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.
An artificial-intelligence-based nursing knowledge base can serve as an expert clinical decision support system in the areas of standards of care, care plans, continuing education, and others for patient conditions with both medical and nursing diagnoses.
This study presents a robust control system for a linear ceramic motor (LCM) that is driven by a high-frequency voltage source inverter using two-inductance two-capacitance (LLCC) resonant technique. The structure and driving principle of the LCM are introduced. Because the dynamic characteristics and motor parameters of the LCM are nonlinear and time varying, a robust control system is designed based on the hypothetical dynamic model to achieve high-precision position control. The presentation of robust control for the LCM drive system is divided into three parts, which comprise state feedback controller, feed-forward controller, and uncertainty controller. The adaptation laws of control gains in the robust control system are derived in the sense of Lyapunov stability theorem such that the stability of the control system can be guaranteed. It not only has the learning ability similar to intelligent control, but also its control framework is more simple than intelligent control. With the proposed robust control system, the controlled LCM drive possesses the advantages of good tracking control performance and robustness to uncertainties. The effectiveness of the proposed robust control system is verified by experimental results in the presence of uncertainties. In addition, the advantages of the proposed control system are indicated in comparison with the traditional integral-proportional (IP) position control system.
Sensorial analysis based on the utilisation of human senses, is one of the most important and straightforward investigation methods in food and chemical analysis. An electronic nose has been used to detect in vivo Urinary Tract Infections from 45 suspected cases that were sent for analysis in a UK Health Laboratory environment. These samples were analysed by incubation in a volatile generation test tube system for 4-5 h. The volatile production patterns were then analysed using an electronic nose system with 14 conducting polymer sensors. An intelligent model consisting of an odour generation mechanism, rapid volatile delivery and recovery system, and a classifier system based on learning techniques has been considered. The implementation of an Extended Normalised Radial Basis Function network with advanced features for determining its size and parameters and the concept of fusion of multiple classifiers dedicated to specific feature parameters has been also adopted in this study. The proposed scheme achieved a very high classification rate of the testing dataset, demonstrating in this way the efficiency of the proposed scheme compared with other approaches. This study has shown the potential for early detection of microbial contaminants in urine samples using electronic nose technology.
We present an approach for designing a knowledge-based system, called Sequence Acquisition In Context (SAIC), that will be able to cooperate with a biologist in the analysis of DNA sequences. The main task of the system is the acquisition of the expert knowledge that the biologist uses for solving ambiguities from gel autoradiograms, with the aim of re-using it later for solving similar ambiguities. The various types of expert knowledge constitute what we call the contextual knowledge of the sequence analysis. Contextual knowledge deals with the unavoidable problems that are common in the study of the living material (eg noise on data, difficulties of observations). Indeed, the analysis of DNA sequences from autoradiograms belongs to an emerging and promising area of investigation, namely reasoning with images. The SAIC project is developed in a theoretical framework that is shared with other applications. Not all tasks have the same importance in each application. We use this observation for designing an intelligent assistant system with three applications. In the SAIC project, we focus on knowledge acquisition, human-computer interaction and explanation. The project will benefit research in the two other applications. We also discuss our SAIC project in the context of large international projects that aim to re-use and share knowledge in a repository.
This paper describes the framework of a real-time simulation system to model human behavior and reactions in dangerous environments. The system utilizes the latest 3D computer animation techniques, combined with artificial intelligence, robotics and psychology, to model human behavior, reactions and decision making under expected/unexpected dangers in real-time in virtual environments. The development of the system includes: classification on the conscious/subconscious behaviors and reactions of different people; capturing different motion postures by the Eagle Digital System; establishing 3D character animation models; establishing 3D models for the scene; planning the scenario and the contents; and programming within Virtools Dev. Programming within Virtools Dev is subdivided into modeling dangerous events, modeling character's perceptions, modeling character's decision making, modeling character's movements, modeling character's interaction with environment and setting up the virtual cameras. The real-time simulation of human reactions in hazardous environments is invaluable in military defense, fire escape, rescue operation planning, traffic safety studies, and safety planning in chemical factories, the design of buildings, airplanes, ships and trains. Currently, human motion modeling can be realized through established technology, whereas to integrate perception and intelligence into virtual human's motion is still a huge undertaking. The challenges here are the synchronization of motion and intelligence, the accurate modeling of human's vision, smell, touch and hearing, the diversity and effects of emotion and personality in decision making. There are three types of software platforms which could be employed to realize the motion and intelligence within one system, and their advantages and disadvantages are discussed.
Rapid changes in healthcare coupled with parallel advances in technology have stimulated the evolution of new approaches for laboratory automation. In particular, the emergence of commercially available laboratory robotic systems offers promise for streamlining the clinical laboratory. Increasing cost-containment pressures make the application of this technology extremely attractive, and several organizations have begun to systematically integrate robotic devices into their laboratory automation schemes. Integration of these technologies, however, presents many challenges for software developers, instrument manufacturers, and laboratory workers. Differing needs across laboratories require flexibility and intelligence in robots, instruments, and control systems. Standardization of mechanical and electronic interfaces will be key to making these systems easy to integrate. Systems engineering, aided by simulation modeling and artificial intelligence schemes, will be important to assist in the design of optimal configurations. Software for the overall control of integrated automation will be needed that can be tailored by the laboratorian to fit the requirements of the individual laboratory. Thus, laboratory workers will need to be actively involved in implementing this new wave of laboratory automation, becoming well-versed in computers, electronics, and systems engineering.
Explore the source record for details and available documents.
The inability of many clinical decision-support applications to integrate with existing databases limits the wide-scale deployment of such systems. To overcome this obstacle, we have designed a data-interpretation module that can be embedded in a general architecture for protocol-based reasoning and that can support the fundamental task of detecting temporal abstractions. We have developed this software module by coupling two existing systems--RESUME and Chronus--that provide complementary temporal-abstraction techniques at the application and the database levels, respectively. Their encapsulation into a single module thus can resolve the temporal queries of protocol planners with the domain-specific knowledge needed for the temporal-abstraction task and with primary time-stamped data stored in autonomous clinical databases. We show that other computer methods for the detection of temporal abstractions do not scale up to the data- and knowledge-intensive environments of protocol-based decision-support systems.
Easier and focused access to healthcare information can empower individuals to make 'informed' choices and judgements about personal health maintenance. To achieve 'optimum' patient empowerment, we need to re-evaluate and potentially re-design the processes of healthcare information delivery. Our suggestion is that healthcare information should be personalised according to each individual's healthcare needs and it should be pro-actively delivered, i.e. pushed towards the individual. We present an intelligent Personalised Healthcare Information Delivery Systems that aims to enhance patient empowerment by pro-actively pushing customised, based on one's Electronic Medical Record, health maintenance information via the WWW.
An easy and rapid test system is reported for the quantitative assessment of speech intelligibility following laryngectomy. 20 changing randomised monosyllables and 5 changing sentences are spoken by the patient into a telephone with the investigator listening in without visual contact with the patient. The number of correctly understood words and sentences is determined. Reliability and validity of the linguistic pool as well as reproducibility of the test system can be demonstrated.
A general theory is proposed that attributes the origins of human intelligence to an expansion of dopaminergic systems in human cognition. Dopamine is postulated to be the key neurotransmitter regulating six predominantly left-hemispheric cognitive skills critical to human language and thought: motor planning, working memory, cognitive flexibility, abstract reasoning, temporal analysis/sequencing, and generativity. A dopaminergic expansion during early hominid evolution could have enabled successful chase-hunting in the savannas of sub-Saharan Africa, given the critical role of dopamine in counteracting hyperthermia during endurance activity. In turn, changes in physical activity and diet may have further increased cortical dopamine levels by augmenting tyrosine and its conversion to dopamine in the central nervous system (CNS). By means of the regulatory action of dopamine and other substances, the physiological and dietary changes may have contributed to the vertical elongation of the body, increased brain size, and increased cortical convolutedness that occurred during human evolution. Finally, emphasizing the role of dopamine in human intelligence may offer a new perspective on the advanced cognitive reasoning skills in nonprimate lineages such as cetaceans and avians, whose cortical anatomy differs radically from that of primates.
Computer literacy is justified and defined in terms of core knowledge about fundamental problem-solving methods for information processing (not as computer languages, hardware characteristics, and so on). These core principles provide a solid grounding that will remain essentially applicable and valid over time. Some of the most powerful methods are used to create expert systems applications, simulations, and database management systems.
Knowledge-based expert systems for medical applications have received considerable attention in recent years. In this review, fundamental terms and notions of artificial intelligence techniques as applied to expert systems are introduced. The most well-known and influential medical expert systems are discussed in detail, and newer efforts are surveyed. A critical comparison of strengths and weaknesses of the systems is made, discussing depth and complexity of knowledge, acquisition of knowledge, user interaction and explanations, knowledge engineering tools, system evaluations, and user resistance. Long- and short-term trends are appraised.
The New York State Department of Health has created a data warehouse to analyze and evaluate the Medicaid managed care program. Online query tools and reports, grouping tools such as Diagnostic Related Groups, and measurement tools such as Health Plan Data and Information Set (HEDIS) measures have been incorporated into the data warehouse. Other public health data sets including birth certificate data have also been integrated. The result is a powerful data set that can analyze information quickly and efficiently, with built-in data intelligence. Developed over time, this system can provide states, health insurance companies, and health data consortiums a roadmap on how to implement an integrated data warehouse solution.
OBJECTIVE: The objectives of our study were (1) to implement intelligent respiratory alarms with a neural network; and (2) to increase alarm specificity and decrease false-alarm rates compared with current alarms. METHODS: We trained a neural network to recognize 13 faults in an anesthesia breathing circuit. The system extracted 30 breath-to-breath features from the airway CO2, flow, and pressure signals. We created training data for the network by introducing 13 faults repeatedly in 5 dogs (616 total faults). We used the data to train the neural network using the backward error propagation algorithm. RESULTS: In animals, the trained network reported the alarms correctly for 95.0% of the faults when tested during controlled ventilation, and for 86.9% of the faults during spontaneous breathing. When tested in the operating room, the system found and correctly reported 54 of 57 faults that occurred during 43.6 hr of use. The alarm system produced a total of 74 false alarms during 43.6 hr of monitoring. CONCLUSION: Neural networks may be useful in creating intelligent anesthesia alarm systems.
For a knowledge-based system (KBS) to exhibit an intelligent behavior, it must be endowed with knowledge enabling it to represent the expert's strategies. The elicitation task is inherently difficult for strategic knowledge, because strategy is often tacit, and, even when it has been made explicit, it is not an easy task to describe it in a form which may be directly translated and implemented into a program. This paper describes a Specialized Framework for Medical Diagnostic Knowledge-Based Systems that can help an expert in the process of building KBSs in a medical domain. The framework is based on an epistemological model of diagnostic reasoning which has proven to be helpful in describing the diagnostic process in terms of the tasks that it is composed of. It allows a straightforward modeling of diagnostic reasoning at the knowledge level by the domain expert, thus helping to convey domain-dependent strategies into the target KBS.
This article uses a socioecological analytical approach to assess the capacity of the public health nutrition work force in Australia as a prelude to work force development strategy planning. It demonstrates how the socioecological model can be used to assess and inform the development of the infrastructure required for effective public health nutrition effort. An interpretive case study method was used involving triangular analysis of quantitative and qualitative data from multiple sources including semistructured interviews with advanced-level practitioners, literature review, a cross-sectional national work force survey, and position description audit and consensus development using a Delphi study. The findings of this analysis indicate that the Australian public health nutrition work force's capacity to effectively address priority nutrition issues is limited by determinants that can be categorized as relating to human resource infrastructure, organizational and policy environments, intelligence access and use, practice improvement and learning systems, and work force preparation. This socioecological analysis supports an intelligence-based focus for work force development effort in Australia and a conceptual framework for work force capacity assessment with potential applications in other countries.
A novel method to interpret two-dimensional electrophoresis gels is presented. Genetic background and electrophoretic processes are summarized. Present methods to analyze gel images and to exploit series of gels are described, then their drawbacks are outlined. Artificial Intelligence techniques are introduced to build an image interpretation system which can compensate for certain failures of present methods and augment their efficiency. By reproducing methods of biological experts, this system automatically identifies proteins--whether isolated or inside constellations--on an electrophoretic gel. This system is based on a modular architecture, featuring image processing procedures, which allows extraction of parameters on the image and a top-down and bottom-up reasoning process. The reasoning process first matches extracted parameters to possible geometric models of proteins; it then returns to the image to determine possible missing elements on the gel. A prototype of this system was implemented and tested on plasma gels to identify apolipoproteins.