PubMed Health⌕ Search

SEARCH · PubMed Health

Results for “Neural Networks, Computer”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

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

At least 757 records · Page 42Linked to original sources
PubMedDate not supplied

Data mining and healthcare informatics.

OBJECTIVE: To acquaint members of the Academy with a relatively recent development in the area of data exploration and statistical analysis. METHODS: A review of the concepts and methods inherent in data-mining with a special emphasis on the those methods applicable to predictive modeling. RESULTS: Data-mining is demonstrated to be a useful tool for researchers in those circumstances where large amounts of information are available. CONCLUSIONS: With the advent and proliferation of on-line data collection, truly massive databases are now available to health care researchers. In that situation, data-mining methods yield some unique opportunities to researchers who wish to develop prediction models and to establish associations.

Database Management Systems↗
PubMed1997

Prognostic factors: classification approaches in patients with lung cancer.

With the proliferation of potential prognostic factors for lung cancer, it is becoming increasingly more difficult to integrate the information provided by these factors into a single accurate prediction of clinical outcome. Here we reviewed five classification methods for their capabilities in classification of 200 patients with lung cancer into distinct prognostic groups using survival outcome as a criteria. The source of patient data for this study is a Lung Tumour Registry from Institute for Lung Diseases, University Clinical Hospital, Belgrade. Almost all developed classification algorithms determined prognostic groups according to biochemical tumour markers LDH and alkaline phosphatase, producing most significant split, instead of commonly used staging variables. The choice of which approach to use for a given classification problem depends not only on statistical properties of method, but also on medical considerations, such as whether more differential findings are given greater weight and the applicability of a classification rule.

Alkaline Phosphatase↗
PubMed1999

Data integration to assist gastric emptying data analysis.

The diagnosis of dyspepsia is very difficult because the symptoms are clinically aspecific and the gastric emptying time tests are of complex interpretation. An integrated and automated analysis of clinical and instrumental data may improve the diagnostic process. We present a system to collect data on dyspeptic patient from different sources which has been set up to assist the clinician in the diagnosis of dyspepsia. The data base integrates a wide set of symptoms with data coming from laboratory tests. Moreover, we assess the feasibility of classifying gastric emptying profiles using both octanoid acid excretion data and electrogastrography.

Adult↗
PubMed1999

[CMACPAR an modified parallel neuro-controller for control processes].

CMACPAR is a Parallel Neurocontroller oriented to real time systems as for example Control Processes. Its characteristics are mainly a fast learning algorithm, a reduced number of calculations, great generalization capacity, local learning and intrinsic parallelism. This type of neurocontroller is used in real time applications required by refineries, hydroelectric centers, factories, etc. In this work we present the analysis and the parallel implementation of a modified scheme of the Cerebellar Model CMAC for the n-dimensional space projection using a mean granularity parallel neurocontroller. The proposed memory management allows for a significant memory reduction in training time and required memory size.

Algorithms↗
PubMed2001

Combining decision support and image processing: a PROforma model.

This paper addresses two important problems in medical image interpretation:(1) integration of numeric and symbolic information, (2) access to external sources of medical knowledge. We have developed a prototype in which image processing algorithms are combined with symbolic representations for reasoning, decision making and task management in an integrated, platform-independent system for the differential diagnosis of abnormalities in mammograms. The prototype is based on PROforma, a generic technology for building decision support systems based on clinical guidelines. The PROforma language defines a set of tasks, one of which, the enquiry, is used as means of interaction with the outside world. However, the current enquiry model has proved to be too limited for our purposes. In this paper we outline a more general model, which can be used as an interface between symbolic functions and image or other signal data.

Algorithms↗
PubMed2005

Evaluating the discriminatory power of a computer-based system for assessing penetrating trauma on retrospective multi-center data.

OBJECTIVE: To evaluate the discriminatory power of TraumaSCAN-Web, a system for assessing penetrating trauma, using retrospective multi-center case data for gunshot and stab wounds to the thorax and abdomen. METHODS: 80 gunshot and 114 stab cases were evaluated using TraumaSCAN-Web. Areas under the Receiver Operator Characteristic Curves (AUC) were calculated for each condition modeled in TraumaSCAN-Web. RESULTS: Of the 23 conditions modeled by TraumaSCAN-Web, 19 were present in either the gunshot or stab case data. The gunshot AUCs ranged from 0.519 (pericardial tamponade) to 0.975 (right renal injury). The stab AUCs ranged from 0.701 (intestinal injury) to 1.000 (tracheal injury).

Abdominal Injuries↗
PubMed1997

Update in digital mammography.

Digital mammography is a rapidly developing technology that has great potential to improve upon and ultimately replace conventional film-screen mammography for the early detection of breast cancer. This article reviews current progress in digital mammographic systems, computer-aided diagnostic programs, and artificial neural networks. Digital mammographic systems are currently in an investigational phase only. Large-scale clinical trials are needed in all areas of digital mammography before this exciting new technology can be implemented outside of research centers.

Artificial Intelligence↗
PubMed2004

An analysis of exponential stability of delayed neural networks with time varying delays.

This paper derives a new sufficient condition for the exponential stability of the equilibrium point for delayed neural networks with time varying delays by employing a Lyapunov-Krasovskii functional and using Linear Matrix Inequality (LMI) approach. This result establishes a relation between the delay time and the parameters of the network. The result is also compared with the most recent result derived in the literature.

Animals↗
PubMed2000

Prediction and significance of the temporal pattern of hormone secretion in disease states.

Comparison of the temporal pattern of hormone secretion in health and disease reveals distinct differences in many systems. Analysis of these visually apparent differences conventionally rests on computer-assisted programs based on either model assumptions, or estimations of hormonal decay rates or threshold values, all of which may not accurately reflect physiological and/or pathophysiological states. Only recently have new methods evolved which are independent of preexisting knowledge of the system under study. Apart from the widely used approximate entropy statistic (ApEn), a measure for the regularity of a time-series, artificial neural networks are able to capture temporal structures in endocrine rhythms without any previous assumptions. In particular, non-linear dynamical systems may be delineated and separated from random behaviour. This is achieved by mapping complex input data to a given complex output by propagating data from the input layer to the output layer through a larger number of interconnections, so-called hidden layers. The networks are capable to extract relevant features from training samples and store this information in the distributed structure of interconnections. Using this approach on growth hormone (GH) rhythms of healthy controls, fasted healthy subjects, untreated acromegalic patients and acromegalics under octreotide suppressive therapy we were recently able to demonstrate the power of this approach to differentiate the temporal pattern of GH secretion following normalization of the data for absolute amplitudes. In a second approach we were able to significantly reduce the number of data points required to characterize the temporal structure of these rhythms. This latter quality of the networks may help to transfer analysis of changes in the temporal pattern of hormone secretion on a more routine basis.

Human Growth Hormone↗
PubMed2005

Generalised reliability characteristics for probabilistic networks.

BACKGROUND: In the medical domain, establishing a diagnosis typically amounts to reasoning about the unobservable truth, based upon a set of indirect observations from diagnostic tests. A diagnostic test may not be perfectly reliable, however. To avoid misdiagnosis, therefore, the reliability characteristics of the test should be taken into account upon reasoning. OBJECTIVE: In this paper, we address the issue of modelling the reliability characteristics of diagnostic tests in a probabilistic network. METHOD: To this end, we study the mathematical foundation of a test's characteristics and collate them with the probabilities required for a probabilistic network. RESULTS: We show that the standard reliability characteristics that are generally available from the literature have to be further detailed and stratified, for example by experts, before they can be included in a network. We demonstrate these modelling issues by means of a real-life probabilistic network in oncology.

Diagnosis, Computer-Assisted↗
PubMed1998

A dynamic neural network with temporal coding and functional connectivity.

A neural network model capable of altering its pattern classifying properties by program input is proposed. Here the "program input" is another source of input besides the pattern input. Unlike most neural network models, this model runs as a deterministic point process of spikes in continuous time; connections among neurons have finite delays, which are set randomly according to a normal distribution. Furthermore, this model utilizes functional connectivity which is dynamic connectivity among neurons peculiar to temporal-coding neural networks with short neuronal decay time constants. Computer simulation of the proposed network has been performed, and the results are considered in light of experimental results shown recently for correlated firings of neurons.

Computer Simulation↗
PubMed1996

Learning activation rules rather than connection weights.

In the construction of neural networks involving associative recall, information is sometimes best encoded with a local representation. Moreover, a priori knowledge can lead to a natural selection of connection weights for these networks. With predetermined and fixed weights, standard learning algorithms that work by altering connection strengths are unable to train such networks. To address this problem, this paper derives a supervised learning rule based on gradient descent, where connection weights are fixed and a network is trained by changing the activation rule. It incorporates both traditional and competitive activation mechanisms, the latter being an efficient method for instilling competition in a network. The learning rule has been implemented, and the results from several test networks demonstrate that it works effectively.

Algorithms↗
PubMed1996

Artificial neural networks: a prospective tool for the analysis of psychiatric disorders.

Artificial neural networks are computer simulations of biological parallel distributed processing systems. They are able to undertake complex pattern recognition tasks, including diagnostic classification, prediction of disease onset and prognosis, and identification of determinants of clinical decisions. These capabilities have been utilized in general medicine, but as yet there has been little application of artificial neural networks in psychiatric research. Artificial neural networks can also be used to create models of brain function, providing a paradigm for cognition and the organization of neural systems that demonstrates how changes at the cellular level can affect information processing. These models are able to encompass both the biological and the behavioral dimensions of psychiatric disorders.

Humans↗
PubMed1999

Observer variation in cytologic grading for cervical dysplasia of Papanicolaou smears with the PAPNET testing system.

BACKGROUND: To assess the interobserver and intraobserver variation of Papanicolaou (Pap) smear screening with the computer-assisted (neural network based) PAPNET Testing System in diagnosing cervical smear abnormalities, results of agreement were compared with the interobserver and intraobserver variation of conventional smear analysis. METHODS: Cervical smears obtained from women in 1996 were reevaluated both by conventional light microscopy and with use of the PAPNET Testing System by the same four investigators, and results were compared with the original screening diagnoses obtained by both methods. RESULTS: The interobserver results for epithelial abnormalities (the degree of agreement between the cytologists), characterized by weighted kappa statistics, were 0.71 (95% CI: 0. 68-0.73) for PAPNET screening and 0.69 (95% CI: 0.66-0.72) for conventional screening. No significant differences were found among the individual results obtained by the four cytotechnologists (intraobserver variation) with conventional screening versus PAPNET reviewing. CONCLUSIONS: Pap smear grading with the PAPNET Testing System has interobserver and intraobserver variation similar to that of conventional screening of Pap smears in routine use. Cancer (Cancer Cytopathol)

Diagnosis, Differential↗
PubMed1997

A preliminary laboratory investigation of air embolus detection and grading using an artificial neural network.

SUMMARY STATEMENT: Processed digitized Doppler signals abstracted from recordings during continuous air infusion in dogs were used to train a neural network to estimate air embolism infusion rates. BACKGROUND: Precordial Doppler is a sensitive technique for detecting venous air embolism during anesthesia, but it requires constant attentive listening. Since neural networks are particularly well suited to the task of pattern recognition, we sought to investigate this technology for detection and grading of air embolism. METHODS: Air was infused into peripheral veins of four anesthetized dogs at rates of 0.025, 0.05, 0.10, 0.25, 0.50 and 1.0 ml-1.kg-1.min-1 while digital recordings of the precordial Doppler ultrasound signal were collected. The frequency content of the recordings was determined by Fourier analysis. The output of the Fourier transform was the input to a neural network. The network was then trained to estimate the air infusion rate. RESULTS: The correlation coefficient between the size of the air embolism and the air infusion rate was greater than r2 = 0.93 for each of the four animals in the study when the network was trained using the data for all four dogs. When the data from a dog was withheld from the training set and used only for testing the correlation coefficients ranged from r2 = 0.75 to r2 = 0.27. For frequencies below 250 Hz, the acoustic energy tended to fall as the air infusion rate increased. The opposite occurred at frequencies above 325 Hz. CONCLUSIONS: Neural network processing of the precordial Doppler signal provides a quantitative estimate of the size of an air embolism.

Anesthesia↗
PubMed1994

Model reference direct adaptive control of nonlinear plants using neural networks.

A learning scheme for multilayer feedforward neural networks used as direct adaptive controllers of nonlinear plants is suggested. This scheme is a supervised steepest descent one that does not require backpropagation of the error. Using a neural network controller trained with this method does not require the identification stage and this makes it superior to the other methodologies. Methods for using neural networks in plant control suggested in the literature are discussed and compared with the proposed system. The structure of the network and the training method used are explained. Simulations based on model reference control of some nonlinear plants show satisfactory performance.

Computer Simulation↗