SEARCH · Search PubMed
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.
The goal of intelligent alarms is not only to recognize potentially dangerous situations, but to discriminate whether the condition is truly threatening or has resulted from nonthreatening causes, such as artifacts. The authors describe a knowledge-based approach in the development of intelligent alarms, using complex guidelines that simulate human reasoning and follow "if, then" rules of problem solving.
Intensive care units become more complicated each day as the number of devices developed to monitor various aspects of a patient's status continues to increase. Intelligent monitors attempt to reduce this complexity by interpreting the data and presenting a high level summary to the clinician. We propose an innovative parallel software architecture for constructing intelligent medical monitors: the process trellis. The process trellis is an explicitly parallel structure, and therefore can take advantage of the performance gains available from parallel computing hardware. It does not, however, presuppose any expertise in parallel programming on the part of the application programmer. A prototype cardiovascular monitor has been built using this parallel software architecture. Preliminary testing of the monitor has shown that real-time cardiovascular monitoring, including data calculations, symbolic classification, and interpretation can be accomplished in real-time.
This study was conducted to evaluate the effect of an intelligent seat system, a microprocessor-based interactive seat that automatically adjusts itself to fit a seated individual by making pressure-sensitive adjustments on its own. First, a standard American automobile seat ('baseline' seat) was assessed for comfort. Subjective ratings of comfort, pressure distribution and seated anthropometric measurements were recorded for 20 test subjects. These measurements were recorded while the subjects maintained a simulated driving position in a seat buck. The comfort scale was based on a rating of 1 to 10, with 1 corresponding to 'very poor' and 10 corresponding to 'very good.' Based on a nonlinear, multiple regression model that had been previously developed, the comfort rating of the seat was predicted based on the subjective ratings and the recorded values of 450 pressure measurements from 20 subjects. The predicted comfort value was 7.46 for the baseline seat. Following the baseline assessment, the intelligent seat system was installed into the standard American automobile seat. The objective and subjective assessments were then repeated for 17 subjects and the new predicted comfort rating was 8.06. A t-test performed on the subjective and objective measures indicated that this was a significant improvement in seat comfort. Overall, subjects felt the self-adjusting seat was more customized and more comfortable, providing a better fit.
A rule-based computer system was developed to perform clinical decision-making support within a medical information system, oncology practice, and clinical research. This rule-based system, which has been programmed using deterministic rules, possesses features of generalizability, modularity of structure, convenience in rule acquisition, explanability, and utility for patient care and teaching, features which have been identified as advantages of artificial intelligence (AI) rule-based systems. Formal rules are primarily represented as conditional statements; common conditions and actions are stored in system dictionaries so that they can be recalled at any time to form new decision rules. Important similarities and differences exist in the structure of this system and clinical computer systems utilizing artificial intelligence (AI) production rule techniques. The non-AI rule-based system possesses advantages in cost and ease of implementation. The degree to which significant medical decision problems can be solved by this technique remains uncertain as does whether the more complex AI methodologies will be required.
This paper describes a methodology for using the knowledge in existing health care text corpora to prime intelligent split menus for provider data-entry. A split menu is one where the top portion of a menu list is organized by user-selection frequency and the bottom portion of the list is traditionally organized in alphabetical order. A simulation shows that data-entry with these intelligent split menus requires between two and five times less effort (in terms of user selections or mouse clicks) than menus arranged alphabetically. This paper uses a corpus from echocardiography to develop the simulation. The methodology uses statistical associations between word categories in the corpus such as 'anatomy' or 'pathology' to prime the frequency ordering of the menus. A dictionary of terms contains the categorical information. After the initial priming, actual user selections are used to update the frequencies used to adapt to providers' individual data-entry patterns.
American firms want 'total quality'. The time and money spent by U.S. companies attempting to qualify for the coveted Baldrige Award exemplifies corporate America's desire to achieve new quality standards. Corporate intelligence and 'total quality' are inextricably linked. In this article, the authors demonstrate how shared and properly-used information can be a powerful tool for elevating quality standards, and how corporate intelligence programmes can provide the information links vital for success in attaining the highest standards of quality.
There is considerable controversy over whether nutrition in early life has a long-term influence on neurodevelopment. We have shown previously that, in preterm infants, mother's choice to provide breast milk was associated with higher developmental scores at 18 months. We now report data on intelligence quotient (IQ) in the same children seen at 7 1/2-8 years. IQ was assessed in 300 children with an abbreviated version of the Weschler Intelligence Scale for Children (revised Anglicised). Children who had consumed mother's milk in the early weeks of life had a significantly higher IQ at 7 1/2-8 years than did those who received no maternal milk. An 8.3 point advantage (over half a standard deviation) in IQ remained even after adjustment for differences between groups in mother's education and social class (p less than 0.0001). This advantage was associated with being fed mother's milk by tube rather than with the process of breastfeeding. There was a dose-response relation between the proportion of mother's milk in the diet and subsequent IQ. Children whose mothers chose to provide milk but failed to do so had the same IQ as those whose mothers elected not to provide breast milk. Although these results could be explained by differences between groups in parenting skills or genetic potential (even after adjustment for social and educational factors), our data point to a beneficial effect of human milk on neurodevelopment.
OBJECTIVE: As an aid to discrimination of sufferers with back pain an artificial intelligence neural network was constructed to differentiate paraspinal power spectra. DESIGN: Clinical investigation using surface electromyography. METHOD: The surface electromyogram power spectra from 60 subjects, 33 non-back-pain sufferers and 27 chronic back pain sufferers were used to construct a back propagation neural network that was then tested. Subjects were placed on a test frame in 30 degrees of lumbar forward flexion. An isometric load of two-thirds maximum voluntary contraction was held constant for 30 s whilst surface electromyograms were recorded at the level of the L(4-5). Paraspinal power spectra were calculated and loaded into the input layer of a three-layer back propagation network. The neural network classified the spectra into normal or back pain type. RESULTS: The back propagation neural was shown to have satisfactory convergence with a specificity of 79% and a sensitivity of 80%. CONCLUSIONS: Artificial intelligence neural networks appear to be a useful method of differentiating paraspinal power spectra in back-pain sufferers.
The project we describe here is aimed at assisting out-patients affected by Insulin Dependent Diabetes Mellitus. Our approach exploits the usual scheme of diabetic patients management, based on (i) a periodic evaluation of patients' metabolic control performed by the physician, and (ii) patient-tailored tables for self-adjustments of insulin dosages. Following this scheme we have defined a system built on a two-level architecture. The High Level Module exploits both medical knowledge and clinical information in order to assess an insulin protocol, defined in terms of insulin timing, type, and total amount. The High Level Module exchanges information with the Low Level Module in order to define the control actions to be taken at the low level, as well as to periodically evaluate protocol adequacy on the basis of patient data. The goal of the Low Level Module, whose characteristics can be adaptively modified by the High Level Module, is to suggest the next insulin dosage, depending on the actual blood glucose measurement and a certain pre-defined insulin delivery protocol. The Level Control Module is based on an adaptive controller, consisting of a Fuzzy Set Controller and an ARX (Autoregressive eXogenous input) Model. The scheme here presented may be conveniently viewed in a telemedicine context, in which the low level controller is implemented on a portable device communicating to the high level controller, implemented on a remote computer. A preliminary assessment has been performed, analyzing a data set of 60 patients provided by the American Association of Artificial Intelligence, Artificial Intelligence in Medicine Subgroup, and the implementation of the system is currently in progress.
Intelligent polymers, also referred as "stimuli-responsive polymers" undergo strong property changes (in shape, surface characteristics, solubility, etc.) when only small changes in their environment (changes in temperature, pH, ionic strength light, electrical and magnetic field, etc.). They have been used in several novel applications, drug delivery systems, tissue engineering scaffolds, bioseparation, biomimetic actuators, etc. The most popular member of these type of polymers is poly(N-isopropylacrylamide) (poly(NIPA)) which exhibits temperature-sensitive character, in which the polymer chains change from water-soluble coils to water-insoluble globules in aqueous solution as temperature increases above the lower critical solution temperature (LCST) of the polymer. Copolymerization of NIPA with acrylic acid (AAc) allows the synthesis of both pH and temperature-responsive copolymers. This paper summarizes some of our related studies in which NIPA and its copolymers were synthesized and used as intelligent carriers in diverse applications.
Artificial intelligence techniques of neural network and fuzzy systems were applied as alternative methods to determine beach litter grading, based on litter surveys of the Antalya coastline (the Turkish Riviera). Litter measurements were categorized and assessed by artificial intelligence techniques, which lead to a new litter categorization system. The constructed neural network satisfactorily predicted the grading of the Antalya beaches and litter categories based on the number of litter items in the general litter category. It has been concluded that, neural networks could be used for high-speed predictions of litter items and beach grading, when the characteristics of the main litter category was determined by field studies. This can save on field effort when fast and reliable estimations of litter categories are required for management or research studies of beaches--especially those concerned with health and safety, and it has economic implications. The main advantages in using fuzzy systems are that they consider linguistic adjectival definitions, e.g. many/few, etc. As a result, additional information inherent in linguistic comments/refinements and judgments made during field studies can be incorporated in grading systems.
Bacteria have developed intricate communication capabilities (e.g. quorum-sensing, chemotactic signaling and plasmid exchange) to cooperatively self-organize into highly structured colonies with elevated environmental adaptability. We propose that bacteria use their intracellular flexibility, involving signal transduction networks and genomic plasticity, to collectively maintain linguistic communication: self and shared interpretations of chemical cues, exchange of chemical messages (semantic) and dialogues (pragmatic). Meaning-based communication permits colonial identity, intentional behavior (e.g. pheromone-based courtship for mating), purposeful alteration of colony structure (e.g. formation of fruiting bodies), decision-making (e.g. to sporulate) and the recognition and identification of other colonies - features we might begin to associate with a bacterial social intelligence. Such a social intelligence, should it exist, would require going beyond communication to encompass unknown additional intracellular processes to generate inheritable colonial memory and commonly shared genomic context.
Over the past 4 years our group has developed a prototype intelligent system which applies captured expert knowledge to support clinical decision-making during labour. This chapter presents a review of the system and the progress made to date. The system classifies the same features from the CTG as experienced clinicians using numerical algorithms and a small neural network. This hybrid approach has been shown to obtain a comparable performance with experts. The CTG information, together with the patient information and labour events, are collectively passed to an expert system for processing. The expert system interprets this combined data using a database of over 400 rules which are used to recommend action. Importantly, as the knowledge is rule-based, it allows the system to explain the reasoning which led it to recommend a certain action. In this way, the clinician is not expected to blindly follow the system's recommendations but can reach an informed judgement in the same way they might by discussing the case with an experienced informed colleague. After two internal evaluations had found the system obtained a performance comparable with local experts, an extensive external validation was undertaken. This study involved 17 experts from 16 leading centres within the UK. Each expert and the system reviewed 50 cases twice, at least one month apart which contained those CTGs considered most difficult to interpret selected from a database of 2400 high-risk labours. This study found that the majority of experts agreed well and were consistent in their management of the cases. The system obtained a performance that was indistinguishable from the experts, except it was more consistent, even when used by an engineer with little knowledge of labour management. This study demonstrates the potential for intelligent systems to transform the cardiotocograph from a difficult-to-use, ineffective recorder of fetal heart rate, to an interactive and effective decision support tool capable of raising the skills of staff.
How well can a sequence of frames be represented by a subset of the frames? Video sequences of American Sign Language (ASL) were investigated in two modes: dynamic (ordinary video) and static (frames printed side by side on the display). An activity index was used to choose critical frames at event boundaries, times when the difference between successive frames is at a local minimum. Sign intelligibility was measured for 32 experienced ASL signers who viewed individual signs. For full gray-scale dynamic signs activity-index subsampling yielded sequences that were significantly more intelligible than when every mth frame was chosen. This result was even more pronounced for static images. For binary images, the relative advantage of activity subsampling was smaller. We conclude that event boundaries can be defined computationally and that subsampling from event boundaries is better than choosing at regular intervals.
This study tested the hypothesis that short-term memory (STM) capacity moderates the effect of social deviance on alcohol problems. Personality, cognitive ability, and alcohol use and abuse were assessed in the adult offspring of alcoholics (FHPs; n = 153) and the adult offspring of nonalcoholics (FHNs; n = 150). The results revealed that STM capacity moderated the effect of social deviance on alcohol problems, independent of intelligence. High social deviance and high-STM participants had fewer alcohol problems than did high social deviance and low-STM participants. Intelligence also moderated the effect of social deviance on alcohol problems in the same way, independent of STM capacity. FHPs had lower IQs, lower verbal ability, and more response perseveration than FHNs. The results suggest that working memory capacity moderates the risk for alcoholism associated with disinhibited traits.
Although a 2-factor model has advanced research on the psychopathy construct, a 3-factor model was recently developed that emphasized pathological personality and eliminated antisocial behavior. However, dropping antisocial behavior from the psychopathy construct may not be advantageous. Using a large sample of psychiatric patients from the MacArthur Risk Assessment Study (J. Monahan & H. J. Steadman, 1994), the authors used confirmatory factor analysis to test a 4-factor model of psychopathy, which included interpersonal, affective, and behavioral impulsivity dimensions and an antisocial behavior dimension. Model fit was good for this 4-factor model, even when ethnicity, gender, and intelligence variables were included in the model. Structural equation modeling was used to compare the 3- and 4-factor models in predicting proximal (violence) and distal (intelligence) correlates of psychopathy.
Examination of measurement invariance tests the assumption that the model underlying a set of test scores is directly comparable across groups. The observation of measurement invariance provides fundamental evidence for the inference that scores on a test afford equivalent measurement of the same psychological traits among diverse groups. Groups may be derived from different psychosocial backgrounds or different clinical presentations. In the Wechsler Adult Intelligence Scale-III (WAIS-III)/Wechsler Memory Scale-III (WMS-III) Technical Manual (Psychological Corporation, 2002), there appears to be a breakdown in factor structure among the standardization cases in older adults. In this study, the authors evaluated the invariance of the measurement model of the WAIS-III across 5 age bands. All components of the measurement model were examined. Overall, the evidence pointed to invariance across age of a modified 4-factor model that included cross-loadings for the Similarities and Arithmetic subtests. These results support the utility of the WAIS-III as a measure of stable intelligence traits across a wide age range.
The Northwestern University Auditory Test Number 6 (NU-6) measure of speech discrimination was time compressed and presented to four age groups ranging from 54 to 84 years of age. Experimental stimuli were presented at sensation levels of 24, 32, and 40 dB to an equal number of right and left ears and male and female subjects. Results indicated that intelligibility decreased as a function of increasing time compression and age and decreasing sensation level. Changes in speech intelligibility associated with the aging process appear to be closely allied to changes in the temporal resolving power of the central auditory processing system.