed1998

Cubic approximation neural network for multivariate functions.

This paper introduces a novel neural network architecture-cubic approximation neural network (CANN), capable of local approximation of multivariate functions. It is particularly simple in concept and in structure. Its simplicity enables a quantitative evaluation of its approximation capabilities, namely, for a desired error bound the size of the needed network can be calculated. In addition, if a training session is used, a thorough analysis of the learning process performance is performed. The trade-off between the rate of learning and the steady-state performance is clearly demonstrated. On the other hand, this approach suffers from the problem common to all local approximation networks-the number of neurons grows exponentially with the dimension of the input vector.

Journal Article↗
PubMed2003

Artificial neural networks for decision-making in urologic oncology.

Artificial neural networks (ANNs) are computational methodologies that perform multifactorial analyses, inspired by networks of biological neurons. Like neural networks, ANNs contain layers of simple points (nodes) of data that interract through carefully weighted connection lines. ANNs are "trained" and balanced by having been previously fed data, which the ANN uses as the means for adjusting its interconnections. Studies have shown that novel and highly accurate ANNs significantly enhance the ability to detect prostate cancer early (high sensitivity) while avoiding a greater number of unnecessary tissue samplings (high specificity). The use of ANNs in prostate cancer is ideal because of 1) multiple predicting factors that influence outcome; 2) the desire to offer individual consulting based on various tests; 3) the fact that prior logistic regression analysis results have had serious limitations in application; and 4) the need for an up-to-date tool that can apply easily to everyone. An ANN should be seen as an important tool that is complementary to the physician's personal knowledge and judgment in making decisions.

Journal Article↗
PubMed2004

Non-linear filtering of ultrasonic signals using neural networks.

Structure noise from inhomogeneous micro-structures makes the detection of flaws present in highly scattering materials difficult. Several techniques have been applied to improve the signal-to-noise ratio (SNR) in order to make flaw detection easier. Linear filtering does not provide good results because both structure noise and flaw signal concentrate energy in the same frequency band. Non-linear filtering can be used to reduce the structure noise of ultrasonic signals. Therefore, neural networks are applied in this work for this purpose. In order to use neural networks for non-linear filtering, dynamic structures must be applied. The easiest way to implement a neural network with the capability of processing temporal patterns is to consider them spatial ones, applying the signal into a tapped delay line of finite extension, that is the input of a static neural network (for example, a multi-layer perceptron). In this work, a dynamic neural network has been built to filter ultrasonic signals with structure noise, and has been trained with the real-time back-propagation algorithm, using as inputs 3000 synthetic ultrasonic signals of 896 samples each. Target signals for training are the same as the ones used as inputs but without noise. The neural network is trained in order to generate as output the target signal when the noisy input one is applied. For testing the performance of the non-linear filter, a new set of 500 noisy signals has been used. The SNR improvement is about 6 dB average. The results show that this non-linear filtering method is quite useful as pre-processing stage in flaw detection systems.

Algorithms↗
PubMed1993

A neural network approach to the classification of autism.

A nonlinear pattern recognition system, neural network technology, was explored for its utility in assisting in the classification of autism. It was compared with a more traditional approach, simultaneous and stepwise linear discriminant analyses, in terms of the ability of each methodology to both classify and predict persons as having autism or mental retardation based on information obtained from a new structured parent interview: the Autistic Behavior Interview. The neural network methodology was superior to discriminant function analysis both in its ability to classify groups (92 vs. 85%) and to generalize to new cases that were not part of the training sample (92 vs. 82%). Interrater and test-retest reliabilities and measures of internal consistency were satisfactory for most of the subscales in the Autistic Behavior Interview. The implications of neural network technology for diagnosis, in general, and for understanding of possible core deficits in autism are discussed.

Adolescent↗
PubMedDate not supplied

Classification of in vivo 1H MR spectra from breast tissue using artificial neural networks.

BACKGROUND: The study was designed in order to investigate whether artificial neural networks could be used for analysis of in vivo magnetic resonance (MR) spectra from breast cancer patients. MATERIALS AND METHODS: In vivo 1H MR spectra with three different echo times (TE 135, 350 and 450 msec) were acquired from patients with benign and malignant breast lesions and from healthy volunteers, of whom some were breast-feeding. A spectral region (4.0-1.5 ppm) was used as input for artificial neural network analysis, for the attempted classification of the data into different groups. RESULTS: Data recorded at all three echo times were necessary to obtain the best results. Furthermore, malignant tissue was differentiated from benign tumours using this approach, whereas benign tumours were poorly separated from healthy tissue. CONCLUSION: The results presented here indicate that in vivo MR spectroscopy in conjunction with neural network analysis might be useful for the evaluation of breast lesions.

Breast↗
PubMed2003

Prediction of lower pole stone clearance after shock wave lithotripsy using an artificial neural network.

PURPOSE: We performed this study as a comprehensive evaluation of variables reported to affect lower pole stone clearance after shock wave lithotripsy using artificial neural network analysis. MATERIALS AND METHODS: The radiographic images and treatment records of 680 patients with lower pole renal calculi treated with primary shock wave lithotripsy using the Wolf Piezolith 2500 (Wolf, Knittlingen, Germany) lithotriptor were retrospectively evaluated by applying artificial neural network analysis. Successful stone clearance was defined as absent fragments of any size detected on plain x-ray with tomography and/or excretory pyelography performed 6 months after treatment. Prognostic variables included patient characteristics, laboratory values, stone characteristics and the spatial anatomy of the lower pole, as defined by infundibular length, diameter, caliceal pelvic height, 2 measurements of the lower infundibulopelvic and infundibuloureteropelvic angles as well as the pattern of dynamic urinary transport. RESULTS: Artificial neural network analysis had 92% accuracy for correctly predicting lower pole stone clearance. The pattern of dynamic urinary transport represented the most influential predictor of stone clearance, followed by a measure of the infundibuloureteropelvic angle, body mass index, caliceal pelvic height and stone size. Anatomical measurements of lower pole anatomy and classification of the type of urinary transport were well reproducible with low intra-observer and interobserver variability (correlation coefficient alpha >0.8). CONCLUSIONS: In a comprehensive analysis of variables reported to influence lower pole stone clearance artificial neural network analysis predicted stone clearance with a high degree of accuracy. The relative importance of dynamic urinary transport in lower pole stones and the usefulness of artificial neural network analysis to predict shock wave lithotripsy outcomes in individuals must be confirmed in a prospective trial.

Adolescent↗