PubMed Health⌕ Search

Biomedical subjects

C A Kulikowski

Publications and source records attributed to C A Kulikowski.

At least 19 recordsLinked to original sources
PubMed2002

The micro-macro spectrum of medical informatics challenges: from molecular medicine to transforming health care in a globalizing society.

BACKGROUND: Medical informatics has always encompassed a very broad spectrum of techniques for clinical and biomedical research, education and practice. There has been a concomitant variety of depth of specialization, ranging from the routine application of information processing methods to cutting-edge research on fundamental problems of computer-based systems and their relations to cognition and perception in biomedicine. OBJECTIVES: Challenges for the field can be placed in perspective by considering the scale of each--from the highly detailed scientific problems in bioinformatics and emerging molecular medicine to the broad and complex social problems of introducing medical informatics into web-related global settings. METHODS: The scale of an informatics problem is not only determined by the inherent physical space in which it exists, but also by the conceptual complexity that it involves, reinforcing the need to investigate the semantic web within which medical informatics is defined. RESULTS AND CONCLUSION: Bioinformatics, biomedical imaging and language understanding provide examples that anchor research and practice in biomedical informatics at the detailed, scientific end of the spectrum. Traditional concerns of medical informatics in the clinical arena make up the broad mid-range of the spectrum, while novel social interaction models of competition and cooperation will be needed to understand the implications of distributed health information technology for individual and societal change in an increasingly interconnected world.

Databases, Factual↗
PubMed2001

Biomedical image skeletonization: a novel method applied to fibrin network structures.

To understand the rheological behavior of fibrin clots, we must obtain quantitative measurements of morphometric parameters of the networks formed under various conditions. The networks are so complex that researchers must currently manually segment the images of network samples and estimate the parameters from them. Skeletonization is a promising tool for automating this task. We here propose a method that rapidly constructs a coarse representation of a skeleton graph and, using the snake model, deforms the graph to obtain smooth skeletons. Unlike many existing approaches, our method does not involve explicit object boundary information or high order derivatives. Since our method processes a given image as a whole, the presence of multiple objects in an image is automatically detected and the skeletons of these objects are computed simultaneously.

Algorithms↗
PubMed2001

Protein structural domain parsing by consensus reasoning over multiple knowledge sources and methods.

Domain parsing, or the detection of signals of protein structural domains from sequence data, is a complex and difficult problem. If carried out reliably it would be a powerful interpretive and predictive tool for genomic and proteomic studies. We report on a novel approach to domain parsing using consensus techniques based on Hidden Markov Models (HMMs) and BLAST searches built from a training set of 1471 continuous structural domains from the Dali Domain Dictionary (DDD). Validation on an independent test sample of family-matched structural domain sequences from the Scop database yields a consensus prediction performance rate of 75.5%, well above the 58% obtained by simple agreement of methods.

Algorithms↗
PubMed1998

Structural-functional bioinformatics: knowledge-based NMR interpretation.

This paper describes a knowledge-based approach to a problem of structural-functional bioinformatics, specifically the determination of protein structure through the automated analysis of NMR data. Highly successful results in carrying out sequence-specific assignments of residues from multidimensional NMR datasets has led us to automation of NOE dataset interpretation and a design for integrating these results with other protein structure and function analysis programs.

Computational Biology↗
PubMed1997

Automated analysis of protein NMR assignments using methods from artificial intelligence.

An expert system for determining resonance assignments from NMR spectra of proteins is described. Given the amino acid sequence, a two-dimensional 15N-1H heteronuclear correlation spectrum and seven to eight three-dimensional triple-resonance NMR spectra for seven proteins, AUTOASSIGN obtained an average of 98% of sequence-specific spin-system assignments with an error rate of less than 0.5%. Execution times on a Sparc 10 workstation varied from 16 seconds for smaller proteins with simple spectra to one to nine minutes for medium size proteins exhibiting numerous extra spin systems attributed to conformational isomerization. AUTOASSIGN combines symbolic constraint satisfaction methods with a domain-specific knowledge base to exploit the logical structure of the sequential assignment problem, the specific features of the various NMR experiments, and the expected chemical shift frequencies of different amino acids. The current implementation specializes in the analysis of data derived from the most sensitive of the currently available triple-resonance experiments. Potential extensions of the system for analysis of additional types of protein NMR data are also discussed.

Automation↗
PubMed1995

Knowledge-based medical image analysis and representation for integrating content definition with the radiological report.

Technology breakthroughs in high-speed, high-capacity, and high performance desk-top computers and workstations make the possibility of integrating multimedia medical data to better support clinical decision making, computer-aided education, and research not only attractive, but feasible. To systematically evaluate results from increasingly automated image segmentation it is necessary to correlate them with the expert judgments of radiologists and other clinical specialists interpreting the images. These are contained in increasingly computerized radiological reports and other related clinical records. But to make automated comparison feasible it is necessary to first ensure compatibility of the knowledge content of images with the descriptions contained in these records. Enough common vocabulary, language, and knowledge representation components must be represented on the computer, followed by automated extraction of image-content descriptions from the text, which can then be matched to the results of automated image segmentation. A knowledge-based approach to image segmentation is essential to obtain the structured image descriptions needed for matching against the expert's descriptions. We have developed a new approach to medical image analysis which helps generate such descriptions: a knowledge-based object-centered hierarchical planning method for automatically composing the image analysis processes. The problem-solving steps of specialists are represented at the knowledge level in terms of goals, tasks, and domain objects and concepts separately from the implementation level for specific representations of different image types, and generic analysis methods. This system can serve as a major functional component in incrementally building and updating a structured and integrated hybrid information system of patient data.(ABSTRACT TRUNCATED AT 250 WORDS)

Artificial Intelligence↗
PubMed1993

A constraint reasoning system for automating sequence-specific resonance assignments from multidimensional protein NMR spectra.

AUTOASSIGN is a prototype expert system designed to aid in the determination of protein structure from nuclear magnetic resonance (NMR) measurements. In this paper we focus on one of the key steps of this process, the assignment of the observed NMR signals to specific atomic nuclei in the protein; i.e. the determination of sequence-specific resonance assignments. Recently developed triple-resonance (1H, 15N, and 13C) NMR experiments [Montelione et al., 1992] have provided an important breakthrough in this field, as the resulting data are more amenable to automated analysis than data sets generated using conventional strategies [Wuethrich, 1986]. The "assignment problem" can be stated as a constraint satisfaction problem (CSP) with some added complexities. There is very little internal structure to the problem, making it difficult to apply subgoaling and problem decomposition. Moreover, the data used to generate the constraints are incomplete, non-unique, and noisy, and constraints emerge dynamically as analysis progresses. The traditional inference engine is replaced by a set of very tightly-coupled modules which enforce extensive constraint propagation, with state information distributed over the objects whose relationships are being constrained. AUTOASSIGN provides correct and nearly complete resonance assignments with both simulated and real 3D triple-resonance data for a 72 amino acid protein.

Amino Acids↗
PubMed1991

Automatic generation of plans for biomedical image interpretation.

This paper presents a new object-centered, goal-driven planning approach to biomedical image interpretation. We describe here a prototype system which takes advantage of spatial and detectability constraints from an expert-derived model of expected anatomical structures to automatically generate plans for the interpretation of multimodality images.

Artificial Intelligence↗
PubMed1989

An artificial-intelligence technique for qualitatively deriving enzyme kinetic mechanisms from initial-velocity measurements and its application to hexokinase.

We have developed a computer method based on artificial-intelligence techniques for qualitatively analysing steady-state initial-velocity enzyme kinetic data. We have applied our system to experiments on hexokinase from a variety of sources: yeast, ascites and muscle. Our system accepts qualitative stylized descriptions of experimental data, infers constraints from the observed data behaviour and then compares the experimentally inferred constraints with corresponding theoretical model-based constraints. It is desirable to have large data sets which include the results of a variety of experiments. Human intervention is needed to interpret non-kinetic information, differences in conditions, etc. Different strategies were used by the several experimenters whose data was studied to formulate mechanisms for their enzyme preparations, including different methods (product inhibitors or alternate substrates), different experimental protocols (monitoring enzyme activity differently), or different experimental conditions (temperature, pH or ionic strength). The different ordered and rapid-equilibrium mechanisms proposed by these experimenters were generally consistent with their data. On comparing the constraints derived from the several experimental data sets, they are found to be in much less disagreement than the mechanisms published, and some of the disagreement can be ascribed to different experimental conditions (especially ionic strength).

Adenosine Triphosphate↗
PubMed1988

Theory formation in postulating enzyme kinetic mechanisms: reasoning with constraints.

This paper reports on a prototype system for modeling and analyzing the expert reasoning involved in postulating enzyme kinetic mechanisms. It involves data-driven, theory-driven, and analogical components of reasoning within a generate-and-test cycle. Its central component is a set of domain-specific "filters" for matching experimentally and theoretically derived constraints. The input to the system consists of an abstracted qualitative description of an experiment and prior knowledge reported in the literature. Its output shows how the results match those expected for a set of postulated reaction mechanism models and also provides a trace of which features do or do not match each of the candidate topological models. Results, constraints, and models are all analyzed and compared to those from other, similar experiments. We deduced rules for interpreting the qualitative features of enzyme kinetic experiments from natural language descriptions in the literature and verified that the rules were correct by predicting the results for typical mechanisms. We obtained the correct behavior for all 37 states of a complex enzyme mechanism involving three substrates and three products. We tested our system on data from several published reports dealing with the enzyme hexokinase and obtained detailed listings of the differences in conclusions and interpretation reported in several journal articles. This system, which provides qualitative representations of enzyme kinetic results, should facilitate further experimentation on theory formation in enzyme kinetics and lead to more efficient experimental designs.

Artificial Intelligence↗
PubMed1987

Modeling and artificial intelligence approaches to enzyme systems.

Modeling is a means of formulating and testing complex hypotheses. Useful modeling is now possible with biological laboratory microcomputers with which experimenters feel comfortable. Artificial intelligence (AI) is sufficiently similar to modeling that AI techniques, now becoming usable on microcomputers, are applicable to modeling. Microcomputer and AI applications to physiological system studies with multienzyme models and with kinetic models of isolated enzymes are described. Using an IBM PC microcomputer, we have been able to fit kinetic enzyme models; to extend this process to design kinetic experiments by determining the optimal conditions; and to construct an enzyme (hexokinase) kinetics data base. We have also used a PC to do most of the constructing of complex multienzyme models, initially with small simple BASIC programs; alternative methods with standard spreadsheet or data base programs have been defined. Formulating and solving differential equations in appropriate representational languages, and sensitivity analysis, are soon likely to be feasible with PCs. Much of the modeling process can be stated in terms of AI expert systems, using sets of rules for fitting and evaluating models and designing further experiments. AI techniques also permit critiquing and evaluating the data, experiments, and hypotheses being modeled, and can be extended to supervise the calculations involved.

Artificial Intelligence↗
PubMed1984

An expert consultation system for frontline health workers in primary eye care.

In developing countries, blindness is a major health problem whose control depends on the application of simple measures by frontline workers because, in many of these countries, specialist medical care is not readily available. To assist primary health workers in the management of common and potentially blinding eye disorders, we have developed a prototype computer program for a hand-held computer that incorporates a set of guidelines for diagnosis and treatment. This eye treatment program will help evaluate the potential of such devices for improving health care delivery in developing countries. This approach is now feasible because of recent advances in expert system and portable computer technology.

Blindness↗
PubMed1984

Therapy selection in an expert medical consultation system for ocular herpes simplex.

This paper describes a general scheme for selecting therapies which can be used in expert medical consultation systems. The scheme consists of a topological sorting procedure within a general production rule representation. The procedure is used to choose among competing therapies on the basis of precedence rules. This approach provides a natural way in which therapy choices can be automatically explained. The precedence rule has the capability to summarize a great many facts elegantly and to insure that the conclusions reached will be mutually exclusive. Precedence rules are computationally more efficient in both storage and time than an equivalent set of production rules. As the number of competing therapies increases this computational advantage increases. An expert consultation system for diagnosis and therapy planning of ocular herpes simplex has been implemented using this approach and examples of the system's output on actual cases of this disease are given.

Antiviral Agents↗
PubMed1983

Expert medical consultation systems.

Expert medical consultation systems have come of age in the last 5 years. There has been considerable progress in developing new and powerful representations for medical knowledge, microprocessor- and instrument-related expert systems, methods for knowledge acquisition and learning, and more sophisticated techniques of reasoning, explanation, and evaluation.

Computers↗
PubMed1982

Knowledge-based acquisition of rules for medical diagnosis.

Medical consultation systems in the EXPERT framework contain rules written under the guidance of expert physicians. We present a methodology and preliminary implementation of a system that learns compiled rule chains from positive case examples of a diagnostic class and negative examples of alternative diagnostic classes. Rule acquisition is guided by the constraints of physiological process models represented in the system. Evaluation of the system is proceeding in the area of glaucoma diagnosis, and an example of an experiment in this domain is included.

Diagnosis, Computer-Assisted↗