SEARCH · Search PubMed

Results for “knowledge graphs”

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 73 records · Page 4Linked to original sources

PubMed1993

A tutorial introduction to stochastic simulation algorithms for belief networks.

Belief networks combine probabilistic knowledge with explicit information about conditional independence assumptions. A belief network consists of a directed acyclic graph in which the nodes represent variables and the edges express relationships of conditional dependence. When information about one variable's state is given to the network in the form of evidence, an update algorithm computes the posterior marginal probability distributions for the remaining variables in the network. Many algorithms for performing this inference task have been proposed. Exact algorithms report precise results for some classes of networks, but take exponential time (in the number of nodes) both in the worst case and for many interesting networks. Stochastic simulation algorithms estimate the posterior marginal probability distribution for many graph topologies that would require exponential time when using an exact algorithm. Nonetheless, for some belief networks, stochastic simulation algorithms are also known to have exponential worst case performance. This article describes at a tutorial level several stochastic simulation algorithms for belief networks, and illustrates them on some simple examples. In addition, the theoretical and empirical performance of the algorithms is briefly surveyed.

Algorithms↗

PubMed1992

A robust and efficient automated docking algorithm for molecular recognition.

A completely automated method is described for determining the most likely mode of binding of two (macro)molecules from the knowledge of their three-dimensional structures alone. The method is based on well-known graph theoretical techniques and has been used successfully to determine and rationalize the binding of a number of known macromolecular complexes. In this article we present results for a special case of the general molecular recognition problem--given the information concerning the particular atoms involved in the binding for one of the molecules, the algorithm can correctly identify the corresponding (contacting) atoms of the other molecule. The approach used can be easily extended to the general molecular recognition problem and requires the extraction of maximal common subgraphs. In these studies the docking of the macromolecules was achieved without the aid of computer graphics or other visual aids. The algorithm has been used to determine the correct mode of binding of a protein antigen to an antibody in approximately 100 min on a DEC micro VAX 3600.

Algorithms↗

PubMed1999

Bars and lines: a study of graphic communication.

Interpretations of graphs seem to be rooted in principles of cognitive naturalness and information processing rather than arbitrary correspondences. These predict that people should more readily associate bars with discrete comparisons between data points because bars are discrete entities and facilitate point estimates. They should more readily associate lines with trends because lines connect discrete entities and directly represent slope. The predictions were supported in three experiments--two examining comprehension and one production. The correspondence does not seem to depend on explicit knowledge of rules. Instead, it may reflect the influence of the communicative situation as well as the perceptual properties of graphs.

Adult↗

PubMed2026

A nonlinear multi-omics data integration and classification model based on pathway self-attention and graph convolutional networks.

The abundance of omics data has significantly advanced the development of multi-omics data integration techniques. Non-linear embedding approaches for data integration have gradually become the mainstream in multi-omics research, as these approaches can substantially improve cancer analysis by enhancing the quality of the embeddings. However, current multi-omics data integration methods are typically confined to omics measurements, neglecting domain-specific prior knowledge encompassing biological pathways. In this study, we proposed a multi-omics integrated classification model, PathTransGCN, based on pathway self-attention and graph convolutional networks (GCN). The model integrated biological pathway information into multi-omics data analysis with the aim of enhancing the accuracy of cancer classification. Multi-omics data for breast cancer (BRCA), non-small cell lung cancer (NSCLC), and low-grade glioma (LGG) were obtained from The Cancer Genome Atlas (TCGA) and UCSC Xena databases. These data included gene mutations, DNA methylation, copy number variations, and gene expression, and were used to assess the model's generalizability across different cancers. First, PathTransGCN employed a pathway self-attention module to learn latent representations of samples across different pathways, thereby obtaining multi-omics integration vectors. Concurrently, a patient similarity network (PSN) was constructed using the similarity network fusion (SNF) approach. Second, the integrated vectors and the PSN were jointly fed into a GCN for end-to-end training, enabling precise classification of cancer subtypes. Through multi-omics data analysis of the BRCA dataset, PathTransGCN outperformed several popular algorithms (such as MoGCN and DeePathNet) in the five-class classification of cancer subtypes, achieving an accuracy rate of 87.6% and an F1 score of 86.4%. Moreover, the model demonstrated robust generalization capabilities across both NSCLC and LGG datasets, while effectively identifying key disease-associated biomarkers at the pathway level. Experimental results demonstrate that PathTransGCN exhibits outstanding performance in integrating omics data and delivering interpretable classification outcomes, presenting significant potential for clinical applications.

Humans↗

PubMed1992

Natural language processing and semantical representation of medical texts.

For medical records, the challenge for the present decade is Natural Language Processing (NLP) of texts, and the construction of an adequate Knowledge Representation. This article describes the components of an NLP system, which is currently being developed in the Geneva Hospital, and within the European Community's AIM programme. They are: a Natural Language Analyser, a Conceptual Graphs Builder, a Data Base Storage component, a Query Processor, a Natural Language Generator and, in addition, a Translator, a Diagnosis Encoding System and a Literature Indexing System. Taking advantage of a closed domain of knowledge, defined around a medical specialty, a method called proximity processing has been developed. In this situation no parser of the initial text is needed, and the system is based on semantical information of near words in sentences. The benefits are: easy implementation, portability between languages, robustness towards badly-formed sentences, and a sound representation using conceptual graphs.

Abstracting and Indexing↗

PubMed1995

Nutrition intervention program of the Modification of Diet in Renal Disease Study: a self-management approach.

OBJECTIVE: To characterize the Modification of Diet in Renal Disease (MDRD) Study nutrition intervention program by determining the frequency of intervention strategies used by the dietitians and the usefulness of program components as rated by participants. DESIGN: Dietitians recorded which of 32 intervention strategies they used at each monthly visit. Participants rated the usefulness of 19 program components. SUBJECTS: 840 adults with renal insufficiency. INTERVENTION: Participants were assigned randomly to usual-, low-, or very-low-protein diet groups. Each eating pattern also specified a phosphorus intake goal. Each participant met monthly with a dietitian for an average of 26 months. STATISTICAL ANALYSES: Analyses of variance and chi 2 analyses. RESULTS: Dietitians used the following intervention strategies most often in all groups: providing feedback based on self-monitoring and/or food records, reviewing adherence or biochemistry data, providing low-protein foods, and reviewing graphs of adherence progress. In general, the dietitians used feedback, modeling, and support strategies more often, and knowledge and skills strategies less often, with participants who had to make the greatest reductions in protein intake and those with more advanced disease. In all groups, the dietitians' use of knowledge and skills, feedback, and modeling strategies decreased over time (P < .001), whereas use of support strategies was maintained. The type and frequency of intervention strategies used by dietitians and the usefulness ratings of participants did not vary by educational level of the participant. Both self-monitoring and dietitian support were rated as "very useful" by 88% of the participants. CONCLUSIONS: Three features were central to the MDRD Study nutrition intervention program: feedback, particularly from self-monitoring and from measures of adherence; modeling, particularly by providing low-protein food products; and dietitian support. We recommend the self-management approach.

Adult↗

PubMed1995

Dynamic characteristics of prosthetic heart valves.

The relation between flow rate (Q) and transvalvular pressure-drop (DP) is of fundamental importance for a prosthetic heart valve tested in steady flow conditions. The Q-DP plot can thus be called the static characteristic of the valve. While in pulsatile flow, with time (t) as a parameter, the instantaneous Q(t)-DP(t) relation can also be obtained. The Q-DP relation forms a phase graph on an X-Y plane during a whole cardiac cycle, and can be regarded as the dynamic characteristic, which to our knowledge has never been systematically explored before. With in vitro experiment the Q(t)-DP(t) relations are presented for five different aortic valves. Properly modelling the characteristics of heart valves is a key link in modelling the interactions between the ventricle and arterial system. Treatments for valves, such as diode analogue and orifice area assumption governed by the Gorlin formula, are found unsatisfactory. A simple one-dimensional flow equation is used to further examine the Q-DP graph, and both the dynamic resistance characteristic and the dynamic flow characteristic can be obtained. It is found that the dynamic characteristic differs from the static one not only in the inertance effect but also in the transient process, which can be quite energy-consuming and therefore important. Geometric relations of these phase graphs with the transvalvular power loss are discussed. The method of dynamic characteristics provides a new way to evaluate the performance of a tested valve.

Biomedical Engineering↗

PubMed1995

The compositional approach for representing medical concept systems.

The representation of patient-specific information in the computer-based medical record requires an expressive formalism, which supports computational services particularly with respect to subsumption. These demands are not sufficiently met by conventional medical terminology and classification systems. This paper investigates the weaknesses of conventional systems, which are primarily coding systems and contain a certain amount of implicit knowledge. The alternatives are logic-based formalisms, particularly languages of the KL-ONE-family and conceptual graphs, which are based on the formal representation of meanings. Principles of these approaches are reported and compared to the concept representation language developed in the GALEN project. Finally, an overview on the BERNWARD model is given, which aims at the formal description, classification, and composition of medical concepts. In BERNWARD subsumption and part-whole relation are treated in a symmetrical manner. There are explicit and formal criteria for supporting the inference of generic and partitive relations.

Disease↗

PubMed1996

Monocular scotomata and spinal manipulation: the step phenomenon.

OBJECTIVE: To discuss a case history wherein microvascular spasm of the optic nerve was treated by spinal manipulation. CLINICAL FEATURES: A 62-yr-old man developed a scotoma in the vision of the right eye during chiropractic treatment. INTERVENTION AND OUTCOME: Spinal manipulation treatment was continued with total resolution of the scotoma. The rate of recovery of the scotoma was mapped using computerized static perimetry. These measurements showed that significant recovery occurred at each spinal manipulation treatment, producing a stepped graph. CONCLUSION: The use of computerized static perimetry to measure the cerebral effects of spinal manipulation has increased knowledge of how chiropractic works. The further recovery of vision with each spinal adjustment suggests that more treatment may be better than less treatment in the chiropractic management of such cases.

Chiropractic↗

PubMedDate not supplied

[An educational management system for the postgraduate training of physician-radiologists].

The paper is devoted to the development of a system of program-oriented postgraduate education of radiologists based methodologically on acquiring professional knowledge and skills. Educational goals were adapted for each subject area. Matrix analysis and plotting of a logical structure graph were used for a choice of the final goals of education. The subject matter is in full accord with the educational goals, based upon the qualification characteristics of radiologists. The developed and published methodological materials make it possible to control the students' activities during extracurricular training and practical work in x-ray units and at seminars. Directed text control is used for the estimation of efficacy and correction of education.

Education, Medical, Continuing↗

PubMed1990

[Quality control and optimization of therapeutic activity with the use of thermoanalytic methods].

Thermogravimetry, differential scanning calorimetry, thermomicroscopy, transparency measure permit drug quality control: knowledge of solvated or unsolvated mole, thermal stability, identification of crystalline form (polymorphism) quick determination of total impurity with graphs. These methods can be used for therapeutic activity optimization of very weakly soluble drugs: research of the polymorph showing the best kinetic dissolution, establishment of phase diagram drug/inert substance by example for determination invariant composition particularly eutectic for which the drug solubility is increased.

Calorimetry, Differential Scanning↗

PubMed1989

[Relevance of the Periotest as a function of root shape and cross-section].

In the laboratory extracted teeth were provided with an artificial periodontal ligament. Subsequently periotest values were measured around the complete circumference of the crown. When plotted in a graph the relationship between root cross-section and damping value can be demonstrated. At the present level of knowledge only comparative measurements, in particular in teeth with low periotest values, seem reliable.

Humans↗

PubMed1995

[Glossary of terms used by radiologists in image processing].

We give the definition of 166 words used in image processing. Adaptivity, aliazing, analog-digital converter, analysis, approximation, arc, artifact, artificial intelligence, attribute, autocorrelation, bandwidth, boundary, brightness, calibration, class, classification, classify, centre, cluster, coding, color, compression, contrast, connectivity, convolution, correlation, data base, decision, decomposition, deconvolution, deduction, descriptor, detection, digitization, dilation, discontinuity, discretization, discrimination, disparity, display, distance, distorsion, distribution dynamic, edge, energy, enhancement, entropy, erosion, estimation, event, extrapolation, feature, file, filter, filter floaters, fitting, Fourier transform, frequency, fusion, fuzzy, Gaussian, gradient, graph, gray level, group, growing, histogram, Hough transform, Houndsfield, image, impulse response, inertia, intensity, interpolation, interpretation, invariance, isotropy, iterative, JPEG, knowledge base, label, laplacian, learning, least squares, likelihood, matching, Markov field, mask, matching, mathematical morphology, merge (to), MIP, median, minimization, model, moiré, moment, MPEG, neural network, neuron, node, noise, norm, normal, operator, optical system, optimization, orthogonal, parametric, pattern recognition, periodicity, photometry, pixel, polygon, polynomial, prediction, pulsation, pyramidal, quantization, raster, reconstruction, recursive, region, rendering, representation space, resolution, restoration, robustness, ROC, thinning, transform, sampling, saturation, scene analysis, segmentation, separable function, sequential, smoothing, spline, split (to), shape, threshold, tree, signal, speckle, spectrum, spline, stationarity, statistical, stochastic, structuring element, support, syntaxic, synthesis, texture, truncation, variance, vision, voxel, windowing.

Diagnostic Imaging↗

PubMed2000

An algorithm for clustering cDNA fingerprints.

Clustering large data sets is a central challenge in gene expression analysis. The hybridization of synthetic oligonucleotides to arrayed cDNAs yields a fingerprint for each cDNA clone. Cluster analysis of these fingerprints can identify clones corresponding to the same gene. We have developed a novel algorithm for cluster analysis that is based on graph theoretic techniques. Unlike other methods, it does not assume that the clusters are hierarchically structured and does not require prior knowledge on the number of clusters. In tests with simulated libraries the algorithm outperformed the Greedy method and demonstrated high speed and robustness to high error rate. Good solution quality was also obtained in a blind test on real cDNA fingerprints.

Algorithms↗

PubMed1995

Free text analysis.

In the context of hospital information systems (HIS) medical free text analysis is reviewed with respect to current automated approaches to literature retrieval, case retrieval and fact retrieval from textual data in the patient record. The Unified Medical Language System (UMLS) project has enormously stimulated current research. It is expected that UMLS knowledge sources and SNOMED III (which need a translation into other languages as soon as possible) as well as the conceptual graphs formalism, could become standards to utilize free text information contained in HIS databases.

Abstracting and Indexing↗

PubMed1980

Computer-assisted customized antimicrobial dosages.

The use of a computer-based consultation program to customize dosage regimens of antimicrobials for patients with meningitis or bacteremia is described. Using clinical and laboratory information entered by the user, the program determines causative organisms, recommends therapeutic regimens, and generates a graph depicting the expected blood level of each drug as a function of time. During therapy selection, the program considers the site of infection, the susceptibility of the organism to antibiotics, and the patient's clinical status and drug history. Individualized pharmacokinetic values allow for dosage adjustments in renal failure and estimation of blood levels. If renal impairment is present, dosage regimens for drugs excreted by the kidneys are adjusted to assure the desired steady-state blood levels. To help in selection of the optimal regimen, estimated blood levels for each regimen are graphed along with the minimum inhibitory concentration for the organism and the toxic level of the drug. A bulit-in knowledge base in conjunction with patient-specific information enables the computer program to determine appropriate treatment specific to a patient's age, renal function, and prior drug reactions.

Adult↗

PubMedDate not supplied

Using neural network predicted secondary structure information in automatic protein NMR assignment.

In CAPRI, an automated NMR assignment software package that was developed in our laboratory, both chemical shift values and coupling topologies of spin patterns are used in a procedure for amino acids recognition. By using a knowledge base of chemical shift distributions of the 20 amino acid types, fuzzy mathematics, and pattern recognition theory, the spin coupling topological graphs are mapped onto specific amino acid residues. In this work, we investigated the feasibility of using secondary structure information of proteins as predicted by neural networks in the automated NMR assignment. As the 1H and 13C chemical shifts of proteins are known to correlate to their secondary structures, secondary structure information is useful in improving the amino acid recognition. In this study, the secondary structures of proteins predicted by the PHD protein server and our own trained neural networks are used in the amino acid type recognition. The results show that the predicted secondary structure information can help to improve the accuracy of the amino acid recognition.

Algorithms↗

PubMed1998

Conceptual integration of information databases into an Intranet.

Large information systems handle massive volume of data stored in heterogeneous sources of information. Each server has its own model of concepts representation with regard to its aims. One of the main problems encountered by end-users when accessing different servers is to match their own viewpoint on biomedical concepts with their various representations that are made in the database servers. The aim of the project ARIANE is to provide end-users with easy-to-use and natural means to access and query heterogeneous information databases. The objectives of this research work consist in building a conceptual interface by means of the Internet technology inside an enterprise Intranet, and to propose a method to realize it. Moreover, this method provides designers of web sites with a powerful tool to manage them on the basis of an ontology of the biomedical domain. This method is based on the knowledge sources provided by the Unified Medical Language System project of the U.S. National Library of Medicine and exploits intensively the conceptual graphs theory.

Computer Communication Networks↗