SEARCH · PubMed Health

Results for “Knowledge base”

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 325 records · Page 18Linked to original sources

PubMed1999

Discourse structures in medical reports--watch out! The generation of referentially coherent and valid text knowledge bases in the MEDSYNDIKATE system.

The automatic analysis of medical narratives currently suffers from neglecting text structure phenomena such as referential relations between discourse units. This has unwarranted effects on the descriptional adequacy of medical knowledge bases automatically generated from texts. The resulting representation bias can be characterized in terms of incomplete, artificially fragmented and referentially invalid knowledge structures. We focus here on four basic types of textual reference relations, viz. pronominal and nominal anaphora, textual ellipsis and metonymy and show how to deal with them in an adequate text parsing device. Since the types of reference relations we discuss show an increasing dependence on conceptual background knowledge, we stress the need for formally grounded, expressive conceptual representation systems for medical knowledge. Our suggestions are based on experience with MEDSYNDIKATE, a medical text knowledge acquisition system designed to properly deal with various sorts of discourse structure phenomena.

Artificial Intelligence↗

PubMed2005

A new explanatory model of an SIR disease epidemic: a knowledge-based, probabilistic approach to epidemic analysis.

A new explanatory model for epidemic analysis is presented; it has a knowledge based component and a probabilistic computational component. The former assembles details of household characteristics, social networks and connectivity in the community--'knowledge'--which is used to determine the structure of the computational component. The latter links individuals and households through statistically-defined opportunities for contacts and, by repeated trials, determines an average longitudinal time course (epidemic curve) of the simulated infection as it spreads through the community from inception to extinction of the epidemic. The model thus aims to describe the epidemic itself, rather than any abstraction of it. In application to a 1955-56, self-contained epidemic of an SIR disease, variola minor, the model generates 1 dominant longitudinal pattern that matches closely the epidemic curve of observed daily case rates; it is suggested that other patterns indicate different ways in which the epidemic might have evolved. The model can be used to show how differing community characteristics would affect the simulated epidemic.

Brazil↗

PubMed2006

Energetics and stability of transmembrane helix packing: a replica-exchange simulation with a knowledge-based membrane potential.

The energetics and stability of the packing of transmembrane helices were investigated by Monte Carlo simulations with the replica-exchange method. The helices were modeled with a united atom representation, and the CHARMM19 force field was employed. Based on known experimental structures of membrane proteins, an implicit knowledge-based potential was developed to describe the helix-membrane interactions at the residue level, whose validity was tested through prediction of the orientations when single helices were inserted into a membrane. Two systems were studied in this article, namely the glycophorin A dimer, and helices A and B of Bacteriorhodopsin. For the glycophorin A dimer, the most stable structure (0.5 A away from the experimental structure) is mainly stabilized by the favorable helix-helix interactions, and has the most population regardless of the helix-membrane interaction. However, for helices A and B of Bacteriorhodopsin, it was found that the packing determined by helix-helix interactions is nonspecific, and a native-like structure (0.2 A from the experimental one) can be identified from several structural analogs as the most stable one only after applying the membrane potential. Our results suggest that the contribution from the helix-membrane interaction could be critical in the correct packing of transmembrane helices in the membrane.

Computer Simulation↗

PubMed2004

Protein sequence randomization: efficient estimation of protein stability using knowledge-based potentials.

Modifications of the amino acid sequence generally affect protein stability. Here, we use knowledge-based potentials to estimate the stability of protein structures under sequence variation. Calculations on a variety of protein scaffolds result in a clear distinction of known mutable regions from arbitrarily chosen control patches. For example, randomly changing the sequence of an antibody paratope yields a significantly lower number of destabilized mutants as compared to the randomization of comparable regions on the protein surface. The technique is computationally efficient and can be used to screen protein structures for regions that are amenable to molecular tinkering by preserving the stability of the mutated proteins.

Amino Acid Sequence↗

PubMed2003

A prototype natural language interface to a large complex knowledge base, the Foundational Model of Anatomy.

We describe a constrained natural language interface to a large knowledge base, the Foundational Model of Anatomy (FMA). The interface, called GAPP, handles simple or nested questions that can be parsed to the form, subject-relation-object, where subject or object is unknown. With the aid of domain-specific dictionaries the parsed sentence is converted to queries in the StruQL graph-searching query language, then sent to a server we developed, called OQAFMA, that queries the FMA and returns output as XML. Preliminary evaluation shows that GAPP has the potential to be used in the evaluation of the FMA by domain experts in anatomy.

Anatomy↗

PubMed1990

BRAINDEX: an interactive, knowledge-based system supporting brain death diagnosis.

BRAINDEX (Brain-Death Expert System) is an interactive, knowledge-based expert system offering support to physicians in decision making concerning brain death. The physician is given the possibility of communicating in almost natural language and, therefore, in terms with which he is familiar. This updated version of the system is implemented on an IBM-PC/AT with the expert system shell PC-PLUS and consists of about 430 rules. The determination of brain death is realized with backward chaining and for the optional coma-scaling a forward-chaining mechanism is used.

Brain Death↗

PubMed1990

A combined data- and knowledge base system for the interpretation of metabolic investigations of erythrocytes from hemolytic and polycythemic patients.

A knowledge based-information system has been constructed to facilitate and standardize the interpretation of data obtained from specialized analyses in laboratory medicine. For illustration the system was applied to metabolic studies of erythrocytes from patients in whom hereditary disorders are suspected to explain the presence of a hemolytic anemia or polycythemia. The study includes assay of the catalytic activity of ten different enzymes and the concentration of some key metabolites. The knowledge based system is an excellent tool for documentation, updating and transfer of knowledge about the interpretative process. This will reduce the risk that changes in this process are made without sound motivation and documentation. Furthermore, the statistical and graphic features of the system provide data for long-term quality assessment and insights into reference sample groups which are used to update decision limits. A few cases are used to illustrate the advantages of the system.

Anemia, Hemolytic↗

PubMed1994

Knowledge-based temporal abstraction for diabetic monitoring.

We have developed a general method that solves the task of creating abstract, interval-based concepts from time-stamped clinical data. We refer to this method as knowledge-based temporal-abstraction (KBTA). In this paper, we focus on the knowledge representation, acquisition, maintenance, reuse and sharing aspects of the KBTA method. We describe five problem-solving mechanisms that solve the five subtasks into which the KBTA method decomposes its task, and four types of knowledge necessary for instantiating these mechanisms in a particular domain. We present an example of instantiating the KBTA method in the clinical area of monitoring insulin-dependent-diabetes patients.

Artificial Intelligence↗

PubMed2005

Minimalist knowledge representation of primary care diseases in the medrapid.info knowledge base.

BACKGROUND: Communication media commonly used in medicine today no longer meet the needs brought on by the present knowledge explosion. The Heidelberg medrapid project has been developed to quickly communicate high-quality clinical knowledge to physicians. METHODS: In this paper, medrapid is introduced as an online clinical knowledge resource, and the methods used by the 'knowledge entry' function for the minimalist representation of clinical knowledge in the knowledge base are discussed. RESULTS: On average, fewer than 1.4 problems per disease arose during the input of the formal representation of clinical knowledge using the 'knowledge entry' function. However, representation of disease time processes, descriptions, warnings and graphics with the 'knowledge entry' function remains problematic. CONCLUSIONS: The 'knowledge entry' function allows fast formal representation of clinical knowledge (<14 minutes per disease) and testing using the integrated quality management system. In the near future, new measures must be found to improve the problematic representation of disease time processes, descriptions, warnings and graphics to formally represent clinical knowledge using the medrapid 'knowledge entry' function.

Germany↗

PubMed2007

A knowledge-based move set for protein folding.

The free energy landscape of protein folding is rugged, occasionally characterized by compact, intermediate states of low free energy. In computational folding, this landscape leads to trapped, compact states with incorrect secondary structure. We devised a residue-specific, protein backbone move set for efficient sampling of protein-like conformations in computational folding simulations. The move set is based on the selection of a small set of backbone dihedral angles, derived from clustering dihedral angles sampled from experimental structures. We show in both simulated annealing and replica exchange Monte Carlo (REMC) simulations that the knowledge-based move set, when compared with a conventional move set, shows statistically significant improved ability at overcoming kinetic barriers, reaching deeper energy minima, and achieving correspondingly lower RMSDs to native structures. The new move set is also more efficient, being able to reach low energy states considerably faster. Use of this move set in determining the energy minimum state and for calculating thermodynamic quantities is discussed.

Glycine↗

PubMed2002

Discriminative ability with respect to amino acid types: assessing the performance of knowledge-based potentials without threading.

We present a novel method designed to analyze the discriminative ability of knowledge-based potentials with respect to the 20 residue types. The method is based on the preference of amino acids for specific types of protein environment, and uses a virtual mutagenesis experiment to estimate how much information a given potential can provide about environments of each amino acid type. This allows one to test and optimize the performance of real potentials at the level of individual amino acids, using actual data on residue environments from a dataset of known protein structures. We have applied our method to long-range and medium-range pairwise distance-dependent potentials. The results of our study indicate that these potentials are only able to discriminate between a very limited number of residue types, and that discriminative ability is extremely sensitive to the choice of parameters used to construct the potentials, and even to the size of the training dataset. We also show that different types of pairwise distance potentials are dominated by different types of interactions. These dominant interactions strongly depend on the type of approximation used to define residue position. For each potential, our methodology is able to identify a potential-specific amino acid distance matrix and a reduced amino acid alphabet of any specified size, which may have implications for sequence alignment and multibody models.

Amino Acid Substitution↗

PubMed2000

Knowledge-based scoring function to predict protein-ligand interactions.

The development and validation of a new knowledge-based scoring function (DrugScore) to describe the binding geometry of ligands in proteins is presented. It discriminates efficiently between well-docked ligand binding modes (root-mean-square deviation <2.0 A with respect to a crystallographically determined reference complex) and those largely deviating from the native structure, e.g. generated by computer docking programs. Structural information is extracted from crystallographically determined protein-ligand complexes using ReLiBase and converted into distance-dependent pair-preferences and solvent-accessible surface (SAS) dependent singlet preferences for protein and ligand atoms. Definition of an appropriate reference state and accounting for inaccuracies inherently present in experimental data is required to achieve good predictive power. The sum of the pair preferences and the singlet preferences is calculated based on the 3D structure of protein-ligand binding modes generated by docking tools. For two test sets of 91 and 68 protein-ligand complexes, taken from the Protein Data Bank (PDB), the calculated score recognizes poses generated by FlexX deviating <2 A from the crystal structure on rank 1 in three quarters of all possible cases. Compared to FlexX, this is a substantial improvement. For ligand geometries generated by DOCK, DrugScore is superior to the "chemical scoring" implemented into this tool, while comparable results are obtained using the "energy scoring" in DOCK. None of the presently known scoring functions achieves comparable power to extract binding modes in agreement with experiment. It is fast to compute, regards implicitly solvation and entropy contributions and produces correctly the geometry of directional interactions. Small deviations in the 3D structure are tolerated and, since only contacts to non-hydrogen atoms are regarded, it is independent from assumptions of protonation states.

Artificial Intelligence↗

PubMed1991

Knowledge-based system for the three-dimensional reconstruction of blood vessels from two angiographic projections.

A knowledge-based system for the three-dimensional reconstruction of blood vessels from wide-angle coronary and stereoscopic cerebral angiographic projections is developed. For the reconstruction of the coronary vessels, the left coronary artery (LCA) is automatically labelled on standard RAO and LAO projections, using anatomical models of the LCA. The labelling system succeeds in giving the most important coronary arteries a correct anatomical label. These labelling results enable us to find corresponding segments in both images. In the case of the reconstruction of the cerebral vessels however, such an anatomical model is clearly unavailable. To find corresponding segments, small-angle projections must be relied on, resulting in very similar images. Owing to the small angular separation between both projections, the three-dimensional reconstruction will be less accurate. Once the corresponding segments in both projections are obtained, the three-dimensional artery trajectory is reconstructed with dynamic programming techniques. The three-dimensional reconstructed coronary vessels are also used for an automatic quantification of stenotic lesions.

Blood Vessels↗

PubMed2006

Automatic adjustment of pressure support by a computer-driven knowledge-based system during noninvasive ventilation: a feasibility study.

OBJECTIVE: To evaluate the feasibility of using a knowledge-based system designed to automatically titrate pressure support (PS) to maintain the patient in a "respiratory comfort zone" during noninvasive ventilation (NIV) in patients with acute respiratory failure. DESIGN AND SETTING: Prospective crossover interventional study in an intensive care unit of a university hospital. PATIENTS: Twenty patients. INTERVENTIONS: After initial NIV setting and startup in conventional PS by the chest physiotherapist NIV was continued for 45 min with the automated PS activated. MEASUREMENTS AND RESULTS: During automated PS minute-volume was maintained constant while respiratory rate decreased significantly from its pre-NIV value (20+/-3 vs. 25+/-3 bpm). There was a trend towards a progressive lowering of dyspnea. In hypercapnic patients PaCO(2) decreased significantly from 61+/-9 to 51+/-2 mmHg, and pH increased significantly from 7.31+/-0.05 to 7.35+/-0.03. Automated PS was well tolerated. Two system malfunctions occurred prompting physiotherapist intervention. CONCLUSIONS: The results of this feasibility study suggest that the system can be used during NIV in patients with acute respiratory failure. Further studies should now determine whether it can improve patient-ventilator interaction and reduce caregiver workload.

Aged↗

PubMed1995

[An approach for planning hospital menus using a knowledge-based system].

Menu planning in hospitals is a complex decision problem. Patients expect the menu plan to be healthful and in accordance with their nutritional habits. Furthermore, the menu plan must conform to capacity limits of the kitchen. In this paper we present an approach to computerized food selection and menu composition. The model is based on nutritional knowledge, which is represented in the computer and used for problem solving.

Artificial Intelligence↗

PubMed1991

A structured visual language for a knowledge-based front-end to statistical analysis systems in biomedical research.

Within the last few years, several knowledge-based systems for statistical analysis systems have been proposed (see Refs. 1-4 for references). Most of these systems provide so-called 'natural-language' interfaces for acquisition and application of meta-data. Since graphics have been very efficient in displaying results (e.g., as scatter, QQ and residual plots), some attempts have been made (cf. Refs. 5,6) to use graphics also to display knowledge of the statistical strategy. In the present paper I will concentrate on the visualization of knowledge of the experimental design and its impacts on the design of a structured visual syntax language for acquisition and application of this knowledge in the field of biomedical research.

Artificial Intelligence↗

PubMed2001

Automatic segmentation of cardiac magnetic resonance images using knowledge base.

OBJECTIVE: To study the automated implementation of cardiac magnetic resonance image (MRI) segmentation. METHODS: By training the feature parameters of the images and establishing a knowledge base, an efficient method for extracting and using prior knowledge was proposed. RESULTS and CONCLUSION: Through extracting and using prior knowledge of cardiac MRI, automation of cardiac MRI segmentation can be well accomplished.

Journal Article↗

PubMed1999

Knowledge-based tensor anisotropic diffusion of cardiac magnetic resonance images.

We present a general formulation for a new knowledge-based approach to anisotropic diffusion of multi-valued and multi-dimensional images, with an illustrative application for the enhancement and segmentation of cardiac magnetic resonance (MR) images. In the proposed method all available information is incorporated through a new definition of the conductance function which differs from previous approaches in two aspects. First, we model the conductance as an explicit function of time and position, and not only of the differential structure of the image data. Inherent properties of the system (such as geometrical features or non-homogeneous data sampling) can therefore be taken into account by allowing the conductance function to vary depending on the location in the spatial and temporal coordinate space. Secondly, by defining the conductance as a second-rank tensor, the non-homogeneous diffusion equation gains a truly anisotropic character which is essential to emulate and handle certain aspects of complex data systems. The method presented is suitable for image enhancement and segmentation of single- or multi-valued images. We demonstrate the efficiency of the proposed framework by applying it to anatomical and velocity-encoded cine volumetric (4-D) MR images of the left ventricle. Spatial and temporal a priori knowledge about the shape and dynamics of the heart is incorporated into the diffusion process. We compare our results to those obtained with other diffusion schemes and exhibit the improvement in regions of the image with low contrast and low signal-to-noise ratio.

Algorithms↗