Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Intelligent Systems”

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 1,729 records · Page 96Linked to original sources

A prospective analysis of cognitive function and anticardiolipin antibodies in systemic lupus erythematosus.

OBJECTIVE: To prospectively analyze the association between changes in cognitive function and circulating anticardiolipin antibodies (aCL) over a period of 5 years in patients with systemic lupus erythematosus (SLE). METHODS: Cognitive function was assessed in 51 unselected female SLE patients at baseline and after a mean followup of 64.5 months (range 52-71 months), using standardized tests of cognitive function, i.e., the Wechsler Adult Intelligence Scale-Revised, the Wechsler Memory Scale-Revised, and the California Verbal Learning Test. Circulating IgG, IgA, and IgM aCL and anti-double-stranded DNA (anti-dsDNA) antibody levels were determined by enzyme-linked immunosorbent assay on 4-7 occasions over the same time period. Persistent antibody reactivity was defined as levels more than 2 standard deviations (moderately positive) and more than 5 standard deviations (highly positive) above the mean for normal controls over the duration of the study. Changes in overall cognitive performance and in raw scores on individual cognitive tests were compared in patients who were persistently positive or negative for aCL. RESULTS: At baseline 11 patients (22%) were cognitively impaired, compared with 7 (14%) at followup. Between 16% and 37% of patients had persistently elevated aCL levels of different isotypes. There was no significant difference in the prevalence of overall cognitive impairment in patients who were persistently positive for aCL compared with those who were not. In contrast, over the period of study, patients who had persistent IgG aCL positivity had a reduction in psychomotor speed, and patients who had persistent IgA aCL positivity had a reduction in conceptual reasoning and executive ability. Similar associations with anti-dsDNA antibodies were not found. CONCLUSION: These results suggest that IgG and IgA aCL may be responsible for long-term subtle deterioration in cognitive function in patients with SLE.

Adult↗

Expert system-controlled image display.

Conventional computer-based medical expert systems deliver advice to physicians as written text. While such advice is useful, it has distinct limitations in a visually oriented discipline such as diagnostic radiology, in which decisions often depend on pattern recognition and appreciation of subtle morphologic features. The authors developed a prototype expert computer system, IMAGE/ICON, which displays groups of images sorted into a series of axes based on different ways in which they may be similar. They may share a common feature, group of features, causes, or clinical setting. IMAGE/ICON may display examples of morphologic variations of a dominant finding or a spectrum of abnormalities seen in an specific disease or group of diseases. The system also assembles a written analysis of key features of a case. Such a tool may be useful as a diagnostic aid or for continuing medical education. It is likely to have particular impact in the form of an intelligent radiologic workstation, as picture archiving and communication systems become available.

Diagnosis, Computer-Assisted↗

A grid architecture for medical applications.

Grid technology can provide medical organisations with powerful tools through which they can gain coordinated access to computational resources that hitherto where inaccessible to them. This paper discusses how several classes of medical applications could benefit from the use of Grid technology. We concentrate on applications that were put forward by partners in the Dutch VL-e project. After describing the difficulties related to the realization of such applications without making use of the Grid, we describe an architecture that allows the applications to use Grid resources. We demonstrate how this architecture can be integrated into existing systems to provide flexible and transparent access to Grid services and show performance results of a test case.

Artificial Intelligence↗

A knowledge-based, concept-oriented view generation system for clinical data.

Information overload is a well-known problem for clinicians who must review large amounts of data in patient records. Concept-oriented views, which organize patient data around clinical concepts such as diagnostic strategies and therapeutic goals, may offer a solution to the problem of information overload. However, although concept-oriented views are desirable, they are difficult to create and maintain. We have developed a general-purpose, knowledge-based approach to the generation of concept-oriented views and have developed a system to test our approach. The system creates concept-oriented views through automated identification of relevant patient data. The knowledge in the system is represented by both a semantic network and rules. The key relevant data identification function is accomplished by a rule-based traversal of the semantic network. This paper focuses on the design and implementation of the system; an evaluation of the system is reported separately.

Artificial Intelligence↗

Bioinformatics integration and agent technology.

Vast amounts of life sciences data are scattered around the world in the form of a variety of heterogeneous data sources. The need to be able to co-relate relevant information is fundamental to increase the overall knowledge and understanding of a specific subject. Bioinformaticians aspire to find ways to integrate biological data sources for this purpose and system integration is a very important research topic. The purpose of this paper is to provide an overview of important integration issues that should be considered when designing a bioinformatics integration system. The currently prevailing approach for integration is presented with examples of bioinformatics information systems together with their main characteristics. Here, we introduce agent technology and we argue why it provides an appropriate solution for designing bioinformatics integration systems.

Algorithms↗

Waveguide model of the hearing aid earmold system.

BACKGROUND: The earmold system of the Behind-The-Ear hearing aid is an acoustic system that modifies the spectrum of the propagated sound waves. Improper selection of the earmold system may result in deterioration of sound quality and speech intelligibility. Computer modeling methods may be useful in the process of hearing aid fitting, allowing physician to examine various earmold system configurations and choose the optimum one for the hearing aid user. METHODS: In this paper, a computer model adequate for this task is proposed. This model is based on the waveguide modeling method. The waveguide model simulates the propagation of sound waves in the system of cylindrical tubes. Frequency response of the hearing aid receiver is simulated in the model and the influence of the ear canal and the eardrum on the earmold system is taken into account. The model parameters are easily calculated from parameters of a physical hearing aid system. Transfer function of the model is calculated and frequency response plots are obtained using the Matlab system. RESULTS: The frequency response plots of the earmold model were compared to the measurement plots of the corresponding physical earmold systems. The same changes in frequency responses caused by modification of length or diameter of a selected waveguide section, are observed in both measurement data of a real earmold system and in computed model responses. CONCLUSION: Comparison of model responses obtained for various sets of parameters with measurement data proved that the proposed model accurately simulates the real earmold system and the developed model may be used to construct a computer system assisting the physician who performs earmold system fitting.

Journal Article↗

Computer simulations of neural information processing and the schizophrenia-mania dichotomy.

Recent developments in artificial intelligence use computer simulations of complex neural systems to model associative memory and gestalt-seeking during cognition. Perturbations imposed on such computer simulations caused catastrophic breakdowns of neural functioning. The resulting cognitive disturbances assumed two forms, one "schizophreniclike" and the other "maniclike." The former was induced by memory overload and resulted in misperceptions, loose associations, and also parasitic processing states that pathologically controlled the flow of associations. The latter was caused by increased randomness of neural activity, which induced "jumps" from one gestalt to another. The relationship between this differential model of psychotic disturbances and other studies of schizophrenia and mania were explored.

Arousal↗

Speech intelligibility assessment in a helium environment.

The purpose of this study was to compare the appropriateness and effectiveness of the speech perception in noise (SPIN) test and the Griffiths version of the modified rhyme test (GMRT) in assessing Navy divers' speech understanding using communication systems containing different helium speech unscramblers (HSUs), one of which produces, by subjective observations, more intelligible output than the other. Divers participating in a saturation deep dive and a group of nondivers using digital audio tape recordings of the stimuli used by the divers were tested. Mean percent correct scores on the SPIN and GMRT lists within two listening conditions (taped, topside-diver and live-voice, diver-diver) were almost identical. Listeners scored better on both tests in the topside-diver condition than in the diver-diver condition. The majority of the SPIN errors were on low-predictability items that are void of context. Context clearly played a role in measuring the performance of these subjects, at least for the SPIN test. No significant differences were measured between the two HSUs, although a trend was seen favoring one HSU over the other for the divers. These results have theoretical as well as practical value for measuring the quality and intelligibility of helium speech enhancement systems.

Adult↗

Predicting minority students' success in medical school.

Despite recent attention to minority student recruitment and retention, data on predicting the success of minority medical students are scarce. Traditional predictors (college grades and scores on the Medical College Admission Test) have modest correlations with medical school grades and scores on the National Board of Medical Examiners examination for minority students. Nonetheless, admission committees also consider nontraditional variables when selecting minority students. Measures of nontraditional variables seem to assess types of intelligence not covered by traditional means. A system of organizing nontraditional or noncognitive variables into eight dimensions is proposed. The dimensions are self-concept, realistic, self-appraisal, understanding and dealing with racism, long-range goals, having a strong support person, showing leadership, having community involvement, and nontraditional knowledge acquired. Further, assessment should place more emphasis on recognizing and defining problems and on performance rather than knowledge. Combining traditional and nontraditional methods is best in selecting minority students, and sufficiently well developed measures exist in each area to make this a practical recommendation for any admission program.

Achievement↗

KBSIM/FLUIDTHERAPY: a system for optimized design of fluid resuscitation in trauma.

An application of the KBSIM (Knowledge-Based SIMulation) system to the improved design of fluid resuscitation is described. The system integrates knowledge from three domains, viz. the pathophysiology of traumatized patients represented in a quantitative biodynamic model, the heuristics of fluid resuscitation of such patients as represented in 'production rules', and some 'metaknowledge' reflected in the design of a multi-window user interface. This technique of combining numerical simulation with symbolic reasoning has obvious advantages during the design process and in training, by giving the user a possibility to evaluate his measures by direct feedback from the system. This feature of the system to assist in evaluation of alternative resuscitation procedures should also be useful as a means for decision support.

Artificial Intelligence↗

Neuro-immunophysiology of colon function.

Neuroimmunophysiology involves direct communication between the mucosal immune system and the minibrain in the colon. Communication is chemical in nature (paracrine) and involves specialized sensing functions of the immune cells for specific antigens together with intelligent interpretation of the signals by the enteric nervous system. Immunoneural integration progresses sequentially starting with immune detection followed by signal transfer to enteric microcircuits followed by neural interpretation and then selection of a specific neural program of coordinated mucosal secretion and motor propulsion that acts to clear the antigenic threat from the colonic lumen. Histamine and serotonin are important chemical messages released from mucosal mast cells to act at specific receptor subtypes on neural elements of the enteric minibrain.

Animals↗

OQAFMA Querying agent for the Foundational Model of Anatomy: a prototype for providing flexible and efficient access to large semantic networks.

The development of large semantic networks, such as the UMLS, which are intended to support a variety of applications, requires a flexible and efficient query interface for the extraction of information. Using one of the source vocabularies of UMLS as a test bed, we have developed such a prototype query interface. We first identify common classes of queries needed by applications that access these semantic networks. Next, we survey StruQL, an existing query language that we adopted, which supports all of these classes of queries. We then describe the OQAFMA Querying Agent for the Foundational Model of Anatomy (OQAFMA), which provides an efficient implementation of a subset of StruQL by pre-computing a variety of indices. We describe how OQAFMA leverages database optimization by converting StruQL queries to SQL. We evaluate the flexibility and efficiency of our implementation using English queries written by anatomists. This evaluation verifies that OQAFMA provides flexible, efficient access to one such large semantic network, the Foundational Model of Anatomy, and suggests that OQAFMA could be an efficient query interface to other large biomedical knowledge bases, such as the Unified Medical Language System.

Abstracting and Indexing↗

Perceptual development on the Rorschach.

The Rorschach was given to 60 school children in two designs: CA and MA orthogonal (9 and 12 years) and CA =MA (for 6, 9 and 12 years). Responses were scored for Form Accuracy, Complexity, Movement, and Friedman's Developmental Level (DL) Scoring System. There were significant MA effects independent of CA on Form Accuracy, Complexity and DL, and significant CA effects on Complexity and Movement. Form Accuracy was highly correlated with the DL score and correlated with MA at a slightly higher level than DL with MA. The Complexity score provided some additional information about development. Movement decreased with age but was higher in intelligent subjects. The results suggested that the DL system does assess MA independently of CA, but this is accounted for primarily by Form Accuracy.

Age Factors↗