Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “network analysis”

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 1,189 records · Page 66Linked to original sources
PubMed2001

Time-on-task analysis using wavelet networks in an event-related potential study on attention-deficit hyperactivity disorder.

OBJECTIVE: The aim of this event-related potential (ERP) study was to test time-on-task analysis at the level of single sweeps in a clinical trial. Since inattentiveness is one of the main symptoms of attention-deficit hyperactivity disorder (ADHD), this child psychiatric disorder was chosen as an exemplary application. METHODS: Twenty-four healthy and 24 ADHD boys, aged 9--15 years, performed an auditory selective attention task for about 5 min. ERP single trials were analyzed using wavelet networks. Time-on-task analysis was applied to omission errors, reaction time and slow ERP components (frontal negativity, parietal positivity), represented by a low-frequency wavelet component. RESULTS: Both performance and ERP measures showed distinct temporal dynamics. Time-on-task effects were not only linear, but also of higher order and started after less than 1 min. For ADHD children, earlier time-on-task effects, i.e. an earlier increase of omission errors and frontal negativity, resulted. Healthy children could allocate more attentional resources during the course of the experiment. CONCLUSION: Time-on-task analysis at the level of single trials revealed phenomena probably reflecting ADHD children's attentional deficits. Thus, a more differentiated ERP analysis may provide a better understanding of the pathophysiological background in neuropsychiatric disorders.

Acoustic Stimulation↗
PubMed1997

The application of image analysis and neural network technology to the study of large-cell liver-cell dysplasia and hepatocellular carcinoma.

Liver cell dysplasia (LCD) is considered a preneoplastic lesion, whose characterization and differentiation from hepatocellular carcinoma (HCC) and from the reactive changes seen in cirrhosis has been controversial. We studied 12 cases of LCD (large cell type) with image analysis techniques (IA) and compared the findings with those of HCC (n = 40), and a spectrum of non-neoplastic hepatic lesions including normal liver and cirrhosis (n = 49). A minimum of 200 Feulgen-stained nuclei were measured from each lesion with the CAS 200 image analysis system. The data were collected with the aid of CellSheet software. Thirty-four variables were measured, including geometric, textural, and photometric nuclear features and DNA ploidy. The data were analyzed with multivariate statistics and a backpropagation neural network (NN). Stepwise statistical analysis selected 22 variables that were statistically significant in the three groups with P values <.05. Various NN architectures were developed using these variables. The best NN architecture included a sigmoidal transfer function, 14 input, 16 hidden, and 3 output neurons. It trained to completion after 8,887 runs using 90% of the lesions. This NN yielded a 100% cross-validation rate for unknown cases. These data support the concept of LCD (large cell type) as a lesion that can be objectively distinguished from HCC and non-neoplastic liver. Our study also demonstrates the potential usefulness of IA for the evaluation of difficult histopathological problems.

Carcinoma, Hepatocellular↗
PubMedDate not supplied

Structure-activity relationship studies of carcinogenic activity of polycyclic aromatic hydrocarbons using calculated molecular descriptors with principal component analysis and neural network methods.

Recently a new methodology based on local density of state (LDOS) calculations using topological and semiempirical methods was proposed to identify the carcinogenic activity of polycyclic aromatic hydrocarbons (PAHs). In this work we perform a comparative study of this methodology with principal component analysis (PCA) and neural networks (NN). The PCA and NN results show that LDOS quantum chemical descriptors are relevant descriptors to identify the carcinogenic activity of methylated and non-methylated PAHs. Also, we show that the combination of these distinct methodologies can be an efficient and powerful tool in the structure-activity studies of PAHs compounds. We have studied 81 methylated and non-methylated PAHs, and our study shows that with the use of these methods it is possible to correctly predict the carcinogenic activity of PAHs with accuracy higher than 80%.

Carcinogens↗
PubMed1998

Classification of observational data with artificial neural networks versus discriminant analysis in pharmacoepidemiological studies--can outcome of fluoxetine treatment be predicted?

For several years, there has been an ongoing discussion about appropriate methodological tools to be applied to observational data in pharmacoepidemiological studies. It is now suggested by our research group that artificial neural networks (ANN) might be advantageous in some cases for classification purposes when compared with discriminant analysis. This is due to their inherent capability to detect complex linear and nonlinear functions in multivariate data sets, the possibility of including data on different scales in the same model, as well as their relative resistance to "noisy" input. In this paper, a short introduction is given to the basics of neural networks and possible applications. For demonstration, a comparison between artificial neural networks and discriminant analysis was performed on a multivariate data set, consisting of observational data of 19738 patients treated with fluoxetine. It was tested, which of the two statistical tools outperforms the two other in regard to the therapeutic response prediction from the clinical input data. Essentially, it was found that neither discriminant analysis nor ANN are able to predict the clinical outcome on the basis of the employed clinical variables. Applying ANN, we were able to rule out the possibility of undetected suppressor effects to a greater extent than would have been possible by the exclusive application of discriminant analysis.

Antidepressive Agents, Second-Generation↗
PubMed1993

Protection of patient data in multi-institutional medical computer networks: regulatory effectiveness analysis.

Privacy protection is one of the major issues in the development of multi-institutional clinical information networks. Judicial decisions have confirmed patient's rights to protection of a "reasonable expectation of privacy". Incorporating this protection into a system requires analysis of appropriate models. The National Practitioner Data Bank (NPDB) contains confidential data concerning physician competence. The medical profession had substantial input into the privacy protection features of the NPDB, which are much more comprehensive than those used in many clinical information systems. The NPDB represents the privacy protection which physicians expect for their own data. Regulatory Effectiveness Analysis can be used to analyze the suitability of the NPDB as a model for patient privacy protection. Judicial opinions set public policy and legal structures for privacy, and the NPDB provides an inventory of useable technical tools. After eliminating minor discontinuities, the NPDB can be used as a model to create a useable standard for privacy for multi institutional data transfers.

Civil Rights↗
PubMed1998

Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach.

Flexible modelling in survival analysis can be useful both for exploratory and predictive purposes. Feed forward neural networks were recently considered for flexible non-linear modelling of censored survival data through the generalization of both discrete and continuous time models. We show that by treating the time interval as an input variable in a standard feed forward network with logistic activation and entropy error function, it is possible to estimate smoothed discrete hazards as conditional probabilities of failure. We considered an easily implementable approach with a fast selection criteria of the best configurations. Examples on data sets from two clinical trials are provided. The proposed artificial neural network (ANN) approach can be applied for the estimation of the functional relationships between covariates and time in survival data to improve model predictivity in the presence of complex prognostic relationships.

Clinical Trials as Topic↗
PubMedDate not supplied

Flow visualization tools for image analysis of capillary networks.

OBJECTIVE: Video recordings of red blood cell (RBC) flow through capillary networks contain a considerable amount of information pertaining to oxygen transport through the microcirculation. Image analysis of these video recordings has been widely used to determine RBC dynamics (velocity, lineal density and supply rate) and oxygenation (Brunner et al., 2000; Ellis et al., 1990, 1992; Ellsworth et al., 1987; Klyscz et al., 1997; Pries 1988). However, not all capillaries in a given field of view are suitable for image analysis. Typically, capillary segments that are relatively straight and in sharp focus, and exhibit flow of individual RBCs that are well separated by plasma gaps, are good candidates for analysis. We have developed several image processing tools to aid in the selection of such capillaries for analysis and to obtain quick overviews of RBC flow through the microcirculation. METHODS: Burgess et al. (Microcirc. 2:75, 1995) and Burkell et al. (Annals Biomed. Eng. 24:1, 1996; J. Vasc. Res. 35:2, 1998) have previously introduced mean and variance images to aid in the selection of capillaries for analysis. We have extended their concept and developed similar two dimensional visualization techniques for studies of RBC flow through capillary networks. RESULTS: Five new methods of processing video data were developed. The minimum image highlights all capillaries containing RBCs in a given field of view. The maximum image identifies capillaries that exhibit high lineal density or stopped flow. The range image represents the difference between the maximum and minimum light intensity values that occur at a given pixel over a given time period, and helps to identify capillary segments that are in good focus and are perfused by RBCs and plasma. The difference image represents the cumulative sum of the square of differences in intensity values between consecutive frames and gives an indication of the frequency of passage of RBCs separated by plasma gaps. The transition image represents the number of times the intensity at a given pixel crosses a predefined threshold and indicates the number of RBCs (or trains of RBCs) that passes a given location during the observation period. CONCLUSIONS: The above flow visualization techniques are valuable tools to aid in the study of image focus, network geometry, RBC flow paths and dynamics, that can then be used in identifying capillaries for subsequent (separate) detailed analysis to provide quantitative information about RBC flow.

Algorithms↗
PubMed2006

Translating DNA data tables into quasi-median networks for parsimony analysis and error detection.

Every DNA data table can be turned into a quasi-median network that faithfully represents the data. We show that for (weighted) condensed data tables the associated network harbors all most parsimonious reconstructions for any tree that connects the sampled haplotypes. Structural features of this network can be computed directly from the data table. The key principle repeatedly used is that the quasi-median network is uniquely determined by the sub-tables for pairs of characters. The translation of a table into a network enhances the understanding of the properties of the data in regard to homoplasy and potential artifacts. The total number of nodes of such a network measures the complexity of the data. In particular, networks that display the results of filter analyses by which hotspot mutations are removed help to detect data idiosyncrasies and thus pinpoint sequencing problems. A pertinent example drawn from human mtDNA illustrates these points.

Animals↗
PubMed2002

Impact of hepatitis B core antibody status on outcomes of cadaveric renal transplantation: analysis of United network of organ sharing database between 1994 and 1999.

BACKGROUND: Organ shortage continues to be a major problem in transplantation. The use of organs from marginal donors who are hepatitis B surface antigen (HBsAg) negative and hepatitis B core antibody (anti-HBc Ab) reactive (+), could increase the donor pool substantially. Little information is available about the effects of anti-HBc Ab (+) donor status on viral transmission, and graft and patient survival. To address these issues, an analysis was performed using the United Network of Organ Sharing cadaveric kidney transplant database between 1994 to 1999. METHODS: All cadaveric kidney transplants performed between 1994 to 1999 with negative HBsAg serology were evaluated. Viral transmission, and graft and patient outcomes were measured. The analysis included follow-up information in the United Network of Organ Sharing database through September 2000. A multivariate analysis was performed, using known confounding factors that may affect the outcomes in donors and recipients who were designated as (+) or (-) (D+/R+, ++D+/R-, D-/R-, and D-/R+) according to their anti-HBc Ab status. RESULTS: Univariate analyses showed that graft and patient survival rates were statistically significantly lower in D+/R- compared with those who were D-/R-. However, multivariate regression analyses showed that neither donor nor recipient anti-HBc Ab status influenced the risk of graft failure or patient death after adjustment for other factors. Anti-HBc Ab (+) kidneys resulted in a higher incidence of anti-HBc antibody seroconversion but this was not associated with a higher incidence of HBsAg detection. CONCLUSION: We conclude that renal allografts from anti-HBc Ab (+) donors should be considered for transplant especially in successfully immunized recipients.

Adult↗
PubMed2004

Learning feedforward control using a dilated B-spline network: frequency domain analysis and design.

This paper presents a frequency-domain analysis and design approach for a learning feedforward controller (LFFC) using a dilated B-spline network. The LFFC acts as an add-on element to the existing feedback controller (FBC). The LFFC signal is updated iteratively based on the FBC signal of the previous iteration as the task repeats. Similar to proportional-integral-derivative controller tuning, there are only two parameters to adjust: The B-spline support width and the learning gain. The effect of dilation in the B-spline network is discussed. Detailed design formulae are given based on a stability analysis. As an illustration, simulation results on the path tracking control of a wheeled mobile robot are presented.

Artificial Intelligence↗
PubMed2005

Deriving sufficient conditions for global asymptotic stability of delayed neural networks via nonsmooth analysis--II.

Following our recent approach of nonsmooth analysis, we report a new set of sufficient conditions and its implications for the global asymptotic stability of delayed cellular neural networks (DCNN). The new conditions not only unify a string of previous stability results, but also yield strict improvement over them by allowing the symmetric part of the feedback matrix positive definite, hence enlarging the application domain of DCNNs. Advantages of the new results over existing ones are illustrated with examples. We also compare our results with those related results obtained via LMI approach.

Algorithms↗
PubMed1996

An expert diagnostic system based on neural networks and image analysis techniques in the field of automated cytogenetics.

In this study, we introduce an expert system for intelligent chromosome recognition and classification based on artificial neural networks (ANN) and features obtained by automated image analysis techniques. A microscope equipped with a CCTV camera, integrated with an IBM-PC compatible computer environment including a frame grabber, is used for image data acquisition. Features of the chromosomes are obtained directly from the digital chromosome images. Two new algorithms for automated object detection and object skeletonizing constitute the basis of the feature extraction phase which constructs the components of the input vector to the ANN part of the system. This first version of our intelligent diagnostic system uses a trained unsupervised neural network structure and an original rule-based classification algorithm to find a karyotyped form of randomly distributed chromosomes over a complete metaphase. We investigate the effects of network parameters on the classification performance and discuss the adaptability and flexibility of the neural system in order to reach a structure giving an output including information about both structural and numerical abnormalities. Moreover, the classification performances of neural and rule-based system are compared for each class of chromosome.

Algorithms↗
PubMedDate not supplied

A novel neural network technique for analysis and classification of EM single-particle images.

We propose a novel self-organizing neural network for the unsupervised classification of electron microscopy (EM) images of biological macromolecules. The radical novelty of the algorithm lies in its rigorous mathematical formulation that, starting from a large set of possibly very noisy input data, finds a set of "representative" data items, organized onto an ordered output map, such that the probability density of this set of representative items resembles at its possible best the probability density of the input data. In a way, it summarizes large amounts of information into a concise description that rigorously keeps the basic pattern of the input data distribution. In this application to the field of three-dimensional EM of single particles, two different data sets have been used; one comprised 2458 rotational power spectra of individual negative stain images of the G40P helicase of Bacillus subtilis bacteriophage SPP1, and the other contained 2822 cryoelectron images of SV40 large T-antigen. Our experimental results prove that this technique is indeed very successful, providing the user with the capability of exploring complex patterns in a succinct, informative, and objective manner. The above facts, together with the consideration that the integration of this new algorithm with commonly used software packages is immediate, prompt us to propose it as a valuable new tool in the analysis of large collections of noisy data.

Algorithms↗
PubMed2026

Comparative Efficacy of Insulin and Alternative Therapies for Hypertriglyceridemia-Associated Acute Pancreatitis: A Systematic Review and Network Meta-Analysis.

BACKGROUND AND AIMS: Hypertriglyceridemia-induced acute pancreatitis is associated with high triglyceride levels and may lead to significant clinical complications. Rapid TG-lowering strategies, including insulin, therapeutic plasma exchange (TPE), heparin, hemofiltration, and conservative management, are used in clinical practice; however, their comparative efficacy and impact on clinical outcomes remain uncertain. METHODS: Following preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines and International Prospective Register of Systematic Reviews (PROSPERO) registration (CRD420251239674), we searched PubMed, Embase, Web of Science, Scopus, CINAHL, Google Scholar, and Cochrane. Primary outcomes included TG reduction, C-reactive protein (CRP), length of stay, mortality, and organ failure. Secondary outcomes included renal and respiratory failure. Random-effects network meta-analyses estimated mean differences or relative risks with 95% confidence intervals; treatments were ranked using the Surface Under the Cumulative Ranking curve (SUCRA). Predefined sensitivity analyses were conducted according to study design (RCTs) and risk of bias (ROB). RESULTS: Across predominantly observational evidence, no intervention demonstrated statistically significant superiority over insulin-based therapy for mortality, organ failure, or length of stay, and no consistent clinical benefit was observed despite differences in biochemical TG reduction. Although some interventions showed relatively favorable SUCRA rankings across selected outcomes, these findings were not consistently supported by statistically significant or high-certainty evidence. In RCT-restricted analyses, therapeutic plasma exchange (TPE) significantly reduced TG levels versus insulin (MD&#x2009;-&#x2009;620.0; p&#x2009;=&#x2009;0.03) and CRP versus conservative therapy (MD&#x2009;-&#x2009;0.80; p&#x2009;<&#x2009;0.01), while insulin plus heparin was associated with shorter hospital stay (MD&#x2009;-&#x2009;1.60&#xa0;days; p&#x2009;<&#x2009;0.01). However, faster triglyceride reduction did not consistently translate into improved mortality, organ failure, ICU-related outcomes, or length of stay. CONCLUSION: Despite improvements in biochemical markers, the clinical significance of rapid TG reduction in HTG-AP remains uncertain, as these effects were not consistently associated with improvements in mortality, organ failure, ICU-related outcomes, or hospital length of stay. Given that most available evidence was derived from nonrandomized studies and that the certainty of evidence was predominantly low or very low, adequately powered randomized controlled trials are needed to determine whether accelerated triglyceride lowering improves clinically meaningful patient outcomes.

Humans↗
PubMed2026

Comparison of Ketamine and Pregabalin on Postoperative Opioid Usage and Pain Management in Spinal Fusion: Systematic Review and Network Meta-analysis.

BACKGROUND CONTEXT: Spinal fusion is associated with substantial early postoperative pain and opioid exposure. Both ketamine and pregabalin are widely incorporated into Enhanced Recovery After Surgery (ERAS) protocols as opioid-sparing adjuncts. However, their comparative efficacy and safety in this specific setting remain uncertain. Our objective was to compare ketamine and pregabalin indirectly for early postoperative opioid consumption, pain, and adverse events in adults undergoing spinal fusion. METHODS: Pubmed, Embase, and Cochrane Trials were searched from inception through October 2025. Eligible studies were randomized trials enrolling adults undergoing instrumented spinal fusion, randomized to perioperative ketamine, pregabalin, or control, and reported extractable 24-hour opioid consumption or pain outcomes. Continuous outcomes were pooled as mean differences in MME or VAS units, and adverse events were reported descriptively. A connected treatment network was analyzed using random-effects models. Risk of bias (RoB) was assessed with the Cochrane RoB 2 tool. RESULTS: Thirteen trials (n=879) were included: ketamine (n=210), pregabalin (n=271), and control (n=398). Six trials contributed opioid data (3 ketamine, 3 pregabalin). Using pregabalin 150 mg as reference, ketamine was associated with lower 0-24-hour opioid use (MD -56.99 mg MME; 95% CI -99.56 to -14.43). Control (MD +21.31; 95% CI -1.05 to +43.66) and pregabalin 300 mg (MD -13.22; 95% CI -40.41 to +13.96) did not significantly differ from pregabalin 150 mg. Seven trials contributed 24-hour VAS data, with control being associated with higher pain versus pregabalin 150 mg (MD +0.84; 95% CI +0.01 to +1.66), while ketamine and pregabalin 300 mg were not k significantly different. Adverse events were generally infrequent and similar to control. CONCLUSIONS: Both ketamine and pregabalin provide early opioid sparing with comparable 24-hour analgesia. Ketamine showed a larger opioid-sparing point estimate, but indirect comparisons are imprecise. Adequately powered head-to-head trials with standardized protocols and adverse event reporting are needed.

Humans↗
PubMed1999

The learning of first and second person pronouns in English: network models and analysis.

Although most English-speaking children master the correct use of first and second person pronouns by three years, some children show persistent reversal errors in which they refer to themselves as you and to others as me. Recently, such differences have been attributed to the relative availability of overheard speech during the learning process. The present study tested this proposal with feed-forward neural networks learning these pronouns. Network learning speed and analysis of their knowledge representations confirmed the importance of exposure to shifting reference provided by overheard speech. Errorless pronoun learning was linked to the amount of overheard speech, interactions with a greater number of speakers, and prior knowledge of the basic-level kind PERSON.

Child↗
PubMed1989

A framework for the analysis of neuronal networks.

The object of this work is to consider the application of some methods of spike train analysis that are not widely known, and are concerned with the description of the interaction between spike trains and the determination of causal connections between them. The notation and terminology follow conventions established in the statistical literature. The examples given are based on in-continuity recordings of the spontaneous activity of single Ia afferents from the soleus muscle and single motor units from the same muscle. Cumulant densities are shown to be simple extensions of the traditional cross-correlation methods, and are useful in characterizing the pattern of activity in one spike train that influences that in another, and to reveal interactions between spike trains that would not be apparent from the correlation histogram alone. Parameters based on the Fourier transforms of the spike trains are shown to be useful in determining timing relations between them, and in inferring patterns of connectivity not possible by correlation methods alone.

Action Potentials↗